thevar1able/ClickHouse
1
0
Fork 0
mirror of https://github.com/ClickHouse/ClickHouse.git synced 2024-11-24 16:42:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'master' into feature/create-simple-lambda-function

Browse Source
This commit is contained in:
Realist007 2021-07-21 10:33:53 +03:00 committed by GitHub
commit 31e26862b5
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
777 changed files with 17748 additions and 7698 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
.github/PULL_REQUEST_TEMPLATE.md vendored
View File

@ -2,25 +2,23 @@ I hereby agree to the terms of the CLA available at: https://yandex.ru/legal/cla
Changelog category (leave one): Changelog category (leave one):
- New Feature - New Feature
- Bug Fix
- Improvement - Improvement
- Bug Fix
- Performance Improvement - Performance Improvement
- Backward Incompatible Change - Backward Incompatible Change
- Build/Testing/Packaging Improvement - Build/Testing/Packaging Improvement
- Documentation (changelog entry is not required) - Documentation (changelog entry is not required)
- Other
- Not for changelog (changelog entry is not required) - Not for changelog (changelog entry is not required)
Changelog entry (a user-readable short description of the changes that goes to CHANGELOG.md): Changelog entry (a user-readable short description of the changes that goes to CHANGELOG.md):
... ...
Detailed description / Documentation draft: Detailed description / Documentation draft:
... ...
By adding documentation, you'll allow users to try your new feature immediately, not when someone else will have time to document it later. Documentation is necessary for all features that affect user experience in any way. You can add brief documentation draft above, or add documentation right into your patch as Markdown files in [docs](https://github.com/ClickHouse/ClickHouse/tree/master/docs) folder. By adding documentation, you'll allow users to try your new feature immediately, not when someone else will have time to document it later. Documentation is necessary for all features that affect user experience in any way. You can add brief documentation draft above, or add documentation right into your patch as Markdown files in [docs](https://github.com/ClickHouse/ClickHouse/tree/master/docs) folder.
If you are doing this for the first time, it's recommended to read the lightweight [Contributing to ClickHouse Documentation](https://github.com/ClickHouse/ClickHouse/tree/master/docs/README.md) guide first. If you are doing this for the first time, it's recommended to read the lightweight [Contributing to ClickHouse Documentation](https://github.com/ClickHouse/ClickHouse/tree/master/docs/README.md) guide first.

8
.gitmodules vendored
View File

@ -193,7 +193,7 @@
url = https://github.com/danlark1/miniselect url = https://github.com/danlark1/miniselect
[submodule "contrib/rocksdb"] [submodule "contrib/rocksdb"]
path = contrib/rocksdb path = contrib/rocksdb
url = https://github.com/ClickHouse-Extras/rocksdb.git url = https://github.com/ClickHouse-Extras/rocksdb.git
[submodule "contrib/xz"] [submodule "contrib/xz"]
path = contrib/xz path = contrib/xz
url = https://github.com/xz-mirror/xz url = https://github.com/xz-mirror/xz
@ -228,3 +228,9 @@
[submodule "contrib/libpqxx"] [submodule "contrib/libpqxx"]
path = contrib/libpqxx path = contrib/libpqxx
url = https://github.com/ClickHouse-Extras/libpqxx.git url = https://github.com/ClickHouse-Extras/libpqxx.git
[submodule "contrib/sqlite-amalgamation"]
path = contrib/sqlite-amalgamation
url = https://github.com/azadkuh/sqlite-amalgamation
[submodule "contrib/s2geometry"]
path = contrib/s2geometry
url = https://github.com/ClickHouse-Extras/s2geometry.git

156
CHANGELOG.md
View File

@ -1,3 +1,159 @@
### ClickHouse release v21.7, 2021-07-09
#### Backward Incompatible Change
* Improved performance of queries with explicitly defined large sets. Added compatibility setting `legacy_column_name_of_tuple_literal`. It makes sense to set it to `true`, while doing rolling update of cluster from version lower than 21.7 to any higher version. Otherwise distributed queries with explicitly defined sets at `IN` clause may fail during update. [#25371](https://github.com/ClickHouse/ClickHouse/pull/25371) ([Anton Popov](https://github.com/CurtizJ)).
* Forward/backward incompatible change of maximum buffer size in clickhouse-keeper (an experimental alternative to ZooKeeper). Better to do it now (before production), than later. [#25421](https://github.com/ClickHouse/ClickHouse/pull/25421) ([alesapin](https://github.com/alesapin)).
#### New Feature
* Support configuration in YAML format as alternative to XML. This closes [#3607](https://github.com/ClickHouse/ClickHouse/issues/3607). [#21858](https://github.com/ClickHouse/ClickHouse/pull/21858) ([BoloniniD](https://github.com/BoloniniD)).
* Provides a way to restore replicated table when the data is (possibly) present, but the ZooKeeper metadata is lost. Resolves [#13458](https://github.com/ClickHouse/ClickHouse/issues/13458). [#13652](https://github.com/ClickHouse/ClickHouse/pull/13652) ([Mike Kot](https://github.com/myrrc)).
* Support structs and maps in Arrow/Parquet/ORC and dictionaries in Arrow input/output formats. Present new setting `output_format_arrow_low_cardinality_as_dictionary`. [#24341](https://github.com/ClickHouse/ClickHouse/pull/24341) ([Kruglov Pavel](https://github.com/Avogar)).
* Added support for `Array` type in dictionaries. [#25119](https://github.com/ClickHouse/ClickHouse/pull/25119) ([Maksim Kita](https://github.com/kitaisreal)).
* Added function `bitPositionsToArray`. Closes [#23792](https://github.com/ClickHouse/ClickHouse/issues/23792). Author [Kevin Wan] (@MaxWk). [#25394](https://github.com/ClickHouse/ClickHouse/pull/25394) ([Maksim Kita](https://github.com/kitaisreal)).
* Added function `dateName` to return names like 'Friday' or 'April'. Author [Daniil Kondratyev] (@dankondr). [#25372](https://github.com/ClickHouse/ClickHouse/pull/25372) ([Maksim Kita](https://github.com/kitaisreal)).
* Add `toJSONString` function to serialize columns to their JSON representations. [#25164](https://github.com/ClickHouse/ClickHouse/pull/25164) ([Amos Bird](https://github.com/amosbird)).
* Now `query_log` has two new columns: `initial_query_start_time`, `initial_query_start_time_microsecond` that record the starting time of a distributed query if any. [#25022](https://github.com/ClickHouse/ClickHouse/pull/25022) ([Amos Bird](https://github.com/amosbird)).
* Add aggregate function `segmentLengthSum`. [#24250](https://github.com/ClickHouse/ClickHouse/pull/24250) ([flynn](https://github.com/ucasfl)).
* Add a new boolean setting `prefer_global_in_and_join` which defaults all IN/JOIN as GLOBAL IN/JOIN. [#23434](https://github.com/ClickHouse/ClickHouse/pull/23434) ([Amos Bird](https://github.com/amosbird)).
* Support `ALTER DELETE` queries for `Join` table engine. [#23260](https://github.com/ClickHouse/ClickHouse/pull/23260) ([foolchi](https://github.com/foolchi)).
* Add `quantileBFloat16` aggregate function as well as the corresponding `quantilesBFloat16` and `medianBFloat16`. It is very simple and fast quantile estimator with relative error not more than 0.390625%. This closes [#16641](https://github.com/ClickHouse/ClickHouse/issues/16641). [#23204](https://github.com/ClickHouse/ClickHouse/pull/23204) ([Ivan Novitskiy](https://github.com/RedClusive)).
* Implement `sequenceNextNode()` function useful for `flow analysis`. [#19766](https://github.com/ClickHouse/ClickHouse/pull/19766) ([achimbab](https://github.com/achimbab)).
#### Experimental Feature
* Add support for virtual filesystem over HDFS. [#11058](https://github.com/ClickHouse/ClickHouse/pull/11058) ([overshov](https://github.com/overshov)) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Now clickhouse-keeper (an experimental alternative to ZooKeeper) supports ZooKeeper-like `digest` ACLs. [#24448](https://github.com/ClickHouse/ClickHouse/pull/24448) ([alesapin](https://github.com/alesapin)).
#### Performance Improvement
* Added optimization that transforms some functions to reading of subcolumns to reduce amount of read data. E.g., statement `col IS NULL` is transformed to reading of subcolumn `col.null`. Optimization can be enabled by setting `optimize_functions_to_subcolumns` which is currently off by default. [#24406](https://github.com/ClickHouse/ClickHouse/pull/24406) ([Anton Popov](https://github.com/CurtizJ)).
* Rewrite more columns to possible alias expressions. This may enable better optimization, such as projections. [#24405](https://github.com/ClickHouse/ClickHouse/pull/24405) ([Amos Bird](https://github.com/amosbird)).
* Index of type `bloom_filter` can be used for expressions with `hasAny` function with constant arrays. This closes: [#24291](https://github.com/ClickHouse/ClickHouse/issues/24291). [#24900](https://github.com/ClickHouse/ClickHouse/pull/24900) ([Vasily Nemkov](https://github.com/Enmk)).
* Add exponential backoff to reschedule read attempt in case RabbitMQ queues are empty. (ClickHouse has support for importing data from RabbitMQ). Closes [#24340](https://github.com/ClickHouse/ClickHouse/issues/24340). [#24415](https://github.com/ClickHouse/ClickHouse/pull/24415) ([Kseniia Sumarokova](https://github.com/kssenii)).
#### Improvement
* Allow to limit bandwidth for replication. Add two Replicated\*MergeTree settings: `max_replicated_fetches_network_bandwidth` and `max_replicated_sends_network_bandwidth` which allows to limit maximum speed of replicated fetches/sends for table. Add two server-wide settings (in `default` user profile): `max_replicated_fetches_network_bandwidth_for_server` and `max_replicated_sends_network_bandwidth_for_server` which limit maximum speed of replication for all tables. The settings are not followed perfectly accurately. Turned off by default. Fixes [#1821](https://github.com/ClickHouse/ClickHouse/issues/1821). [#24573](https://github.com/ClickHouse/ClickHouse/pull/24573) ([alesapin](https://github.com/alesapin)).
* Resource constraints and isolation for ODBC and Library bridges. Use separate `clickhouse-bridge` group and user for bridge processes. Set oom_score_adj so the bridges will be first subjects for OOM killer. Set set maximum RSS to 1 GiB. Closes [#23861](https://github.com/ClickHouse/ClickHouse/issues/23861). [#25280](https://github.com/ClickHouse/ClickHouse/pull/25280) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Add standalone `clickhouse-keeper` symlink to the main `clickhouse` binary. Now it's possible to run coordination without the main clickhouse server. [#24059](https://github.com/ClickHouse/ClickHouse/pull/24059) ([alesapin](https://github.com/alesapin)).
* Use global settings for query to `VIEW`. Fixed the behavior when queries to `VIEW` use local settings, that leads to errors if setting on `CREATE VIEW` and `SELECT` were different. As for now, `VIEW` won't use these modified settings, but you can still pass additional settings in `SETTINGS` section of `CREATE VIEW` query. Close [#20551](https://github.com/ClickHouse/ClickHouse/issues/20551). [#24095](https://github.com/ClickHouse/ClickHouse/pull/24095) ([Vladimir](https://github.com/vdimir)).
* On server start, parts with incorrect partition ID would not be ever removed, but always detached. [#25070](https://github.com/ClickHouse/ClickHouse/issues/25070). [#25166](https://github.com/ClickHouse/ClickHouse/pull/25166) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Increase size of background schedule pool to 128 (`background_schedule_pool_size` setting). It allows avoiding replication queue hung on slow zookeeper connection. [#25072](https://github.com/ClickHouse/ClickHouse/pull/25072) ([alesapin](https://github.com/alesapin)).
* Add merge tree setting `max_parts_to_merge_at_once` which limits the number of parts that can be merged in the background at once. Doesn't affect `OPTIMIZE FINAL` query. Fixes [#1820](https://github.com/ClickHouse/ClickHouse/issues/1820). [#24496](https://github.com/ClickHouse/ClickHouse/pull/24496) ([alesapin](https://github.com/alesapin)).
* Allow `NOT IN` operator to be used in partition pruning. [#24894](https://github.com/ClickHouse/ClickHouse/pull/24894) ([Amos Bird](https://github.com/amosbird)).
* Recognize IPv4 addresses like `127.0.1.1` as local. This is controversial and closes [#23504](https://github.com/ClickHouse/ClickHouse/issues/23504). Michael Filimonov will test this feature. [#24316](https://github.com/ClickHouse/ClickHouse/pull/24316) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* ClickHouse database created with MaterializeMySQL (it is an experimental feature) now contains all column comments from the MySQL database that materialized. [#25199](https://github.com/ClickHouse/ClickHouse/pull/25199) ([Storozhuk Kostiantyn](https://github.com/sand6255)).
* Add settings (`connection_auto_close`/`connection_max_tries`/`connection_pool_size`) for MySQL storage engine. [#24146](https://github.com/ClickHouse/ClickHouse/pull/24146) ([Azat Khuzhin](https://github.com/azat)).
* Improve startup time of Distributed engine. [#25663](https://github.com/ClickHouse/ClickHouse/pull/25663) ([Azat Khuzhin](https://github.com/azat)).
* Improvement for Distributed tables. Drop replicas from dirname for internal_replication=true (allows INSERT into Distributed with cluster from any number of replicas, before only 15 replicas was supported, everything more will fail with ENAMETOOLONG while creating directory for async blocks). [#25513](https://github.com/ClickHouse/ClickHouse/pull/25513) ([Azat Khuzhin](https://github.com/azat)).
* Added support `Interval` type for `LowCardinality`. It is needed for intermediate values of some expressions. Closes [#21730](https://github.com/ClickHouse/ClickHouse/issues/21730). [#25410](https://github.com/ClickHouse/ClickHouse/pull/25410) ([Vladimir](https://github.com/vdimir)).
* Add `==` operator on time conditions for `sequenceMatch` and `sequenceCount` functions. For eg: sequenceMatch('(?1)(?t==1)(?2)')(time, data = 1, data = 2). [#25299](https://github.com/ClickHouse/ClickHouse/pull/25299) ([Christophe Kalenzaga](https://github.com/mga-chka)).
* Add settings `http_max_fields`, `http_max_field_name_size`, `http_max_field_value_size`. [#25296](https://github.com/ClickHouse/ClickHouse/pull/25296) ([Ivan](https://github.com/abyss7)).
* Add support for function `if` with `Decimal` and `Int` types on its branches. This closes [#20549](https://github.com/ClickHouse/ClickHouse/issues/20549). This closes [#10142](https://github.com/ClickHouse/ClickHouse/issues/10142). [#25283](https://github.com/ClickHouse/ClickHouse/pull/25283) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Update prompt in `clickhouse-client` and display a message when reconnecting. This closes [#10577](https://github.com/ClickHouse/ClickHouse/issues/10577). [#25281](https://github.com/ClickHouse/ClickHouse/pull/25281) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Correct memory tracking in aggregate function `topK`. This closes [#25259](https://github.com/ClickHouse/ClickHouse/issues/25259). [#25260](https://github.com/ClickHouse/ClickHouse/pull/25260) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Fix `topLevelDomain` for IDN hosts (i.e. `example.рф`), before it returns empty string for such hosts. [#25103](https://github.com/ClickHouse/ClickHouse/pull/25103) ([Azat Khuzhin](https://github.com/azat)).
* Detect Linux kernel version at runtime (for worked nested epoll, that is required for `async_socket_for_remote`/`use_hedged_requests`, otherwise remote queries may stuck). [#25067](https://github.com/ClickHouse/ClickHouse/pull/25067) ([Azat Khuzhin](https://github.com/azat)).
* For distributed query, when `optimize_skip_unused_shards=1`, allow to skip shard with condition like `(sharding key) IN (one-element-tuple)`. (Tuples with many elements were supported. Tuple with single element did not work because it is parsed as literal). [#24930](https://github.com/ClickHouse/ClickHouse/pull/24930) ([Amos Bird](https://github.com/amosbird)).
* Improved log messages of S3 errors, no more double whitespaces in case of empty keys and buckets. [#24897](https://github.com/ClickHouse/ClickHouse/pull/24897) ([Vladimir Chebotarev](https://github.com/excitoon)).
* Some queries require multi-pass semantic analysis. Try reusing built sets for `IN` in this case. [#24874](https://github.com/ClickHouse/ClickHouse/pull/24874) ([Amos Bird](https://github.com/amosbird)).
* Respect `max_distributed_connections` for `insert_distributed_sync` (otherwise for huge clusters and sync insert it may run out of `max_thread_pool_size`). [#24754](https://github.com/ClickHouse/ClickHouse/pull/24754) ([Azat Khuzhin](https://github.com/azat)).
* Avoid hiding errors like `Limit for rows or bytes to read exceeded` for scalar subqueries. [#24545](https://github.com/ClickHouse/ClickHouse/pull/24545) ([nvartolomei](https://github.com/nvartolomei)).
* Make String-to-Int parser stricter so that `toInt64('+')` will throw. [#24475](https://github.com/ClickHouse/ClickHouse/pull/24475) ([Amos Bird](https://github.com/amosbird)).
* If `SSD_CACHE` is created with DDL query, it can be created only inside `user_files` directory. [#24466](https://github.com/ClickHouse/ClickHouse/pull/24466) ([Maksim Kita](https://github.com/kitaisreal)).
* PostgreSQL support for specifying non default schema for insert queries. Closes [#24149](https://github.com/ClickHouse/ClickHouse/issues/24149). [#24413](https://github.com/ClickHouse/ClickHouse/pull/24413) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix IPv6 addresses resolving (i.e. fixes `select * from remote('[::1]', system.one)`). [#24319](https://github.com/ClickHouse/ClickHouse/pull/24319) ([Azat Khuzhin](https://github.com/azat)).
* Fix trailing whitespaces in FROM clause with subqueries in multiline mode, and also changes the output of the queries slightly in a more human friendly way. [#24151](https://github.com/ClickHouse/ClickHouse/pull/24151) ([Azat Khuzhin](https://github.com/azat)).
* Improvement for Distributed tables. Add ability to split distributed batch on failures (i.e. due to memory limits, corruptions), under `distributed_directory_monitor_split_batch_on_failure` (OFF by default). [#23864](https://github.com/ClickHouse/ClickHouse/pull/23864) ([Azat Khuzhin](https://github.com/azat)).
* Handle column name clashes for `Join` table engine. Closes [#20309](https://github.com/ClickHouse/ClickHouse/issues/20309). [#23769](https://github.com/ClickHouse/ClickHouse/pull/23769) ([Vladimir](https://github.com/vdimir)).
* Display progress for `File` table engine in `clickhouse-local` and on INSERT query in `clickhouse-client` when data is passed to stdin. Closes [#18209](https://github.com/ClickHouse/ClickHouse/issues/18209). [#23656](https://github.com/ClickHouse/ClickHouse/pull/23656) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Bugfixes and improvements of `clickhouse-copier`. Allow to copy tables with different (but compatible schemas). Closes [#9159](https://github.com/ClickHouse/ClickHouse/issues/9159). Added test to copy ReplacingMergeTree. Closes [#22711](https://github.com/ClickHouse/ClickHouse/issues/22711). Support TTL on columns and Data Skipping Indices. It simply removes it to create internal Distributed table (underlying table will have TTL and skipping indices). Closes [#19384](https://github.com/ClickHouse/ClickHouse/issues/19384). Allow to copy MATERIALIZED and ALIAS columns. There are some cases in which it could be helpful (e.g. if this column is in PRIMARY KEY). Now it could be allowed by setting `allow_to_copy_alias_and_materialized_columns` property to true in task configuration. Closes [#9177](https://github.com/ClickHouse/ClickHouse/issues/9177). Closes [#11007] (https://github.com/ClickHouse/ClickHouse/issues/11007). Closes [#9514](https://github.com/ClickHouse/ClickHouse/issues/9514). Added a property `allow_to_drop_target_partitions` in task configuration to drop partition in original table before moving helping tables. Closes [#20957](https://github.com/ClickHouse/ClickHouse/issues/20957). Get rid of `OPTIMIZE DEDUPLICATE` query. This hack was needed, because `ALTER TABLE MOVE PARTITION` was retried many times and plain MergeTree tables don't have deduplication. Closes [#17966](https://github.com/ClickHouse/ClickHouse/issues/17966). Write progress to ZooKeeper node on path `task_path + /status` in JSON format. Closes [#20955](https://github.com/ClickHouse/ClickHouse/issues/20955). Support for ReplicatedTables without arguments. Closes [#24834](https://github.com/ClickHouse/ClickHouse/issues/24834) .[#23518](https://github.com/ClickHouse/ClickHouse/pull/23518) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Added sleep with backoff between read retries from S3. [#23461](https://github.com/ClickHouse/ClickHouse/pull/23461) ([Vladimir Chebotarev](https://github.com/excitoon)).
* Respect `insert_allow_materialized_columns` (allows materialized columns) for INSERT into `Distributed` table. [#23349](https://github.com/ClickHouse/ClickHouse/pull/23349) ([Azat Khuzhin](https://github.com/azat)).
* Add ability to push down LIMIT for distributed queries. [#23027](https://github.com/ClickHouse/ClickHouse/pull/23027) ([Azat Khuzhin](https://github.com/azat)).
* Fix zero-copy replication with several S3 volumes (Fixes [#22679](https://github.com/ClickHouse/ClickHouse/issues/22679)). [#22864](https://github.com/ClickHouse/ClickHouse/pull/22864) ([ianton-ru](https://github.com/ianton-ru)).
* Resolve the actual port number bound when a user requests any available port from the operating system to show it in the log message. [#25569](https://github.com/ClickHouse/ClickHouse/pull/25569) ([bnaecker](https://github.com/bnaecker)).
* Fixed case, when sometimes conversion of postgres arrays resulted in String data type, not n-dimensional array, because `attndims` works incorrectly in some cases. Closes [#24804](https://github.com/ClickHouse/ClickHouse/issues/24804). [#25538](https://github.com/ClickHouse/ClickHouse/pull/25538) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix convertion of DateTime with timezone for MySQL, PostgreSQL, ODBC. Closes [#5057](https://github.com/ClickHouse/ClickHouse/issues/5057). [#25528](https://github.com/ClickHouse/ClickHouse/pull/25528) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Distinguish KILL MUTATION for different tables (fixes unexpected `Cancelled mutating parts` error). [#25025](https://github.com/ClickHouse/ClickHouse/pull/25025) ([Azat Khuzhin](https://github.com/azat)).
* Allow to declare S3 disk at root of bucket (S3 virtual filesystem is an experimental feature under development). [#24898](https://github.com/ClickHouse/ClickHouse/pull/24898) ([Vladimir Chebotarev](https://github.com/excitoon)).
* Enable reading of subcolumns (e.g. components of Tuples) for distributed tables. [#24472](https://github.com/ClickHouse/ClickHouse/pull/24472) ([Anton Popov](https://github.com/CurtizJ)).
* A feature for MySQL compatibility protocol: make `user` function to return correct output. Closes [#25697](https://github.com/ClickHouse/ClickHouse/pull/25697). [#25697](https://github.com/ClickHouse/ClickHouse/pull/25697) ([sundyli](https://github.com/sundy-li)).
#### Bug Fix
* Improvement for backward compatibility. Use old modulo function version when used in partition key. Closes [#23508](https://github.com/ClickHouse/ClickHouse/issues/23508). [#24157](https://github.com/ClickHouse/ClickHouse/pull/24157) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix extremely rare bug on low-memory servers which can lead to the inability to perform merges without restart. Possibly fixes [#24603](https://github.com/ClickHouse/ClickHouse/issues/24603). [#24872](https://github.com/ClickHouse/ClickHouse/pull/24872) ([alesapin](https://github.com/alesapin)).
* Fix extremely rare error `Tagging already tagged part` in replication queue during concurrent `alter move/replace partition`. Possibly fixes [#22142](https://github.com/ClickHouse/ClickHouse/issues/22142). [#24961](https://github.com/ClickHouse/ClickHouse/pull/24961) ([alesapin](https://github.com/alesapin)).
* Fix potential crash when calculating aggregate function states by aggregation of aggregate function states of other aggregate functions (not a practical use case). See [#24523](https://github.com/ClickHouse/ClickHouse/issues/24523). [#25015](https://github.com/ClickHouse/ClickHouse/pull/25015) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Fixed the behavior when query `SYSTEM RESTART REPLICA` or `SYSTEM SYNC REPLICA` does not finish. This was detected on server with extremely low amount of RAM. [#24457](https://github.com/ClickHouse/ClickHouse/pull/24457) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix bug which can lead to ZooKeeper client hung inside clickhouse-server. [#24721](https://github.com/ClickHouse/ClickHouse/pull/24721) ([alesapin](https://github.com/alesapin)).
* If ZooKeeper connection was lost and replica was cloned after restoring the connection, its replication queue might contain outdated entries. Fixed failed assertion when replication queue contains intersecting virtual parts. It may rarely happen if some data part was lost. Print error in log instead of terminating. [#24777](https://github.com/ClickHouse/ClickHouse/pull/24777) ([tavplubix](https://github.com/tavplubix)).
* Fix lost `WHERE` condition in expression-push-down optimization of query plan (setting `query_plan_filter_push_down = 1` by default). Fixes [#25368](https://github.com/ClickHouse/ClickHouse/issues/25368). [#25370](https://github.com/ClickHouse/ClickHouse/pull/25370) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix bug which can lead to intersecting parts after merges with TTL: `Part all_40_40_0 is covered by all_40_40_1 but should be merged into all_40_41_1. This shouldn't happen often.`. [#25549](https://github.com/ClickHouse/ClickHouse/pull/25549) ([alesapin](https://github.com/alesapin)).
* On ZooKeeper connection loss `ReplicatedMergeTree` table might wait for background operations to complete before trying to reconnect. It's fixed, now background operations are stopped forcefully. [#25306](https://github.com/ClickHouse/ClickHouse/pull/25306) ([tavplubix](https://github.com/tavplubix)).
* Fix error `Key expression contains comparison between inconvertible types` for queries with `ARRAY JOIN` in case if array is used in primary key. Fixes [#8247](https://github.com/ClickHouse/ClickHouse/issues/8247). [#25546](https://github.com/ClickHouse/ClickHouse/pull/25546) ([Anton Popov](https://github.com/CurtizJ)).
* Fix wrong totals for query `WITH TOTALS` and `WITH FILL`. Fixes [#20872](https://github.com/ClickHouse/ClickHouse/issues/20872). [#25539](https://github.com/ClickHouse/ClickHouse/pull/25539) ([Anton Popov](https://github.com/CurtizJ)).
* Fix data race when querying `system.clusters` while reloading the cluster configuration at the same time. [#25737](https://github.com/ClickHouse/ClickHouse/pull/25737) ([Amos Bird](https://github.com/amosbird)).
* Fixed `No such file or directory` error on moving `Distributed` table between databases. Fixes [#24971](https://github.com/ClickHouse/ClickHouse/issues/24971). [#25667](https://github.com/ClickHouse/ClickHouse/pull/25667) ([tavplubix](https://github.com/tavplubix)).
* `REPLACE PARTITION` might be ignored in rare cases if the source partition was empty. It's fixed. Fixes [#24869](https://github.com/ClickHouse/ClickHouse/issues/24869). [#25665](https://github.com/ClickHouse/ClickHouse/pull/25665) ([tavplubix](https://github.com/tavplubix)).
* Fixed a bug in `Replicated` database engine that might rarely cause some replica to skip enqueued DDL query. [#24805](https://github.com/ClickHouse/ClickHouse/pull/24805) ([tavplubix](https://github.com/tavplubix)).
* Fix null pointer dereference in `EXPLAIN AST` without query. [#25631](https://github.com/ClickHouse/ClickHouse/pull/25631) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix waiting of automatic dropping of empty parts. It could lead to full filling of background pool and stuck of replication. [#23315](https://github.com/ClickHouse/ClickHouse/pull/23315) ([Anton Popov](https://github.com/CurtizJ)).
* Fix restore of a table stored in S3 virtual filesystem (it is an experimental feature not ready for production). [#25601](https://github.com/ClickHouse/ClickHouse/pull/25601) ([ianton-ru](https://github.com/ianton-ru)).
* Fix nullptr dereference in `Arrow` format when using `Decimal256`. Add `Decimal256` support for `Arrow` format. [#25531](https://github.com/ClickHouse/ClickHouse/pull/25531) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix excessive underscore before the names of the preprocessed configuration files. [#25431](https://github.com/ClickHouse/ClickHouse/pull/25431) ([Vitaly Baranov](https://github.com/vitlibar)).
* A fix for `clickhouse-copier` tool: Fix segfault when sharding_key is absent in task config for copier. [#25419](https://github.com/ClickHouse/ClickHouse/pull/25419) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Fix `REPLACE` column transformer when used in DDL by correctly quoting the formated query. This fixes [#23925](https://github.com/ClickHouse/ClickHouse/issues/23925). [#25391](https://github.com/ClickHouse/ClickHouse/pull/25391) ([Amos Bird](https://github.com/amosbird)).
* Fix the possibility of non-deterministic behaviour of the `quantileDeterministic` function and similar. This closes [#20480](https://github.com/ClickHouse/ClickHouse/issues/20480). [#25313](https://github.com/ClickHouse/ClickHouse/pull/25313) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Support `SimpleAggregateFunction(LowCardinality)` for `SummingMergeTree`. Fixes [#25134](https://github.com/ClickHouse/ClickHouse/issues/25134). [#25300](https://github.com/ClickHouse/ClickHouse/pull/25300) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix logical error with exception message "Cannot sum Array/Tuple in min/maxMap". [#25298](https://github.com/ClickHouse/ClickHouse/pull/25298) ([Kruglov Pavel](https://github.com/Avogar)).
* Fix error `Bad cast from type DB::ColumnLowCardinality to DB::ColumnVector<char8_t>` for queries where `LowCardinality` argument was used for IN (this bug appeared in 21.6). Fixes [#25187](https://github.com/ClickHouse/ClickHouse/issues/25187). [#25290](https://github.com/ClickHouse/ClickHouse/pull/25290) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix incorrect behaviour of `joinGetOrNull` with not-nullable columns. This fixes [#24261](https://github.com/ClickHouse/ClickHouse/issues/24261). [#25288](https://github.com/ClickHouse/ClickHouse/pull/25288) ([Amos Bird](https://github.com/amosbird)).
* Fix incorrect behaviour and UBSan report in big integers. In previous versions `CAST(1e19 AS UInt128)` returned zero. [#25279](https://github.com/ClickHouse/ClickHouse/pull/25279) ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Fixed an error which occurred while inserting a subset of columns using CSVWithNames format. Fixes [#25129](https://github.com/ClickHouse/ClickHouse/issues/25129). [#25169](https://github.com/ClickHouse/ClickHouse/pull/25169) ([Nikita Mikhaylov](https://github.com/nikitamikhaylov)).
* Do not use table's projection for `SELECT` with `FINAL`. It is not supported yet. [#25163](https://github.com/ClickHouse/ClickHouse/pull/25163) ([Amos Bird](https://github.com/amosbird)).
* Fix possible parts loss after updating up to 21.5 in case table used `UUID` in partition key. (It is not recommended to use `UUID` in partition key). Fixes [#25070](https://github.com/ClickHouse/ClickHouse/issues/25070). [#25127](https://github.com/ClickHouse/ClickHouse/pull/25127) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix crash in query with cross join and `joined_subquery_requires_alias = 0`. Fixes [#24011](https://github.com/ClickHouse/ClickHouse/issues/24011). [#25082](https://github.com/ClickHouse/ClickHouse/pull/25082) ([Nikolai Kochetov](https://github.com/KochetovNicolai)).
* Fix bug with constant maps in mapContains function that lead to error `empty column was returned by function mapContains`. Closes [#25077](https://github.com/ClickHouse/ClickHouse/issues/25077). [#25080](https://github.com/ClickHouse/ClickHouse/pull/25080) ([Kruglov Pavel](https://github.com/Avogar)).
* Remove possibility to create tables with columns referencing themselves like `a UInt32 ALIAS a + 1` or `b UInt32 MATERIALIZED b`. Fixes [#24910](https://github.com/ClickHouse/ClickHouse/issues/24910), [#24292](https://github.com/ClickHouse/ClickHouse/issues/24292). [#25059](https://github.com/ClickHouse/ClickHouse/pull/25059) ([alesapin](https://github.com/alesapin)).
* Fix wrong result when using aggregate projection with *not empty* `GROUP BY` key to execute query with `GROUP BY` by *empty* key. [#25055](https://github.com/ClickHouse/ClickHouse/pull/25055) ([Amos Bird](https://github.com/amosbird)).
* Fix serialization of splitted nested messages in Protobuf format. This PR fixes [#24647](https://github.com/ClickHouse/ClickHouse/issues/24647). [#25000](https://github.com/ClickHouse/ClickHouse/pull/25000) ([Vitaly Baranov](https://github.com/vitlibar)).
* Fix limit/offset settings for distributed queries (ignore on the remote nodes). [#24940](https://github.com/ClickHouse/ClickHouse/pull/24940) ([Azat Khuzhin](https://github.com/azat)).
* Fix possible heap-buffer-overflow in `Arrow` format. [#24922](https://github.com/ClickHouse/ClickHouse/pull/24922) ([Kruglov Pavel](https://github.com/Avogar)).
* Fixed possible error 'Cannot read from istream at offset 0' when reading a file from DiskS3 (S3 virtual filesystem is an experimental feature under development that should not be used in production). [#24885](https://github.com/ClickHouse/ClickHouse/pull/24885) ([Pavel Kovalenko](https://github.com/Jokser)).
* Fix "Missing columns" exception when joining Distributed Materialized View. [#24870](https://github.com/ClickHouse/ClickHouse/pull/24870) ([Azat Khuzhin](https://github.com/azat)).
* Allow `NULL` values in postgresql compatibility protocol. Closes [#22622](https://github.com/ClickHouse/ClickHouse/issues/22622). [#24857](https://github.com/ClickHouse/ClickHouse/pull/24857) ([Kseniia Sumarokova](https://github.com/kssenii)).
* Fix bug when exception `Mutation was killed` can be thrown to the client on mutation wait when mutation not loaded into memory yet. [#24809](https://github.com/ClickHouse/ClickHouse/pull/24809) ([alesapin](https://github.com/alesapin)).
* Fixed bug in deserialization of random generator state with might cause some data types such as `AggregateFunction(groupArraySample(N), T))` to behave in a non-deterministic way. [#24538](https://github.com/ClickHouse/ClickHouse/pull/24538) ([tavplubix](https://github.com/tavplubix)).
* Disallow building uniqXXXXStates of other aggregation states. [#24523](https://github.com/ClickHouse/ClickHouse/pull/24523) ([Raúl Marín](https://github.com/Algunenano)). Then allow it back by actually eliminating the root cause of the related issue. ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Fix usage of tuples in `CREATE .. AS SELECT` queries. [#24464](https://github.com/ClickHouse/ClickHouse/pull/24464) ([Anton Popov](https://github.com/CurtizJ)).
* Fix computation of total bytes in `Buffer` table. In current ClickHouse version total_writes.bytes counter decreases too much during the buffer flush. It leads to counter overflow and totalBytes return something around 17.44 EB some time after the flush. [#24450](https://github.com/ClickHouse/ClickHouse/pull/24450) ([DimasKovas](https://github.com/DimasKovas)).
* Fix incorrect information about the monotonicity of toWeek function. This fixes [#24422](https://github.com/ClickHouse/ClickHouse/issues/24422) . This bug was introduced in https://github.com/ClickHouse/ClickHouse/pull/5212 , and was exposed later by smarter partition pruner. [#24446](https://github.com/ClickHouse/ClickHouse/pull/24446) ([Amos Bird](https://github.com/amosbird)).
* When user authentication is managed by LDAP. Fixed potential deadlock that can happen during LDAP role (re)mapping, when LDAP group is mapped to a nonexistent local role. [#24431](https://github.com/ClickHouse/ClickHouse/pull/24431) ([Denis Glazachev](https://github.com/traceon)).
* In "multipart/form-data" message consider the CRLF preceding a boundary as part of it. Fixes [#23905](https://github.com/ClickHouse/ClickHouse/issues/23905). [#24399](https://github.com/ClickHouse/ClickHouse/pull/24399) ([Ivan](https://github.com/abyss7)).
* Fix drop partition with intersect fake parts. In rare cases there might be parts with mutation version greater than current block number. [#24321](https://github.com/ClickHouse/ClickHouse/pull/24321) ([Amos Bird](https://github.com/amosbird)).
* Fixed a bug in moving Materialized View from Ordinary to Atomic database (`RENAME TABLE` query). Now inner table is moved to new database together with Materialized View. Fixes [#23926](https://github.com/ClickHouse/ClickHouse/issues/23926). [#24309](https://github.com/ClickHouse/ClickHouse/pull/24309) ([tavplubix](https://github.com/tavplubix)).
* Allow empty HTTP headers. Fixes [#23901](https://github.com/ClickHouse/ClickHouse/issues/23901). [#24285](https://github.com/ClickHouse/ClickHouse/pull/24285) ([Ivan](https://github.com/abyss7)).
* Correct processing of mutations (ALTER UPDATE/DELETE) in Memory tables. Closes [#24274](https://github.com/ClickHouse/ClickHouse/issues/24274). [#24275](https://github.com/ClickHouse/ClickHouse/pull/24275) ([flynn](https://github.com/ucasfl)).
* Make column LowCardinality property in JOIN output the same as in the input, close [#23351](https://github.com/ClickHouse/ClickHouse/issues/23351), close [#20315](https://github.com/ClickHouse/ClickHouse/issues/20315). [#24061](https://github.com/ClickHouse/ClickHouse/pull/24061) ([Vladimir](https://github.com/vdimir)).
* A fix for Kafka tables. Fix the bug in failover behavior when Engine = Kafka was not able to start consumption if the same consumer had an empty assignment previously. Closes [#21118](https://github.com/ClickHouse/ClickHouse/issues/21118). [#21267](https://github.com/ClickHouse/ClickHouse/pull/21267) ([filimonov](https://github.com/filimonov)).
#### Build/Testing/Packaging Improvement
* Add `darwin-aarch64` (Mac M1 / Apple Silicon) builds in CI [#25560](https://github.com/ClickHouse/ClickHouse/pull/25560) ([Ivan](https://github.com/abyss7)) and put the links to the docs and website ([alexey-milovidov](https://github.com/alexey-milovidov)).
* Adds cross-platform embedding of binary resources into executables. It works on Illumos. [#25146](https://github.com/ClickHouse/ClickHouse/pull/25146) ([bnaecker](https://github.com/bnaecker)).
* Add join related options to stress tests to improve fuzzing. [#25200](https://github.com/ClickHouse/ClickHouse/pull/25200) ([Vladimir](https://github.com/vdimir)).
* Enable build with s3 module in osx [#25217](https://github.com/ClickHouse/ClickHouse/issues/25217). [#25218](https://github.com/ClickHouse/ClickHouse/pull/25218) ([kevin wan](https://github.com/MaxWk)).
* Add integration test cases to cover JDBC bridge. [#25047](https://github.com/ClickHouse/ClickHouse/pull/25047) ([Zhichun Wu](https://github.com/zhicwu)).
* Integration tests configuration has special treatment for dictionaries. Removed remaining dictionaries manual setup. [#24728](https://github.com/ClickHouse/ClickHouse/pull/24728) ([Ilya Yatsishin](https://github.com/qoega)).
* Add libfuzzer tests for YAMLParser class. [#24480](https://github.com/ClickHouse/ClickHouse/pull/24480) ([BoloniniD](https://github.com/BoloniniD)).
* Ubuntu 20.04 is now used to run integration tests, docker-compose version used to run integration tests is updated to 1.28.2. Environment variables now take effect on docker-compose. Rework test_dictionaries_all_layouts_separate_sources to allow parallel run. [#20393](https://github.com/ClickHouse/ClickHouse/pull/20393) ([Ilya Yatsishin](https://github.com/qoega)).
* Fix TOCTOU error in installation script. [#25277](https://github.com/ClickHouse/ClickHouse/pull/25277) ([alexey-milovidov](https://github.com/alexey-milovidov)).
### ClickHouse release 21.6, 2021-06-05 ### ClickHouse release 21.6, 2021-06-05
#### Upgrade Notes #### Upgrade Notes

2
CMakeLists.txt
View File

@ -536,10 +536,12 @@ include (cmake/find/rapidjson.cmake)
include (cmake/find/fastops.cmake) include (cmake/find/fastops.cmake)
include (cmake/find/odbc.cmake) include (cmake/find/odbc.cmake)
include (cmake/find/nanodbc.cmake) include (cmake/find/nanodbc.cmake)
include (cmake/find/sqlite.cmake)
include (cmake/find/rocksdb.cmake) include (cmake/find/rocksdb.cmake)
include (cmake/find/libpqxx.cmake) include (cmake/find/libpqxx.cmake)
include (cmake/find/nuraft.cmake) include (cmake/find/nuraft.cmake)
include (cmake/find/yaml-cpp.cmake) include (cmake/find/yaml-cpp.cmake)
include (cmake/find/s2geometry.cmake)
if(NOT USE_INTERNAL_PARQUET_LIBRARY) if(NOT USE_INTERNAL_PARQUET_LIBRARY)
set (ENABLE_ORC OFF CACHE INTERNAL "") set (ENABLE_ORC OFF CACHE INTERNAL "")

26
base/common/DateLUTImpl.h
View File

@ -18,6 +18,8 @@
#define DATE_LUT_MAX (0xFFFFFFFFU - 86400) #define DATE_LUT_MAX (0xFFFFFFFFU - 86400)
#define DATE_LUT_MAX_DAY_NUM 0xFFFF #define DATE_LUT_MAX_DAY_NUM 0xFFFF
/// Max int value of Date32, DATE LUT cache size minus daynum_offset_epoch
#define DATE_LUT_MAX_EXTEND_DAY_NUM (DATE_LUT_SIZE - 16436)
/// A constant to add to time_t so every supported time point becomes non-negative and still has the same remainder of division by 3600. /// A constant to add to time_t so every supported time point becomes non-negative and still has the same remainder of division by 3600.
/// If we treat "remainder of division" operation in the sense of modular arithmetic (not like in C++). /// If we treat "remainder of division" operation in the sense of modular arithmetic (not like in C++).
@ -270,6 +272,8 @@ public:
auto getOffsetAtStartOfEpoch() const { return offset_at_start_of_epoch; } auto getOffsetAtStartOfEpoch() const { return offset_at_start_of_epoch; }
auto getTimeOffsetAtStartOfLUT() const { return offset_at_start_of_lut; } auto getTimeOffsetAtStartOfLUT() const { return offset_at_start_of_lut; }
auto getDayNumOffsetEpoch() const { return daynum_offset_epoch; }
/// All functions below are thread-safe; arguments are not checked. /// All functions below are thread-safe; arguments are not checked.
inline ExtendedDayNum toDayNum(ExtendedDayNum d) const inline ExtendedDayNum toDayNum(ExtendedDayNum d) const
@ -926,15 +930,17 @@ public:
{ {
if (unlikely(year < DATE_LUT_MIN_YEAR || year > DATE_LUT_MAX_YEAR || month < 1 || month > 12 || day_of_month < 1 || day_of_month > 31)) if (unlikely(year < DATE_LUT_MIN_YEAR || year > DATE_LUT_MAX_YEAR || month < 1 || month > 12 || day_of_month < 1 || day_of_month > 31))
return LUTIndex(0); return LUTIndex(0);
auto year_lut_index = (year - DATE_LUT_MIN_YEAR) * 12 + month - 1;
return LUTIndex{years_months_lut[(year - DATE_LUT_MIN_YEAR) * 12 + month - 1] + day_of_month - 1}; UInt32 index = years_months_lut[year_lut_index].toUnderType() + day_of_month - 1;
/// When date is out of range, default value is DATE_LUT_SIZE - 1 (2283-11-11)
return LUTIndex{std::min(index, static_cast<UInt32>(DATE_LUT_SIZE - 1))};
} }
/// Create DayNum from year, month, day of month. /// Create DayNum from year, month, day of month.
inline ExtendedDayNum makeDayNum(Int16 year, UInt8 month, UInt8 day_of_month) const inline ExtendedDayNum makeDayNum(Int16 year, UInt8 month, UInt8 day_of_month, Int32 default_error_day_num = 0) const
{ {
if (unlikely(year < DATE_LUT_MIN_YEAR || year > DATE_LUT_MAX_YEAR || month < 1 || month > 12 || day_of_month < 1 || day_of_month > 31)) if (unlikely(year < DATE_LUT_MIN_YEAR || year > DATE_LUT_MAX_YEAR || month < 1 || month > 12 || day_of_month < 1 || day_of_month > 31))
return ExtendedDayNum(0); return ExtendedDayNum(default_error_day_num);
return toDayNum(makeLUTIndex(year, month, day_of_month)); return toDayNum(makeLUTIndex(year, month, day_of_month));
} }
@ -1091,9 +1097,9 @@ public:
return lut[new_index].date + time; return lut[new_index].date + time;
} }
inline NO_SANITIZE_UNDEFINED Time addWeeks(Time t, Int64 delta) const inline NO_SANITIZE_UNDEFINED Time addWeeks(Time t, Int32 delta) const
{ {
return addDays(t, delta * 7); return addDays(t, static_cast<Int64>(delta) * 7);
} }
inline UInt8 saturateDayOfMonth(Int16 year, UInt8 month, UInt8 day_of_month) const inline UInt8 saturateDayOfMonth(Int16 year, UInt8 month, UInt8 day_of_month) const
@ -1158,14 +1164,14 @@ public:
return toDayNum(addMonthsIndex(d, delta)); return toDayNum(addMonthsIndex(d, delta));
} }
inline Time NO_SANITIZE_UNDEFINED addQuarters(Time t, Int64 delta) const inline Time NO_SANITIZE_UNDEFINED addQuarters(Time t, Int32 delta) const
{ {
return addMonths(t, delta * 3); return addMonths(t, static_cast<Int64>(delta) * 3);
} }
inline ExtendedDayNum addQuarters(ExtendedDayNum d, Int64 delta) const inline ExtendedDayNum addQuarters(ExtendedDayNum d, Int32 delta) const
{ {
return addMonths(d, delta * 3); return addMonths(d, static_cast<Int64>(delta) * 3);
} }
template <typename DateOrTime> template <typename DateOrTime>

14
base/common/LocalDate.h
View File

@ -70,6 +70,14 @@ public:
m_day = values.day_of_month; m_day = values.day_of_month;
} }
explicit LocalDate(ExtendedDayNum day_num)
{
const auto & values = DateLUT::instance().getValues(day_num);
m_year = values.year;
m_month = values.month;
m_day = values.day_of_month;
}
LocalDate(unsigned short year_, unsigned char month_, unsigned char day_) LocalDate(unsigned short year_, unsigned char month_, unsigned char day_)
: m_year(year_), m_month(month_), m_day(day_) : m_year(year_), m_month(month_), m_day(day_)
{ {
@ -98,6 +106,12 @@ public:
return DayNum(lut.makeDayNum(m_year, m_month, m_day).toUnderType()); return DayNum(lut.makeDayNum(m_year, m_month, m_day).toUnderType());
} }
ExtendedDayNum getExtenedDayNum() const
{
const auto & lut = DateLUT::instance();
return ExtendedDayNum (lut.makeDayNum(m_year, m_month, m_day).toUnderType());
}
operator DayNum() const operator DayNum() const
{ {
return getDayNum(); return getDayNum();

4
base/common/ReplxxLineReader.cpp
View File

@ -69,7 +69,7 @@ void convertHistoryFile(const std::string & path, replxx::Replxx & rx)
} }
std::string line; std::string line;
if (!getline(in, line).good()) if (getline(in, line).bad())
{ {
rx.print("Cannot read from %s (for conversion): %s\n", rx.print("Cannot read from %s (for conversion): %s\n",
path.c_str(), errnoToString(errno).c_str()); path.c_str(), errnoToString(errno).c_str());
@ -78,7 +78,7 @@ void convertHistoryFile(const std::string & path, replxx::Replxx & rx)
/// This is the marker of the date, no need to convert. /// This is the marker of the date, no need to convert.
static char const REPLXX_TIMESTAMP_PATTERN[] = "### dddd-dd-dd dd:dd:dd.ddd"; static char const REPLXX_TIMESTAMP_PATTERN[] = "### dddd-dd-dd dd:dd:dd.ddd";
if (line.starts_with("### ") && line.size() == strlen(REPLXX_TIMESTAMP_PATTERN)) if (line.empty() || (line.starts_with("### ") && line.size() == strlen(REPLXX_TIMESTAMP_PATTERN)))
{ {
return; return;
} }

10
cmake/autogenerated_versions.txt
View File

@ -2,11 +2,11 @@
# NOTE: has nothing common with DBMS_TCP_PROTOCOL_VERSION, # NOTE: has nothing common with DBMS_TCP_PROTOCOL_VERSION,
# only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes. # only DBMS_TCP_PROTOCOL_VERSION should be incremented on protocol changes.
SET(VERSION_REVISION 54453) SET(VERSION_REVISION 54454)
SET(VERSION_MAJOR 21) SET(VERSION_MAJOR 21)
SET(VERSION_MINOR 8) SET(VERSION_MINOR 9)
SET(VERSION_PATCH 1) SET(VERSION_PATCH 1)
SET(VERSION_GITHASH fb895056568e26200629c7d19626e92d2dedc70d) SET(VERSION_GITHASH f48c5af90c2ad51955d1ee3b6b05d006b03e4238)
SET(VERSION_DESCRIBE v21.8.1.1-prestable) SET(VERSION_DESCRIBE v21.9.1.1-prestable)
SET(VERSION_STRING 21.8.1.1) SET(VERSION_STRING 21.9.1.1)
# end of autochange # end of autochange

24
cmake/find/s2geometry.cmake Normal file
View File

@ -0,0 +1,24 @@
option(ENABLE_S2_GEOMETRY "Enable S2 geometry library" ${ENABLE_LIBRARIES})
if (ENABLE_S2_GEOMETRY)
if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/s2geometry")
message (WARNING "submodule contrib/s2geometry is missing. to fix try run: \n git submodule update --init --recursive")
set (ENABLE_S2_GEOMETRY 0)
set (USE_S2_GEOMETRY 0)
else()
if (OPENSSL_FOUND)
set (S2_GEOMETRY_LIBRARY s2)
set (S2_GEOMETRY_INCLUDE_DIR ${ClickHouse_SOURCE_DIR}/contrib/s2geometry/src/s2)
set (USE_S2_GEOMETRY 1)
else()
message (WARNING "S2 uses OpenSSL, but the latter is absent.")
endif()
endif()
if (NOT USE_S2_GEOMETRY)
message (${RECONFIGURE_MESSAGE_LEVEL} "Can't enable S2 geometry library")
endif()
endif()
message (STATUS "Using s2geometry=${USE_S2_GEOMETRY} : ${S2_GEOMETRY_INCLUDE_DIR}")

16
cmake/find/sqlite.cmake Normal file
View File

@ -0,0 +1,16 @@
option(ENABLE_SQLITE "Enable sqlite" ${ENABLE_LIBRARIES})
if (NOT ENABLE_SQLITE)
return()
endif()
if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/sqlite-amalgamation/sqlite3.c")
message (WARNING "submodule contrib/sqlite3-amalgamation is missing. to fix try run: \n git submodule update --init --recursive")
message (${RECONFIGURE_MESSAGE_LEVEL} "Can't find internal sqlite library")
set (USE_SQLITE 0)
return()
endif()
set (USE_SQLITE 1)
set (SQLITE_LIBRARY sqlite)
message (STATUS "Using sqlite=${USE_SQLITE}")

2
cmake/find/stats.cmake
View File

@ -1,4 +1,4 @@
option(ENABLE_STATS "Enalbe StatsLib library" ${ENABLE_LIBRARIES}) option(ENABLE_STATS "Enable StatsLib library" ${ENABLE_LIBRARIES})
if (ENABLE_STATS) if (ENABLE_STATS)
if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/stats") if (NOT EXISTS "${ClickHouse_SOURCE_DIR}/contrib/stats")

14
contrib/CMakeLists.txt vendored
View File

@ -1,3 +1,4 @@
# Third-party libraries may have substandard code.
# Put all targets defined here and in added subfolders under "contrib/" folder in GUI-based IDEs by default. # Put all targets defined here and in added subfolders under "contrib/" folder in GUI-based IDEs by default.
# Some of third-party projects may override CMAKE_FOLDER or FOLDER property of their targets, so they will # Some of third-party projects may override CMAKE_FOLDER or FOLDER property of their targets, so they will
@ -10,10 +11,8 @@ else ()
endif () endif ()
unset (_current_dir_name) unset (_current_dir_name)
# Third-party libraries may have substandard code. set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -w")
# Also remove a possible source of nondeterminism. set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -w")
set (CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -w -D__DATE__= -D__TIME__= -D__TIMESTAMP__=")
set (CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -w -D__DATE__= -D__TIME__= -D__TIMESTAMP__=")
if (WITH_COVERAGE) if (WITH_COVERAGE)
set (WITHOUT_COVERAGE_LIST ${WITHOUT_COVERAGE}) set (WITHOUT_COVERAGE_LIST ${WITHOUT_COVERAGE})
@ -329,3 +328,10 @@ endif()
add_subdirectory(fast_float) add_subdirectory(fast_float)
if (USE_SQLITE)
add_subdirectory(sqlite-cmake)
endif()
if (USE_S2_GEOMETRY)
add_subdirectory(s2geometry-cmake)
endif()

2
contrib/h3 vendored

@ -1 +1 @@
Subproject commit e209086ae1b5477307f545a0f6111780edc59940 Subproject commit c7f46cfd71fb60e2fefc90e28abe81657deff735

19
contrib/h3-cmake/CMakeLists.txt
View File

@ -3,21 +3,22 @@ set(H3_BINARY_DIR "${ClickHouse_BINARY_DIR}/contrib/h3/src/h3lib")
set(SRCS set(SRCS
"${H3_SOURCE_DIR}/lib/algos.c" "${H3_SOURCE_DIR}/lib/algos.c"
"${H3_SOURCE_DIR}/lib/baseCells.c"
"${H3_SOURCE_DIR}/lib/bbox.c"
"${H3_SOURCE_DIR}/lib/coordijk.c" "${H3_SOURCE_DIR}/lib/coordijk.c"
"${H3_SOURCE_DIR}/lib/faceijk.c" "${H3_SOURCE_DIR}/lib/bbox.c"
"${H3_SOURCE_DIR}/lib/geoCoord.c"
"${H3_SOURCE_DIR}/lib/h3Index.c"
"${H3_SOURCE_DIR}/lib/h3UniEdge.c"
"${H3_SOURCE_DIR}/lib/linkedGeo.c"
"${H3_SOURCE_DIR}/lib/localij.c"
"${H3_SOURCE_DIR}/lib/mathExtensions.c"
"${H3_SOURCE_DIR}/lib/polygon.c" "${H3_SOURCE_DIR}/lib/polygon.c"
"${H3_SOURCE_DIR}/lib/h3Index.c"
"${H3_SOURCE_DIR}/lib/vec2d.c" "${H3_SOURCE_DIR}/lib/vec2d.c"
"${H3_SOURCE_DIR}/lib/vec3d.c" "${H3_SOURCE_DIR}/lib/vec3d.c"
"${H3_SOURCE_DIR}/lib/vertex.c" "${H3_SOURCE_DIR}/lib/vertex.c"
"${H3_SOURCE_DIR}/lib/linkedGeo.c"
"${H3_SOURCE_DIR}/lib/localij.c"
"${H3_SOURCE_DIR}/lib/latLng.c"
"${H3_SOURCE_DIR}/lib/directedEdge.c"
"${H3_SOURCE_DIR}/lib/mathExtensions.c"
"${H3_SOURCE_DIR}/lib/iterators.c"
"${H3_SOURCE_DIR}/lib/vertexGraph.c" "${H3_SOURCE_DIR}/lib/vertexGraph.c"
"${H3_SOURCE_DIR}/lib/faceijk.c"
"${H3_SOURCE_DIR}/lib/baseCells.c"
) )
configure_file("${H3_SOURCE_DIR}/include/h3api.h.in" "${H3_BINARY_DIR}/include/h3api.h") configure_file("${H3_SOURCE_DIR}/include/h3api.h.in" "${H3_BINARY_DIR}/include/h3api.h")

2
contrib/poco vendored

@ -1 +1 @@
Subproject commit 5994506908028612869fee627d68d8212dfe7c1e Subproject commit 7351c4691b5d401f59e3959adfc5b4fa263b32da

2
contrib/rocksdb vendored

@ -1 +1 @@
Subproject commit 07c77549a20b63ff6981b400085eba36bb5c80c4 Subproject commit dac0e9a68080c837d6b6223921f3fc151abbfcdc

558
contrib/rocksdb-cmake/CMakeLists.txt
View File

@ -70,11 +70,6 @@ else()
endif() endif()
endif() endif()
set(BUILD_VERSION_CC rocksdb_build_version.cc)
add_library(rocksdb_build_version OBJECT ${BUILD_VERSION_CC})
target_include_directories(rocksdb_build_version PRIVATE "${ROCKSDB_SOURCE_DIR}/util")
include(CheckCCompilerFlag) include(CheckCCompilerFlag)
if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64") if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
CHECK_C_COMPILER_FLAG("-mcpu=power9" HAS_POWER9) CHECK_C_COMPILER_FLAG("-mcpu=power9" HAS_POWER9)
@ -243,272 +238,293 @@ find_package(Threads REQUIRED)
# Main library source code # Main library source code
set(SOURCES set(SOURCES
"${ROCKSDB_SOURCE_DIR}/cache/cache.cc" ${ROCKSDB_SOURCE_DIR}/cache/cache.cc
"${ROCKSDB_SOURCE_DIR}/cache/clock_cache.cc" ${ROCKSDB_SOURCE_DIR}/cache/cache_entry_roles.cc
"${ROCKSDB_SOURCE_DIR}/cache/lru_cache.cc" ${ROCKSDB_SOURCE_DIR}/cache/clock_cache.cc
"${ROCKSDB_SOURCE_DIR}/cache/sharded_cache.cc" ${ROCKSDB_SOURCE_DIR}/cache/lru_cache.cc
"${ROCKSDB_SOURCE_DIR}/db/arena_wrapped_db_iter.cc" ${ROCKSDB_SOURCE_DIR}/cache/sharded_cache.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_addition.cc" ${ROCKSDB_SOURCE_DIR}/db/arena_wrapped_db_iter.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_builder.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_fetcher.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_cache.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_addition.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_garbage.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_builder.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_meta.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_cache.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_reader.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_garbage.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_format.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_meta.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_sequential_reader.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_file_reader.cc
"${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_writer.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_garbage_meter.cc
"${ROCKSDB_SOURCE_DIR}/db/builder.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_format.cc
"${ROCKSDB_SOURCE_DIR}/db/c.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_sequential_reader.cc
"${ROCKSDB_SOURCE_DIR}/db/column_family.cc" ${ROCKSDB_SOURCE_DIR}/db/blob/blob_log_writer.cc
"${ROCKSDB_SOURCE_DIR}/db/compacted_db_impl.cc" ${ROCKSDB_SOURCE_DIR}/db/builder.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/compaction.cc" ${ROCKSDB_SOURCE_DIR}/db/c.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_iterator.cc" ${ROCKSDB_SOURCE_DIR}/db/column_family.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_job.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_iterator.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_fifo.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_level.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_job.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_universal.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_fifo.cc
"${ROCKSDB_SOURCE_DIR}/db/compaction/sst_partitioner.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_level.cc
"${ROCKSDB_SOURCE_DIR}/db/convenience.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/compaction_picker_universal.cc
"${ROCKSDB_SOURCE_DIR}/db/db_filesnapshot.cc" ${ROCKSDB_SOURCE_DIR}/db/compaction/sst_partitioner.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl.cc" ${ROCKSDB_SOURCE_DIR}/db/convenience.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_write.cc" ${ROCKSDB_SOURCE_DIR}/db/db_filesnapshot.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_compaction_flush.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/compacted_db_impl.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_files.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_open.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_write.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_debug.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_compaction_flush.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_experimental.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_files.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_readonly.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_open.cc
"${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_secondary.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_debug.cc
"${ROCKSDB_SOURCE_DIR}/db/db_info_dumper.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_experimental.cc
"${ROCKSDB_SOURCE_DIR}/db/db_iter.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_readonly.cc
"${ROCKSDB_SOURCE_DIR}/db/dbformat.cc" ${ROCKSDB_SOURCE_DIR}/db/db_impl/db_impl_secondary.cc
"${ROCKSDB_SOURCE_DIR}/db/error_handler.cc" ${ROCKSDB_SOURCE_DIR}/db/db_info_dumper.cc
"${ROCKSDB_SOURCE_DIR}/db/event_helpers.cc" ${ROCKSDB_SOURCE_DIR}/db/db_iter.cc
"${ROCKSDB_SOURCE_DIR}/db/experimental.cc" ${ROCKSDB_SOURCE_DIR}/db/dbformat.cc
"${ROCKSDB_SOURCE_DIR}/db/external_sst_file_ingestion_job.cc" ${ROCKSDB_SOURCE_DIR}/db/error_handler.cc
"${ROCKSDB_SOURCE_DIR}/db/file_indexer.cc" ${ROCKSDB_SOURCE_DIR}/db/event_helpers.cc
"${ROCKSDB_SOURCE_DIR}/db/flush_job.cc" ${ROCKSDB_SOURCE_DIR}/db/experimental.cc
"${ROCKSDB_SOURCE_DIR}/db/flush_scheduler.cc" ${ROCKSDB_SOURCE_DIR}/db/external_sst_file_ingestion_job.cc
"${ROCKSDB_SOURCE_DIR}/db/forward_iterator.cc" ${ROCKSDB_SOURCE_DIR}/db/file_indexer.cc
"${ROCKSDB_SOURCE_DIR}/db/import_column_family_job.cc" ${ROCKSDB_SOURCE_DIR}/db/flush_job.cc
"${ROCKSDB_SOURCE_DIR}/db/internal_stats.cc" ${ROCKSDB_SOURCE_DIR}/db/flush_scheduler.cc
"${ROCKSDB_SOURCE_DIR}/db/logs_with_prep_tracker.cc" ${ROCKSDB_SOURCE_DIR}/db/forward_iterator.cc
"${ROCKSDB_SOURCE_DIR}/db/log_reader.cc" ${ROCKSDB_SOURCE_DIR}/db/import_column_family_job.cc
"${ROCKSDB_SOURCE_DIR}/db/log_writer.cc" ${ROCKSDB_SOURCE_DIR}/db/internal_stats.cc
"${ROCKSDB_SOURCE_DIR}/db/malloc_stats.cc" ${ROCKSDB_SOURCE_DIR}/db/logs_with_prep_tracker.cc
"${ROCKSDB_SOURCE_DIR}/db/memtable.cc" ${ROCKSDB_SOURCE_DIR}/db/log_reader.cc
"${ROCKSDB_SOURCE_DIR}/db/memtable_list.cc" ${ROCKSDB_SOURCE_DIR}/db/log_writer.cc
"${ROCKSDB_SOURCE_DIR}/db/merge_helper.cc" ${ROCKSDB_SOURCE_DIR}/db/malloc_stats.cc
"${ROCKSDB_SOURCE_DIR}/db/merge_operator.cc" ${ROCKSDB_SOURCE_DIR}/db/memtable.cc
"${ROCKSDB_SOURCE_DIR}/db/output_validator.cc" ${ROCKSDB_SOURCE_DIR}/db/memtable_list.cc
"${ROCKSDB_SOURCE_DIR}/db/periodic_work_scheduler.cc" ${ROCKSDB_SOURCE_DIR}/db/merge_helper.cc
"${ROCKSDB_SOURCE_DIR}/db/range_del_aggregator.cc" ${ROCKSDB_SOURCE_DIR}/db/merge_operator.cc
"${ROCKSDB_SOURCE_DIR}/db/range_tombstone_fragmenter.cc" ${ROCKSDB_SOURCE_DIR}/db/output_validator.cc
"${ROCKSDB_SOURCE_DIR}/db/repair.cc" ${ROCKSDB_SOURCE_DIR}/db/periodic_work_scheduler.cc
"${ROCKSDB_SOURCE_DIR}/db/snapshot_impl.cc" ${ROCKSDB_SOURCE_DIR}/db/range_del_aggregator.cc
"${ROCKSDB_SOURCE_DIR}/db/table_cache.cc" ${ROCKSDB_SOURCE_DIR}/db/range_tombstone_fragmenter.cc
"${ROCKSDB_SOURCE_DIR}/db/table_properties_collector.cc" ${ROCKSDB_SOURCE_DIR}/db/repair.cc
"${ROCKSDB_SOURCE_DIR}/db/transaction_log_impl.cc" ${ROCKSDB_SOURCE_DIR}/db/snapshot_impl.cc
"${ROCKSDB_SOURCE_DIR}/db/trim_history_scheduler.cc" ${ROCKSDB_SOURCE_DIR}/db/table_cache.cc
"${ROCKSDB_SOURCE_DIR}/db/version_builder.cc" ${ROCKSDB_SOURCE_DIR}/db/table_properties_collector.cc
"${ROCKSDB_SOURCE_DIR}/db/version_edit.cc" ${ROCKSDB_SOURCE_DIR}/db/transaction_log_impl.cc
"${ROCKSDB_SOURCE_DIR}/db/version_edit_handler.cc" ${ROCKSDB_SOURCE_DIR}/db/trim_history_scheduler.cc
"${ROCKSDB_SOURCE_DIR}/db/version_set.cc" ${ROCKSDB_SOURCE_DIR}/db/version_builder.cc
"${ROCKSDB_SOURCE_DIR}/db/wal_edit.cc" ${ROCKSDB_SOURCE_DIR}/db/version_edit.cc
"${ROCKSDB_SOURCE_DIR}/db/wal_manager.cc" ${ROCKSDB_SOURCE_DIR}/db/version_edit_handler.cc
"${ROCKSDB_SOURCE_DIR}/db/write_batch.cc" ${ROCKSDB_SOURCE_DIR}/db/version_set.cc
"${ROCKSDB_SOURCE_DIR}/db/write_batch_base.cc" ${ROCKSDB_SOURCE_DIR}/db/wal_edit.cc
"${ROCKSDB_SOURCE_DIR}/db/write_controller.cc" ${ROCKSDB_SOURCE_DIR}/db/wal_manager.cc
"${ROCKSDB_SOURCE_DIR}/db/write_thread.cc" ${ROCKSDB_SOURCE_DIR}/db/write_batch.cc
"${ROCKSDB_SOURCE_DIR}/env/env.cc" ${ROCKSDB_SOURCE_DIR}/db/write_batch_base.cc
"${ROCKSDB_SOURCE_DIR}/env/env_chroot.cc" ${ROCKSDB_SOURCE_DIR}/db/write_controller.cc
"${ROCKSDB_SOURCE_DIR}/env/env_encryption.cc" ${ROCKSDB_SOURCE_DIR}/db/write_thread.cc
"${ROCKSDB_SOURCE_DIR}/env/env_hdfs.cc" ${ROCKSDB_SOURCE_DIR}/env/composite_env.cc
"${ROCKSDB_SOURCE_DIR}/env/file_system.cc" ${ROCKSDB_SOURCE_DIR}/env/env.cc
"${ROCKSDB_SOURCE_DIR}/env/file_system_tracer.cc" ${ROCKSDB_SOURCE_DIR}/env/env_chroot.cc
"${ROCKSDB_SOURCE_DIR}/env/mock_env.cc" ${ROCKSDB_SOURCE_DIR}/env/env_encryption.cc
"${ROCKSDB_SOURCE_DIR}/file/delete_scheduler.cc" ${ROCKSDB_SOURCE_DIR}/env/env_hdfs.cc
"${ROCKSDB_SOURCE_DIR}/file/file_prefetch_buffer.cc" ${ROCKSDB_SOURCE_DIR}/env/file_system.cc
"${ROCKSDB_SOURCE_DIR}/file/file_util.cc" ${ROCKSDB_SOURCE_DIR}/env/file_system_tracer.cc
"${ROCKSDB_SOURCE_DIR}/file/filename.cc" ${ROCKSDB_SOURCE_DIR}/env/fs_remap.cc
"${ROCKSDB_SOURCE_DIR}/file/random_access_file_reader.cc" ${ROCKSDB_SOURCE_DIR}/env/mock_env.cc
"${ROCKSDB_SOURCE_DIR}/file/read_write_util.cc" ${ROCKSDB_SOURCE_DIR}/file/delete_scheduler.cc
"${ROCKSDB_SOURCE_DIR}/file/readahead_raf.cc" ${ROCKSDB_SOURCE_DIR}/file/file_prefetch_buffer.cc
"${ROCKSDB_SOURCE_DIR}/file/sequence_file_reader.cc" ${ROCKSDB_SOURCE_DIR}/file/file_util.cc
"${ROCKSDB_SOURCE_DIR}/file/sst_file_manager_impl.cc" ${ROCKSDB_SOURCE_DIR}/file/filename.cc
"${ROCKSDB_SOURCE_DIR}/file/writable_file_writer.cc" ${ROCKSDB_SOURCE_DIR}/file/line_file_reader.cc
"${ROCKSDB_SOURCE_DIR}/logging/auto_roll_logger.cc" ${ROCKSDB_SOURCE_DIR}/file/random_access_file_reader.cc
"${ROCKSDB_SOURCE_DIR}/logging/event_logger.cc" ${ROCKSDB_SOURCE_DIR}/file/read_write_util.cc
"${ROCKSDB_SOURCE_DIR}/logging/log_buffer.cc" ${ROCKSDB_SOURCE_DIR}/file/readahead_raf.cc
"${ROCKSDB_SOURCE_DIR}/memory/arena.cc" ${ROCKSDB_SOURCE_DIR}/file/sequence_file_reader.cc
"${ROCKSDB_SOURCE_DIR}/memory/concurrent_arena.cc" ${ROCKSDB_SOURCE_DIR}/file/sst_file_manager_impl.cc
"${ROCKSDB_SOURCE_DIR}/memory/jemalloc_nodump_allocator.cc" ${ROCKSDB_SOURCE_DIR}/file/writable_file_writer.cc
"${ROCKSDB_SOURCE_DIR}/memory/memkind_kmem_allocator.cc" ${ROCKSDB_SOURCE_DIR}/logging/auto_roll_logger.cc
"${ROCKSDB_SOURCE_DIR}/memtable/alloc_tracker.cc" ${ROCKSDB_SOURCE_DIR}/logging/event_logger.cc
"${ROCKSDB_SOURCE_DIR}/memtable/hash_linklist_rep.cc" ${ROCKSDB_SOURCE_DIR}/logging/log_buffer.cc
"${ROCKSDB_SOURCE_DIR}/memtable/hash_skiplist_rep.cc" ${ROCKSDB_SOURCE_DIR}/memory/arena.cc
"${ROCKSDB_SOURCE_DIR}/memtable/skiplistrep.cc" ${ROCKSDB_SOURCE_DIR}/memory/concurrent_arena.cc
"${ROCKSDB_SOURCE_DIR}/memtable/vectorrep.cc" ${ROCKSDB_SOURCE_DIR}/memory/jemalloc_nodump_allocator.cc
"${ROCKSDB_SOURCE_DIR}/memtable/write_buffer_manager.cc" ${ROCKSDB_SOURCE_DIR}/memory/memkind_kmem_allocator.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/histogram.cc" ${ROCKSDB_SOURCE_DIR}/memtable/alloc_tracker.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/histogram_windowing.cc" ${ROCKSDB_SOURCE_DIR}/memtable/hash_linklist_rep.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/in_memory_stats_history.cc" ${ROCKSDB_SOURCE_DIR}/memtable/hash_skiplist_rep.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/instrumented_mutex.cc" ${ROCKSDB_SOURCE_DIR}/memtable/skiplistrep.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/iostats_context.cc" ${ROCKSDB_SOURCE_DIR}/memtable/vectorrep.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/perf_context.cc" ${ROCKSDB_SOURCE_DIR}/memtable/write_buffer_manager.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/perf_level.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/histogram.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/persistent_stats_history.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/histogram_windowing.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/statistics.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/in_memory_stats_history.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_impl.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/instrumented_mutex.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_updater.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/iostats_context.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_util.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/perf_context.cc
"${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_util_debug.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/perf_level.cc
"${ROCKSDB_SOURCE_DIR}/options/cf_options.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/persistent_stats_history.cc
"${ROCKSDB_SOURCE_DIR}/options/configurable.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/statistics.cc
"${ROCKSDB_SOURCE_DIR}/options/customizable.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_impl.cc
"${ROCKSDB_SOURCE_DIR}/options/db_options.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_updater.cc
"${ROCKSDB_SOURCE_DIR}/options/options.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_util.cc
"${ROCKSDB_SOURCE_DIR}/options/options_helper.cc" ${ROCKSDB_SOURCE_DIR}/monitoring/thread_status_util_debug.cc
"${ROCKSDB_SOURCE_DIR}/options/options_parser.cc" ${ROCKSDB_SOURCE_DIR}/options/cf_options.cc
"${ROCKSDB_SOURCE_DIR}/port/stack_trace.cc" ${ROCKSDB_SOURCE_DIR}/options/configurable.cc
"${ROCKSDB_SOURCE_DIR}/table/adaptive/adaptive_table_factory.cc" ${ROCKSDB_SOURCE_DIR}/options/customizable.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/binary_search_index_reader.cc" ${ROCKSDB_SOURCE_DIR}/options/db_options.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block.cc" ${ROCKSDB_SOURCE_DIR}/options/options.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_filter_block.cc" ${ROCKSDB_SOURCE_DIR}/options/options_helper.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_builder.cc" ${ROCKSDB_SOURCE_DIR}/options/options_parser.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_factory.cc" ${ROCKSDB_SOURCE_DIR}/port/stack_trace.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_iterator.cc" ${ROCKSDB_SOURCE_DIR}/table/adaptive/adaptive_table_factory.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_reader.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/binary_search_index_reader.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_builder.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_prefetcher.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_filter_block.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/block_prefix_index.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_builder.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/data_block_hash_index.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_factory.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/data_block_footer.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_iterator.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/filter_block_reader_common.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_based_table_reader.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/filter_policy.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_builder.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/flush_block_policy.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_prefetcher.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/full_filter_block.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/block_prefix_index.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/hash_index_reader.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/data_block_hash_index.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/index_builder.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/data_block_footer.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/index_reader_common.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/filter_block_reader_common.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/parsed_full_filter_block.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/filter_policy.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/partitioned_filter_block.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/flush_block_policy.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/partitioned_index_iterator.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/full_filter_block.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/partitioned_index_reader.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/hash_index_reader.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/reader_common.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/index_builder.cc
"${ROCKSDB_SOURCE_DIR}/table/block_based/uncompression_dict_reader.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/index_reader_common.cc
"${ROCKSDB_SOURCE_DIR}/table/block_fetcher.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/parsed_full_filter_block.cc
"${ROCKSDB_SOURCE_DIR}/table/cuckoo/cuckoo_table_builder.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/partitioned_filter_block.cc
"${ROCKSDB_SOURCE_DIR}/table/cuckoo/cuckoo_table_factory.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/partitioned_index_iterator.cc
"${ROCKSDB_SOURCE_DIR}/table/cuckoo/cuckoo_table_reader.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/partitioned_index_reader.cc
"${ROCKSDB_SOURCE_DIR}/table/format.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/reader_common.cc
"${ROCKSDB_SOURCE_DIR}/table/get_context.cc" ${ROCKSDB_SOURCE_DIR}/table/block_based/uncompression_dict_reader.cc
"${ROCKSDB_SOURCE_DIR}/table/iterator.cc" ${ROCKSDB_SOURCE_DIR}/table/block_fetcher.cc
"${ROCKSDB_SOURCE_DIR}/table/merging_iterator.cc" ${ROCKSDB_SOURCE_DIR}/table/cuckoo/cuckoo_table_builder.cc
"${ROCKSDB_SOURCE_DIR}/table/meta_blocks.cc" ${ROCKSDB_SOURCE_DIR}/table/cuckoo/cuckoo_table_factory.cc
"${ROCKSDB_SOURCE_DIR}/table/persistent_cache_helper.cc" ${ROCKSDB_SOURCE_DIR}/table/cuckoo/cuckoo_table_reader.cc
"${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_bloom.cc" ${ROCKSDB_SOURCE_DIR}/table/format.cc
"${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_builder.cc" ${ROCKSDB_SOURCE_DIR}/table/get_context.cc
"${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_factory.cc" ${ROCKSDB_SOURCE_DIR}/table/iterator.cc
"${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_index.cc" ${ROCKSDB_SOURCE_DIR}/table/merging_iterator.cc
"${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_key_coding.cc" ${ROCKSDB_SOURCE_DIR}/table/meta_blocks.cc
"${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_reader.cc" ${ROCKSDB_SOURCE_DIR}/table/persistent_cache_helper.cc
"${ROCKSDB_SOURCE_DIR}/table/sst_file_dumper.cc" ${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_bloom.cc
"${ROCKSDB_SOURCE_DIR}/table/sst_file_reader.cc" ${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_builder.cc
"${ROCKSDB_SOURCE_DIR}/table/sst_file_writer.cc" ${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_factory.cc
"${ROCKSDB_SOURCE_DIR}/table/table_factory.cc" ${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_index.cc
"${ROCKSDB_SOURCE_DIR}/table/table_properties.cc" ${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_key_coding.cc
"${ROCKSDB_SOURCE_DIR}/table/two_level_iterator.cc" ${ROCKSDB_SOURCE_DIR}/table/plain/plain_table_reader.cc
"${ROCKSDB_SOURCE_DIR}/test_util/sync_point.cc" ${ROCKSDB_SOURCE_DIR}/table/sst_file_dumper.cc
"${ROCKSDB_SOURCE_DIR}/test_util/sync_point_impl.cc" ${ROCKSDB_SOURCE_DIR}/table/sst_file_reader.cc
"${ROCKSDB_SOURCE_DIR}/test_util/testutil.cc" ${ROCKSDB_SOURCE_DIR}/table/sst_file_writer.cc
"${ROCKSDB_SOURCE_DIR}/test_util/transaction_test_util.cc" ${ROCKSDB_SOURCE_DIR}/table/table_factory.cc
"${ROCKSDB_SOURCE_DIR}/tools/block_cache_analyzer/block_cache_trace_analyzer.cc" ${ROCKSDB_SOURCE_DIR}/table/table_properties.cc
"${ROCKSDB_SOURCE_DIR}/tools/dump/db_dump_tool.cc" ${ROCKSDB_SOURCE_DIR}/table/two_level_iterator.cc
"${ROCKSDB_SOURCE_DIR}/tools/io_tracer_parser_tool.cc" ${ROCKSDB_SOURCE_DIR}/test_util/sync_point.cc
"${ROCKSDB_SOURCE_DIR}/tools/ldb_cmd.cc" ${ROCKSDB_SOURCE_DIR}/test_util/sync_point_impl.cc
"${ROCKSDB_SOURCE_DIR}/tools/ldb_tool.cc" ${ROCKSDB_SOURCE_DIR}/test_util/testutil.cc
"${ROCKSDB_SOURCE_DIR}/tools/sst_dump_tool.cc" ${ROCKSDB_SOURCE_DIR}/test_util/transaction_test_util.cc
"${ROCKSDB_SOURCE_DIR}/tools/trace_analyzer_tool.cc" ${ROCKSDB_SOURCE_DIR}/tools/block_cache_analyzer/block_cache_trace_analyzer.cc
"${ROCKSDB_SOURCE_DIR}/trace_replay/trace_replay.cc" ${ROCKSDB_SOURCE_DIR}/tools/dump/db_dump_tool.cc
"${ROCKSDB_SOURCE_DIR}/trace_replay/block_cache_tracer.cc" ${ROCKSDB_SOURCE_DIR}/tools/io_tracer_parser_tool.cc
"${ROCKSDB_SOURCE_DIR}/trace_replay/io_tracer.cc" ${ROCKSDB_SOURCE_DIR}/tools/ldb_cmd.cc
"${ROCKSDB_SOURCE_DIR}/util/coding.cc" ${ROCKSDB_SOURCE_DIR}/tools/ldb_tool.cc
"${ROCKSDB_SOURCE_DIR}/util/compaction_job_stats_impl.cc" ${ROCKSDB_SOURCE_DIR}/tools/sst_dump_tool.cc
"${ROCKSDB_SOURCE_DIR}/util/comparator.cc" ${ROCKSDB_SOURCE_DIR}/tools/trace_analyzer_tool.cc
"${ROCKSDB_SOURCE_DIR}/util/compression_context_cache.cc" ${ROCKSDB_SOURCE_DIR}/trace_replay/trace_replay.cc
"${ROCKSDB_SOURCE_DIR}/util/concurrent_task_limiter_impl.cc" ${ROCKSDB_SOURCE_DIR}/trace_replay/block_cache_tracer.cc
"${ROCKSDB_SOURCE_DIR}/util/crc32c.cc" ${ROCKSDB_SOURCE_DIR}/trace_replay/io_tracer.cc
"${ROCKSDB_SOURCE_DIR}/util/dynamic_bloom.cc" ${ROCKSDB_SOURCE_DIR}/util/coding.cc
"${ROCKSDB_SOURCE_DIR}/util/hash.cc" ${ROCKSDB_SOURCE_DIR}/util/compaction_job_stats_impl.cc
"${ROCKSDB_SOURCE_DIR}/util/murmurhash.cc" ${ROCKSDB_SOURCE_DIR}/util/comparator.cc
"${ROCKSDB_SOURCE_DIR}/util/random.cc" ${ROCKSDB_SOURCE_DIR}/util/compression_context_cache.cc
"${ROCKSDB_SOURCE_DIR}/util/rate_limiter.cc" ${ROCKSDB_SOURCE_DIR}/util/concurrent_task_limiter_impl.cc
"${ROCKSDB_SOURCE_DIR}/util/slice.cc" ${ROCKSDB_SOURCE_DIR}/util/crc32c.cc
"${ROCKSDB_SOURCE_DIR}/util/file_checksum_helper.cc" ${ROCKSDB_SOURCE_DIR}/util/dynamic_bloom.cc
"${ROCKSDB_SOURCE_DIR}/util/status.cc" ${ROCKSDB_SOURCE_DIR}/util/hash.cc
"${ROCKSDB_SOURCE_DIR}/util/string_util.cc" ${ROCKSDB_SOURCE_DIR}/util/murmurhash.cc
"${ROCKSDB_SOURCE_DIR}/util/thread_local.cc" ${ROCKSDB_SOURCE_DIR}/util/random.cc
"${ROCKSDB_SOURCE_DIR}/util/threadpool_imp.cc" ${ROCKSDB_SOURCE_DIR}/util/rate_limiter.cc
"${ROCKSDB_SOURCE_DIR}/util/xxhash.cc" ${ROCKSDB_SOURCE_DIR}/util/ribbon_config.cc
"${ROCKSDB_SOURCE_DIR}/utilities/backupable/backupable_db.cc" ${ROCKSDB_SOURCE_DIR}/util/slice.cc
"${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_compaction_filter.cc" ${ROCKSDB_SOURCE_DIR}/util/file_checksum_helper.cc
"${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db.cc" ${ROCKSDB_SOURCE_DIR}/util/status.cc
"${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db_impl.cc" ${ROCKSDB_SOURCE_DIR}/util/string_util.cc
"${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db_impl_filesnapshot.cc" ${ROCKSDB_SOURCE_DIR}/util/thread_local.cc
"${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_dump_tool.cc" ${ROCKSDB_SOURCE_DIR}/util/threadpool_imp.cc
"${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_file.cc" ${ROCKSDB_SOURCE_DIR}/util/xxhash.cc
"${ROCKSDB_SOURCE_DIR}/utilities/cassandra/cassandra_compaction_filter.cc" ${ROCKSDB_SOURCE_DIR}/utilities/backupable/backupable_db.cc
"${ROCKSDB_SOURCE_DIR}/utilities/cassandra/format.cc" ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_compaction_filter.cc
"${ROCKSDB_SOURCE_DIR}/utilities/cassandra/merge_operator.cc" ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db.cc
"${ROCKSDB_SOURCE_DIR}/utilities/checkpoint/checkpoint_impl.cc" ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db_impl.cc
"${ROCKSDB_SOURCE_DIR}/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc" ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_db_impl_filesnapshot.cc
"${ROCKSDB_SOURCE_DIR}/utilities/debug.cc" ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_dump_tool.cc
"${ROCKSDB_SOURCE_DIR}/utilities/env_mirror.cc" ${ROCKSDB_SOURCE_DIR}/utilities/blob_db/blob_file.cc
"${ROCKSDB_SOURCE_DIR}/utilities/env_timed.cc" ${ROCKSDB_SOURCE_DIR}/utilities/cassandra/cassandra_compaction_filter.cc
"${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_env.cc" ${ROCKSDB_SOURCE_DIR}/utilities/cassandra/format.cc
"${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_fs.cc" ${ROCKSDB_SOURCE_DIR}/utilities/cassandra/merge_operator.cc
"${ROCKSDB_SOURCE_DIR}/utilities/leveldb_options/leveldb_options.cc" ${ROCKSDB_SOURCE_DIR}/utilities/checkpoint/checkpoint_impl.cc
"${ROCKSDB_SOURCE_DIR}/utilities/memory/memory_util.cc" ${ROCKSDB_SOURCE_DIR}/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
"${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/bytesxor.cc" ${ROCKSDB_SOURCE_DIR}/utilities/debug.cc
"${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/max.cc" ${ROCKSDB_SOURCE_DIR}/utilities/env_mirror.cc
"${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/put.cc" ${ROCKSDB_SOURCE_DIR}/utilities/env_timed.cc
"${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/sortlist.cc" ${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_env.cc
"${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/string_append/stringappend.cc" ${ROCKSDB_SOURCE_DIR}/utilities/fault_injection_fs.cc
"${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/string_append/stringappend2.cc" ${ROCKSDB_SOURCE_DIR}/utilities/leveldb_options/leveldb_options.cc
"${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/uint64add.cc" ${ROCKSDB_SOURCE_DIR}/utilities/memory/memory_util.cc
"${ROCKSDB_SOURCE_DIR}/utilities/object_registry.cc" ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/bytesxor.cc
"${ROCKSDB_SOURCE_DIR}/utilities/option_change_migration/option_change_migration.cc" ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/max.cc
"${ROCKSDB_SOURCE_DIR}/utilities/options/options_util.cc" ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/put.cc
"${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/block_cache_tier.cc" ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/sortlist.cc
"${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/block_cache_tier_file.cc" ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/string_append/stringappend.cc
"${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/block_cache_tier_metadata.cc" ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/string_append/stringappend2.cc
"${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/persistent_cache_tier.cc" ${ROCKSDB_SOURCE_DIR}/utilities/merge_operators/uint64add.cc
"${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/volatile_tier_impl.cc" ${ROCKSDB_SOURCE_DIR}/utilities/object_registry.cc
"${ROCKSDB_SOURCE_DIR}/utilities/simulator_cache/cache_simulator.cc" ${ROCKSDB_SOURCE_DIR}/utilities/option_change_migration/option_change_migration.cc
"${ROCKSDB_SOURCE_DIR}/utilities/simulator_cache/sim_cache.cc" ${ROCKSDB_SOURCE_DIR}/utilities/options/options_util.cc
"${ROCKSDB_SOURCE_DIR}/utilities/table_properties_collectors/compact_on_deletion_collector.cc" ${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/block_cache_tier.cc
"${ROCKSDB_SOURCE_DIR}/utilities/trace/file_trace_reader_writer.cc" ${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/block_cache_tier_file.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/lock_manager.cc" ${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/block_cache_tier_metadata.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_tracker.cc" ${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/persistent_cache_tier.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_manager.cc" ${ROCKSDB_SOURCE_DIR}/utilities/persistent_cache/volatile_tier_impl.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/optimistic_transaction_db_impl.cc" ${ROCKSDB_SOURCE_DIR}/utilities/simulator_cache/cache_simulator.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/optimistic_transaction.cc" ${ROCKSDB_SOURCE_DIR}/utilities/simulator_cache/sim_cache.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/pessimistic_transaction.cc" ${ROCKSDB_SOURCE_DIR}/utilities/table_properties_collectors/compact_on_deletion_collector.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/pessimistic_transaction_db.cc" ${ROCKSDB_SOURCE_DIR}/utilities/trace/file_trace_reader_writer.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/snapshot_checker.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/lock_manager.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/transaction_base.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_tracker.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/transaction_db_mutex_impl.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/point/point_lock_manager.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/transaction_util.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/range_tree_lock_manager.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_prepared_txn.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/range_tree_lock_tracker.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_prepared_txn_db.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/optimistic_transaction_db_impl.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/optimistic_transaction.cc
"${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn_db.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/pessimistic_transaction.cc
"${ROCKSDB_SOURCE_DIR}/utilities/ttl/db_ttl_impl.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/pessimistic_transaction_db.cc
"${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/snapshot_checker.cc
"${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index_internal.cc" ${ROCKSDB_SOURCE_DIR}/utilities/transactions/transaction_base.cc
$<TARGET_OBJECTS:rocksdb_build_version>) ${ROCKSDB_SOURCE_DIR}/utilities/transactions/transaction_db_mutex_impl.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/transaction_util.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_prepared_txn.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_prepared_txn_db.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/write_unprepared_txn_db.cc
${ROCKSDB_SOURCE_DIR}/utilities/ttl/db_ttl_impl.cc
${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index.cc
${ROCKSDB_SOURCE_DIR}/utilities/write_batch_with_index/write_batch_with_index_internal.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/concurrent_tree.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/keyrange.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/lock_request.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/locktree.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/manager.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/range_buffer.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/treenode.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/txnid_set.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/locktree/wfg.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/standalone_port.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/util/dbt.cc
${ROCKSDB_SOURCE_DIR}/utilities/transactions/lock/range/range_tree/lib/util/memarena.cc
rocksdb_build_version.cc)
if(HAVE_SSE42 AND NOT MSVC) if(HAVE_SSE42 AND NOT MSVC)
set_source_files_properties( set_source_files_properties(

65
contrib/rocksdb-cmake/rocksdb_build_version.cc
View File

@ -1,3 +1,62 @@
const char* rocksdb_build_git_sha = "rocksdb_build_git_sha:0"; // Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
const char* rocksdb_build_git_date = "rocksdb_build_git_date:2000-01-01"; /// This file was edited for ClickHouse.
const char* rocksdb_build_compile_date = "2000-01-01";
#include <memory>
#include "rocksdb/version.h"
#include "util/string_util.h"
// The build script may replace these values with real values based
// on whether or not GIT is available and the platform settings
static const std::string rocksdb_build_git_sha = "rocksdb_build_git_sha:0";
static const std::string rocksdb_build_git_tag = "rocksdb_build_git_tag:master";
static const std::string rocksdb_build_date = "rocksdb_build_date:2000-01-01";
namespace ROCKSDB_NAMESPACE {
static void AddProperty(std::unordered_map<std::string, std::string> *props, const std::string& name) {
size_t colon = name.find(":");
if (colon != std::string::npos && colon > 0 && colon < name.length() - 1) {
// If we found a "@:", then this property was a build-time substitution that failed. Skip it
size_t at = name.find("@", colon);
if (at != colon + 1) {
// Everything before the colon is the name, after is the value
(*props)[name.substr(0, colon)] = name.substr(colon + 1);
}
}
}
static std::unordered_map<std::string, std::string>* LoadPropertiesSet() {
auto * properties = new std::unordered_map<std::string, std::string>();
AddProperty(properties, rocksdb_build_git_sha);
AddProperty(properties, rocksdb_build_git_tag);
AddProperty(properties, rocksdb_build_date);
return properties;
}
const std::unordered_map<std::string, std::string>& GetRocksBuildProperties() {
static std::unique_ptr<std::unordered_map<std::string, std::string>> props(LoadPropertiesSet());
return *props;
}
std::string GetRocksVersionAsString(bool with_patch) {
std::string version = ToString(ROCKSDB_MAJOR) + "." + ToString(ROCKSDB_MINOR);
if (with_patch) {
return version + "." + ToString(ROCKSDB_PATCH);
} else {
return version;
}
}
std::string GetRocksBuildInfoAsString(const std::string& program, bool verbose) {
std::string info = program + " (RocksDB) " + GetRocksVersionAsString(true);
if (verbose) {
for (const auto& it : GetRocksBuildProperties()) {
info.append("\n ");
info.append(it.first);
info.append(": ");
info.append(it.second);
}
}
return info;
}
} // namespace ROCKSDB_NAMESPACE

1
contrib/s2geometry vendored Submodule

@ -0,0 +1 @@
Subproject commit 20ea540d81f4575a3fc0aea585aac611bcd03ede

128
contrib/s2geometry-cmake/CMakeLists.txt Normal file
View File

@ -0,0 +1,128 @@
set(S2_SOURCE_DIR "${ClickHouse_SOURCE_DIR}/contrib/s2geometry/src")
set(S2_SRCS
"${S2_SOURCE_DIR}/s2/base/stringprintf.cc"
"${S2_SOURCE_DIR}/s2/base/strtoint.cc"
"${S2_SOURCE_DIR}/s2/encoded_s2cell_id_vector.cc"
"${S2_SOURCE_DIR}/s2/encoded_s2point_vector.cc"
"${S2_SOURCE_DIR}/s2/encoded_s2shape_index.cc"
"${S2_SOURCE_DIR}/s2/encoded_string_vector.cc"
"${S2_SOURCE_DIR}/s2/id_set_lexicon.cc"
"${S2_SOURCE_DIR}/s2/mutable_s2shape_index.cc"
"${S2_SOURCE_DIR}/s2/r2rect.cc"
"${S2_SOURCE_DIR}/s2/s1angle.cc"
"${S2_SOURCE_DIR}/s2/s1chord_angle.cc"
"${S2_SOURCE_DIR}/s2/s1interval.cc"
"${S2_SOURCE_DIR}/s2/s2boolean_operation.cc"
"${S2_SOURCE_DIR}/s2/s2builder.cc"
"${S2_SOURCE_DIR}/s2/s2builder_graph.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_closed_set_normalizer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_find_polygon_degeneracies.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_lax_polygon_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_s2point_vector_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_s2polygon_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_s2polyline_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_s2polyline_vector_layer.cc"
"${S2_SOURCE_DIR}/s2/s2builderutil_snap_functions.cc"
"${S2_SOURCE_DIR}/s2/s2cap.cc"
"${S2_SOURCE_DIR}/s2/s2cell.cc"
"${S2_SOURCE_DIR}/s2/s2cell_id.cc"
"${S2_SOURCE_DIR}/s2/s2cell_index.cc"
"${S2_SOURCE_DIR}/s2/s2cell_union.cc"
"${S2_SOURCE_DIR}/s2/s2centroids.cc"
"${S2_SOURCE_DIR}/s2/s2closest_cell_query.cc"
"${S2_SOURCE_DIR}/s2/s2closest_edge_query.cc"
"${S2_SOURCE_DIR}/s2/s2closest_point_query.cc"
"${S2_SOURCE_DIR}/s2/s2contains_vertex_query.cc"
"${S2_SOURCE_DIR}/s2/s2convex_hull_query.cc"
"${S2_SOURCE_DIR}/s2/s2coords.cc"
"${S2_SOURCE_DIR}/s2/s2crossing_edge_query.cc"
"${S2_SOURCE_DIR}/s2/s2debug.cc"
"${S2_SOURCE_DIR}/s2/s2earth.cc"
"${S2_SOURCE_DIR}/s2/s2edge_clipping.cc"
"${S2_SOURCE_DIR}/s2/s2edge_crosser.cc"
"${S2_SOURCE_DIR}/s2/s2edge_crossings.cc"
"${S2_SOURCE_DIR}/s2/s2edge_distances.cc"
"${S2_SOURCE_DIR}/s2/s2edge_tessellator.cc"
"${S2_SOURCE_DIR}/s2/s2error.cc"
"${S2_SOURCE_DIR}/s2/s2furthest_edge_query.cc"
"${S2_SOURCE_DIR}/s2/s2latlng.cc"
"${S2_SOURCE_DIR}/s2/s2latlng_rect.cc"
"${S2_SOURCE_DIR}/s2/s2latlng_rect_bounder.cc"
"${S2_SOURCE_DIR}/s2/s2lax_loop_shape.cc"
"${S2_SOURCE_DIR}/s2/s2lax_polygon_shape.cc"
"${S2_SOURCE_DIR}/s2/s2lax_polyline_shape.cc"
"${S2_SOURCE_DIR}/s2/s2loop.cc"
"${S2_SOURCE_DIR}/s2/s2loop_measures.cc"
"${S2_SOURCE_DIR}/s2/s2measures.cc"
"${S2_SOURCE_DIR}/s2/s2metrics.cc"
"${S2_SOURCE_DIR}/s2/s2max_distance_targets.cc"
"${S2_SOURCE_DIR}/s2/s2min_distance_targets.cc"
"${S2_SOURCE_DIR}/s2/s2padded_cell.cc"
"${S2_SOURCE_DIR}/s2/s2point_compression.cc"
"${S2_SOURCE_DIR}/s2/s2point_region.cc"
"${S2_SOURCE_DIR}/s2/s2pointutil.cc"
"${S2_SOURCE_DIR}/s2/s2polygon.cc"
"${S2_SOURCE_DIR}/s2/s2polyline.cc"
"${S2_SOURCE_DIR}/s2/s2polyline_alignment.cc"
"${S2_SOURCE_DIR}/s2/s2polyline_measures.cc"
"${S2_SOURCE_DIR}/s2/s2polyline_simplifier.cc"
"${S2_SOURCE_DIR}/s2/s2predicates.cc"
"${S2_SOURCE_DIR}/s2/s2projections.cc"
"${S2_SOURCE_DIR}/s2/s2r2rect.cc"
"${S2_SOURCE_DIR}/s2/s2region.cc"
"${S2_SOURCE_DIR}/s2/s2region_term_indexer.cc"
"${S2_SOURCE_DIR}/s2/s2region_coverer.cc"
"${S2_SOURCE_DIR}/s2/s2region_intersection.cc"
"${S2_SOURCE_DIR}/s2/s2region_union.cc"
"${S2_SOURCE_DIR}/s2/s2shape_index.cc"
"${S2_SOURCE_DIR}/s2/s2shape_index_buffered_region.cc"
"${S2_SOURCE_DIR}/s2/s2shape_index_measures.cc"
"${S2_SOURCE_DIR}/s2/s2shape_measures.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_build_polygon_boundaries.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_coding.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_contains_brute_force.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_edge_iterator.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_get_reference_point.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_range_iterator.cc"
"${S2_SOURCE_DIR}/s2/s2shapeutil_visit_crossing_edge_pairs.cc"
"${S2_SOURCE_DIR}/s2/s2text_format.cc"
"${S2_SOURCE_DIR}/s2/s2wedge_relations.cc"
"${S2_SOURCE_DIR}/s2/strings/ostringstream.cc"
"${S2_SOURCE_DIR}/s2/strings/serialize.cc"
# ClickHouse doesn't use strings from abseil.
# So, there is no duplicate symbols.
"${S2_SOURCE_DIR}/s2/third_party/absl/base/dynamic_annotations.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/base/internal/raw_logging.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/base/internal/throw_delegate.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/numeric/int128.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/ascii.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/match.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/numbers.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/str_cat.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/str_split.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/string_view.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/strip.cc"
"${S2_SOURCE_DIR}/s2/third_party/absl/strings/internal/memutil.cc"
"${S2_SOURCE_DIR}/s2/util/bits/bit-interleave.cc"
"${S2_SOURCE_DIR}/s2/util/bits/bits.cc"
"${S2_SOURCE_DIR}/s2/util/coding/coder.cc"
"${S2_SOURCE_DIR}/s2/util/coding/varint.cc"
"${S2_SOURCE_DIR}/s2/util/math/exactfloat/exactfloat.cc"
"${S2_SOURCE_DIR}/s2/util/math/mathutil.cc"
"${S2_SOURCE_DIR}/s2/util/units/length-units.cc"
)
add_library(s2 ${S2_SRCS})
set_property(TARGET s2 PROPERTY CXX_STANDARD 11)
if (OPENSSL_FOUND)
target_link_libraries(s2 PRIVATE ${OPENSSL_LIBRARIES})
endif()
target_include_directories(s2 SYSTEM BEFORE PUBLIC "${S2_SOURCE_DIR}/")
if(M_LIBRARY)
target_link_libraries(s2 PRIVATE ${M_LIBRARY})
endif()

1
contrib/sqlite-amalgamation vendored Submodule

@ -0,0 +1 @@
Subproject commit 9818baa5d027ffb26d57f810dc4c597d4946781c

6
contrib/sqlite-cmake/CMakeLists.txt Normal file
View File

@ -0,0 +1,6 @@
set (LIBRARY_DIR "${ClickHouse_SOURCE_DIR}/contrib/sqlite-amalgamation")
set(SRCS ${LIBRARY_DIR}/sqlite3.c)
add_library(sqlite ${SRCS})
target_include_directories(sqlite SYSTEM PUBLIC "${LIBRARY_DIR}")

4
debian/changelog vendored
View File

@ -1,5 +1,5 @@
clickhouse (21.8.1.1) unstable; urgency=low clickhouse (21.9.1.1) unstable; urgency=low
* Modified source code * Modified source code
-- clickhouse-release <clickhouse-release@yandex-team.ru> Mon, 28 Jun 2021 00:50:15 +0300 -- clickhouse-release <clickhouse-release@yandex-team.ru> Sat, 10 Jul 2021 08:22:49 +0300

2
docker/client/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04 FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/" ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=21.8.1.* ARG version=21.9.1.*
RUN apt-get update \ RUN apt-get update \
&& apt-get install --yes --no-install-recommends \ && apt-get install --yes --no-install-recommends \

2
docker/packager/deb/Dockerfile
View File

@ -27,7 +27,7 @@ RUN apt-get update \
# Special dpkg-deb (https://github.com/ClickHouse-Extras/dpkg) version which is able # Special dpkg-deb (https://github.com/ClickHouse-Extras/dpkg) version which is able
# to compress files using pigz (https://zlib.net/pigz/) instead of gzip. # to compress files using pigz (https://zlib.net/pigz/) instead of gzip.
# Significantly increase deb packaging speed and compatible with old systems # Significantly increase deb packaging speed and compatible with old systems
RUN curl -O https://clickhouse-builds.s3.yandex.net/utils/1/dpkg-deb \ RUN curl -O https://clickhouse-datasets.s3.yandex.net/utils/1/dpkg-deb \
&& chmod +x dpkg-deb \ && chmod +x dpkg-deb \
&& cp dpkg-deb /usr/bin && cp dpkg-deb /usr/bin

2
docker/packager/unbundled/Dockerfile
View File

@ -2,7 +2,7 @@
FROM yandex/clickhouse-deb-builder FROM yandex/clickhouse-deb-builder
RUN export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \ RUN export CODENAME="$(lsb_release --codename --short | tr 'A-Z' 'a-z')" \
&& wget -nv -O /tmp/arrow-keyring.deb "https://apache.bintray.com/arrow/ubuntu/apache-arrow-archive-keyring-latest-${CODENAME}.deb" \ && wget -nv -O /tmp/arrow-keyring.deb "https://apache.jfrog.io/artifactory/arrow/ubuntu/apache-arrow-apt-source-latest-${CODENAME}.deb" \
&& dpkg -i /tmp/arrow-keyring.deb && dpkg -i /tmp/arrow-keyring.deb
# Libraries from OS are only needed to test the "unbundled" build (that is not used in production). # Libraries from OS are only needed to test the "unbundled" build (that is not used in production).

2
docker/server/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:20.04 FROM ubuntu:20.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/" ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=21.8.1.* ARG version=21.9.1.*
ARG gosu_ver=1.10 ARG gosu_ver=1.10
# set non-empty deb_location_url url to create a docker image # set non-empty deb_location_url url to create a docker image

5
docker/server/entrypoint.sh
View File

@ -72,7 +72,10 @@ do
if [ "$DO_CHOWN" = "1" ]; then if [ "$DO_CHOWN" = "1" ]; then
# ensure proper directories permissions # ensure proper directories permissions
chown -R "$USER:$GROUP" "$dir" # but skip it for if directory already has proper premissions, cause recursive chown may be slow
if [ "$(stat -c %u "$dir")" != "$USER" ] || [ "$(stat -c %g "$dir")" != "$GROUP" ]; then
chown -R "$USER:$GROUP" "$dir"
fi
elif ! $gosu test -d "$dir" -a -w "$dir" -a -r "$dir"; then elif ! $gosu test -d "$dir" -a -w "$dir" -a -r "$dir"; then
echo "Necessary directory '$dir' isn't accessible by user with id '$USER'" echo "Necessary directory '$dir' isn't accessible by user with id '$USER'"
exit 1 exit 1

2
docker/test/Dockerfile
View File

@ -1,7 +1,7 @@
FROM ubuntu:18.04 FROM ubuntu:18.04
ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/" ARG repository="deb https://repo.clickhouse.tech/deb/stable/ main/"
ARG version=21.8.1.* ARG version=21.9.1.*
RUN apt-get update && \ RUN apt-get update && \
apt-get install -y apt-transport-https dirmngr && \ apt-get install -y apt-transport-https dirmngr && \

2
docker/test/base/Dockerfile
View File

@ -27,7 +27,7 @@ RUN apt-get update \
# Special dpkg-deb (https://github.com/ClickHouse-Extras/dpkg) version which is able # Special dpkg-deb (https://github.com/ClickHouse-Extras/dpkg) version which is able
# to compress files using pigz (https://zlib.net/pigz/) instead of gzip. # to compress files using pigz (https://zlib.net/pigz/) instead of gzip.
# Significantly increase deb packaging speed and compatible with old systems # Significantly increase deb packaging speed and compatible with old systems
RUN curl -O https://clickhouse-builds.s3.yandex.net/utils/1/dpkg-deb \ RUN curl -O https://clickhouse-datasets.s3.yandex.net/utils/1/dpkg-deb \
&& chmod +x dpkg-deb \ && chmod +x dpkg-deb \
&& cp dpkg-deb /usr/bin && cp dpkg-deb /usr/bin

4
docker/test/fasttest/Dockerfile
View File

@ -27,7 +27,7 @@ RUN apt-get update \
# Special dpkg-deb (https://github.com/ClickHouse-Extras/dpkg) version which is able # Special dpkg-deb (https://github.com/ClickHouse-Extras/dpkg) version which is able
# to compress files using pigz (https://zlib.net/pigz/) instead of gzip. # to compress files using pigz (https://zlib.net/pigz/) instead of gzip.
# Significantly increase deb packaging speed and compatible with old systems # Significantly increase deb packaging speed and compatible with old systems
RUN curl -O https://clickhouse-builds.s3.yandex.net/utils/1/dpkg-deb \ RUN curl -O https://clickhouse-datasets.s3.yandex.net/utils/1/dpkg-deb \
&& chmod +x dpkg-deb \ && chmod +x dpkg-deb \
&& cp dpkg-deb /usr/bin && cp dpkg-deb /usr/bin
@ -65,7 +65,7 @@ RUN apt-get update \
unixodbc \ unixodbc \
--yes --no-install-recommends --yes --no-install-recommends
RUN pip3 install numpy scipy pandas RUN pip3 install numpy scipy pandas Jinja2
# This symlink required by gcc to find lld compiler # This symlink required by gcc to find lld compiler
RUN ln -s /usr/bin/lld-${LLVM_VERSION} /usr/bin/ld.lld RUN ln -s /usr/bin/lld-${LLVM_VERSION} /usr/bin/ld.lld

10
docker/test/fasttest/run.sh
View File

@ -378,6 +378,16 @@ function run_tests
# needs pv # needs pv
01923_network_receive_time_metric_insert 01923_network_receive_time_metric_insert
01889_sqlite_read_write
# needs s2
01849_geoToS2
01851_s2_to_geo
01852_s2_get_neighbours
01853_s2_cells_intersect
01854_s2_cap_contains
01854_s2_cap_union
) )
time clickhouse-test --hung-check -j 8 --order=random --use-skip-list \ time clickhouse-test --hung-check -j 8 --order=random --use-skip-list \

3
docker/test/integration/base/Dockerfile
View File

@ -32,7 +32,7 @@ RUN rm -rf \
RUN apt-get clean RUN apt-get clean
# Install MySQL ODBC driver # Install MySQL ODBC driver
RUN curl 'https://cdn.mysql.com//Downloads/Connector-ODBC/8.0/mysql-connector-odbc-8.0.21-linux-glibc2.12-x86-64bit.tar.gz' --output 'mysql-connector.tar.gz' && tar -xzf mysql-connector.tar.gz && cd mysql-connector-odbc-8.0.21-linux-glibc2.12-x86-64bit/lib && mv * /usr/local/lib && ln -s /usr/local/lib/libmyodbc8a.so /usr/lib/x86_64-linux-gnu/odbc/libmyodbc.so RUN curl 'https://downloads.mysql.com/archives/get/p/10/file/mysql-connector-odbc-8.0.21-linux-glibc2.12-x86-64bit.tar.gz' --location --output 'mysql-connector.tar.gz' && tar -xzf mysql-connector.tar.gz && cd mysql-connector-odbc-8.0.21-linux-glibc2.12-x86-64bit/lib && mv * /usr/local/lib && ln -s /usr/local/lib/libmyodbc8a.so /usr/lib/x86_64-linux-gnu/odbc/libmyodbc.so
# Unfortunately this is required for a single test for conversion data from zookeeper to clickhouse-keeper. # Unfortunately this is required for a single test for conversion data from zookeeper to clickhouse-keeper.
# ZooKeeper is not started by default, but consumes some space in containers. # ZooKeeper is not started by default, but consumes some space in containers.
@ -49,4 +49,3 @@ RUN mkdir /zookeeper && chmod -R 777 /zookeeper
ENV TZ=Europe/Moscow ENV TZ=Europe/Moscow
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone

1
docker/test/integration/runner/Dockerfile
View File

@ -76,6 +76,7 @@ RUN python3 -m pip install \
pytest \ pytest \
pytest-timeout \ pytest-timeout \
pytest-xdist \ pytest-xdist \
pytest-repeat \
redis \ redis \
tzlocal \ tzlocal \
urllib3 \ urllib3 \

2
docker/test/integration/runner/compose/docker_compose_postgres.yml
View File

@ -2,7 +2,7 @@ version: '2.3'
services: services:
postgres1: postgres1:
image: postgres image: postgres
command: ["postgres", "-c", "logging_collector=on", "-c", "log_directory=/postgres/logs", "-c", "log_filename=postgresql.log", "-c", "log_statement=all"] command: ["postgres", "-c", "logging_collector=on", "-c", "log_directory=/postgres/logs", "-c", "log_filename=postgresql.log", "-c", "log_statement=all", "-c", "max_connections=200"]
restart: always restart: always
expose: expose:
- ${POSTGRES_PORT} - ${POSTGRES_PORT}

5
docker/test/stateless/Dockerfile
View File

@ -29,9 +29,10 @@ RUN apt-get update -y \
unixodbc \ unixodbc \
wget \ wget \
mysql-client=5.7* \ mysql-client=5.7* \
postgresql-client postgresql-client \
sqlite3
RUN pip3 install numpy scipy pandas RUN pip3 install numpy scipy pandas Jinja2
RUN mkdir -p /tmp/clickhouse-odbc-tmp \ RUN mkdir -p /tmp/clickhouse-odbc-tmp \
&& wget -nv -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \ && wget -nv -O - ${odbc_driver_url} | tar --strip-components=1 -xz -C /tmp/clickhouse-odbc-tmp \

5
docker/test/stateless/process_functional_tests_result.py
View File

@ -12,7 +12,7 @@ UNKNOWN_SIGN = "[ UNKNOWN "
SKIPPED_SIGN = "[ SKIPPED " SKIPPED_SIGN = "[ SKIPPED "
HUNG_SIGN = "Found hung queries in processlist" HUNG_SIGN = "Found hung queries in processlist"
NO_TASK_TIMEOUT_SIGN = "All tests have finished" NO_TASK_TIMEOUT_SIGNS = ["All tests have finished", "No tests were run"]
RETRIES_SIGN = "Some tests were restarted" RETRIES_SIGN = "Some tests were restarted"
@ -29,7 +29,7 @@ def process_test_log(log_path):
with open(log_path, 'r') as test_file: with open(log_path, 'r') as test_file:
for line in test_file: for line in test_file:
line = line.strip() line = line.strip()
if NO_TASK_TIMEOUT_SIGN in line: if any(s in line for s in NO_TASK_TIMEOUT_SIGNS):
task_timeout = False task_timeout = False
if HUNG_SIGN in line: if HUNG_SIGN in line:
hung = True hung = True
@ -80,6 +80,7 @@ def process_result(result_path):
if result_path and os.path.exists(result_path): if result_path and os.path.exists(result_path):
total, skipped, unknown, failed, success, hung, task_timeout, retries, test_results = process_test_log(result_path) total, skipped, unknown, failed, success, hung, task_timeout, retries, test_results = process_test_log(result_path)
is_flacky_check = 1 < int(os.environ.get('NUM_TRIES', 1)) is_flacky_check = 1 < int(os.environ.get('NUM_TRIES', 1))
logging.info("Is flacky check: %s", is_flacky_check)
# If no tests were run (success == 0) it indicates an error (e.g. server did not start or crashed immediately) # If no tests were run (success == 0) it indicates an error (e.g. server did not start or crashed immediately)
# But it's Ok for "flaky checks" - they can contain just one test for check which is marked as skipped. # But it's Ok for "flaky checks" - they can contain just one test for check which is marked as skipped.
if failed != 0 or unknown != 0 or (success == 0 and (not is_flacky_check)): if failed != 0 or unknown != 0 or (success == 0 and (not is_flacky_check)):

16
docker/test/stress/run.sh
View File

@ -58,11 +58,11 @@ function start()
echo "Cannot start clickhouse-server" echo "Cannot start clickhouse-server"
cat /var/log/clickhouse-server/stdout.log cat /var/log/clickhouse-server/stdout.log
tail -n1000 /var/log/clickhouse-server/stderr.log tail -n1000 /var/log/clickhouse-server/stderr.log
tail -n1000 /var/log/clickhouse-server/clickhouse-server.log tail -n100000 /var/log/clickhouse-server/clickhouse-server.log | grep -F -v '<Warning> RaftInstance:' -e '<Information> RaftInstance' | tail -n1000
break break
fi fi
# use root to match with current uid # use root to match with current uid
clickhouse start --user root >/var/log/clickhouse-server/stdout.log 2>/var/log/clickhouse-server/stderr.log clickhouse start --user root >/var/log/clickhouse-server/stdout.log 2>>/var/log/clickhouse-server/stderr.log
sleep 0.5 sleep 0.5
counter=$((counter + 1)) counter=$((counter + 1))
done done
@ -118,35 +118,35 @@ clickhouse-client --query "SELECT 'Server successfully started', 'OK'" >> /test_
[ -f /var/log/clickhouse-server/stderr.log ] || echo -e "Stderr log does not exist\tFAIL" [ -f /var/log/clickhouse-server/stderr.log ] || echo -e "Stderr log does not exist\tFAIL"
# Print Fatal log messages to stdout # Print Fatal log messages to stdout
zgrep -Fa " <Fatal> " /var/log/clickhouse-server/clickhouse-server.log zgrep -Fa " <Fatal> " /var/log/clickhouse-server/clickhouse-server.log*
# Grep logs for sanitizer asserts, crashes and other critical errors # Grep logs for sanitizer asserts, crashes and other critical errors
# Sanitizer asserts # Sanitizer asserts
zgrep -Fa "==================" /var/log/clickhouse-server/stderr.log >> /test_output/tmp zgrep -Fa "==================" /var/log/clickhouse-server/stderr.log >> /test_output/tmp
zgrep -Fa "WARNING" /var/log/clickhouse-server/stderr.log >> /test_output/tmp zgrep -Fa "WARNING" /var/log/clickhouse-server/stderr.log >> /test_output/tmp
zgrep -Fav "ASan doesn't fully support makecontext/swapcontext functions" > /dev/null \ zgrep -Fav "ASan doesn't fully support makecontext/swapcontext functions" /test_output/tmp > /dev/null \
&& echo -e 'Sanitizer assert (in stderr.log)\tFAIL' >> /test_output/test_results.tsv \ && echo -e 'Sanitizer assert (in stderr.log)\tFAIL' >> /test_output/test_results.tsv \
|| echo -e 'No sanitizer asserts\tOK' >> /test_output/test_results.tsv || echo -e 'No sanitizer asserts\tOK' >> /test_output/test_results.tsv
rm -f /test_output/tmp rm -f /test_output/tmp
# OOM # OOM
zgrep -Fa " <Fatal> Application: Child process was terminated by signal 9" /var/log/clickhouse-server/clickhouse-server.log > /dev/null \ zgrep -Fa " <Fatal> Application: Child process was terminated by signal 9" /var/log/clickhouse-server/clickhouse-server.log* > /dev/null \
&& echo -e 'OOM killer (or signal 9) in clickhouse-server.log\tFAIL' >> /test_output/test_results.tsv \ && echo -e 'OOM killer (or signal 9) in clickhouse-server.log\tFAIL' >> /test_output/test_results.tsv \
|| echo -e 'No OOM messages in clickhouse-server.log\tOK' >> /test_output/test_results.tsv || echo -e 'No OOM messages in clickhouse-server.log\tOK' >> /test_output/test_results.tsv
# Logical errors # Logical errors
zgrep -Fa "Code: 49, e.displayText() = DB::Exception:" /var/log/clickhouse-server/clickhouse-server.log > /dev/null \ zgrep -Fa "Code: 49, e.displayText() = DB::Exception:" /var/log/clickhouse-server/clickhouse-server.log* > /dev/null \
&& echo -e 'Logical error thrown (see clickhouse-server.log)\tFAIL' >> /test_output/test_results.tsv \ && echo -e 'Logical error thrown (see clickhouse-server.log)\tFAIL' >> /test_output/test_results.tsv \
|| echo -e 'No logical errors\tOK' >> /test_output/test_results.tsv || echo -e 'No logical errors\tOK' >> /test_output/test_results.tsv
# Crash # Crash
zgrep -Fa "########################################" /var/log/clickhouse-server/clickhouse-server.log > /dev/null \ zgrep -Fa "########################################" /var/log/clickhouse-server/clickhouse-server.log* > /dev/null \
&& echo -e 'Killed by signal (in clickhouse-server.log)\tFAIL' >> /test_output/test_results.tsv \ && echo -e 'Killed by signal (in clickhouse-server.log)\tFAIL' >> /test_output/test_results.tsv \
|| echo -e 'Not crashed\tOK' >> /test_output/test_results.tsv || echo -e 'Not crashed\tOK' >> /test_output/test_results.tsv
# It also checks for crash without stacktrace (printed by watchdog) # It also checks for crash without stacktrace (printed by watchdog)
zgrep -Fa " <Fatal> " /var/log/clickhouse-server/clickhouse-server.log > /dev/null \ zgrep -Fa " <Fatal> " /var/log/clickhouse-server/clickhouse-server.log* > /dev/null \
&& echo -e 'Fatal message in clickhouse-server.log\tFAIL' >> /test_output/test_results.tsv \ && echo -e 'Fatal message in clickhouse-server.log\tFAIL' >> /test_output/test_results.tsv \
|| echo -e 'No fatal messages in clickhouse-server.log\tOK' >> /test_output/test_results.tsv || echo -e 'No fatal messages in clickhouse-server.log\tOK' >> /test_output/test_results.tsv

16
docs/en/development/adding_test_queries.md
View File

@ -105,11 +105,11 @@ clickhouse-client -nmT < tests/queries/0_stateless/01521_dummy_test.sql | tee te
5) ensure everything is correct, if the test output is incorrect (due to some bug for example), adjust the reference file using text editor. 5) ensure everything is correct, if the test output is incorrect (due to some bug for example), adjust the reference file using text editor.
#### How to create good test #### How to create a good test
- test should be - A test should be
- minimal - create only tables related to tested functionality, remove unrelated columns and parts of query - minimal - create only tables related to tested functionality, remove unrelated columns and parts of query
- fast - should not take longer than few seconds (better subseconds) - fast - should not take longer than a few seconds (better subseconds)
- correct - fails then feature is not working - correct - fails then feature is not working
- deterministic - deterministic
- isolated / stateless - isolated / stateless
@ -126,6 +126,16 @@ clickhouse-client -nmT < tests/queries/0_stateless/01521_dummy_test.sql | tee te
- use other SQL files in the `0_stateless` folder as an example - use other SQL files in the `0_stateless` folder as an example
- ensure the feature / feature combination you want to test is not yet covered with existing tests - ensure the feature / feature combination you want to test is not yet covered with existing tests
#### Test naming rules
It's important to name tests correctly, so one could turn some tests subset off in clickhouse-test invocation.
| Tester flag| What should be in test name | When flag should be added |
|---|---|---|---|
| `--[no-]zookeeper`| "zookeeper" or "replica" | Test uses tables from ReplicatedMergeTree family |
| `--[no-]shard` | "shard" or "distributed" or "global"| Test using connections to 127.0.0.2 or similar |
| `--[no-]long` | "long" or "deadlock" or "race" | Test runs longer than 60 seconds |
#### Commit / push / create PR. #### Commit / push / create PR.
1) commit & push your changes 1) commit & push your changes

4
docs/en/development/build.md
View File

@ -134,10 +134,10 @@ $ ./release
## Faster builds for development ## Faster builds for development
Normally all tools of the ClickHouse bundle, such as `clickhouse-server`, `clickhouse-client` etc., are linked into a single static executable, `clickhouse`. This executable must be re-linked on every change, which might be slow. Two common ways to improve linking time are to use `lld` linker, and use the 'split' build configuration, which builds a separate binary for every tool, and further splits the code into several shared libraries. To enable these tweaks, pass the following flags to `cmake`: Normally all tools of the ClickHouse bundle, such as `clickhouse-server`, `clickhouse-client` etc., are linked into a single static executable, `clickhouse`. This executable must be re-linked on every change, which might be slow. One common way to improve build time is to use the 'split' build configuration, which builds a separate binary for every tool, and further splits the code into several shared libraries. To enable this tweak, pass the following flags to `cmake`:
``` ```
-DCMAKE_C_FLAGS="--ld-path=lld" -DCMAKE_CXX_FLAGS="--ld-path=lld" -DUSE_STATIC_LIBRARIES=0 -DSPLIT_SHARED_LIBRARIES=1 -DCLICKHOUSE_SPLIT_BINARY=1 -DUSE_STATIC_LIBRARIES=0 -DSPLIT_SHARED_LIBRARIES=1 -DCLICKHOUSE_SPLIT_BINARY=1
``` ```
## You Don’t Have to Build ClickHouse {#you-dont-have-to-build-clickhouse} ## You Don’t Have to Build ClickHouse {#you-dont-have-to-build-clickhouse}

1
docs/en/development/contrib.md
View File

@ -79,6 +79,7 @@ SELECT library_name, license_type, license_path FROM system.licenses ORDER BY li
| re2 | BSD 3-clause | /contrib/re2/LICENSE | | re2 | BSD 3-clause | /contrib/re2/LICENSE |
| replxx | BSD 3-clause | /contrib/replxx/LICENSE.md | | replxx | BSD 3-clause | /contrib/replxx/LICENSE.md |
| rocksdb | BSD 3-clause | /contrib/rocksdb/LICENSE.leveldb | | rocksdb | BSD 3-clause | /contrib/rocksdb/LICENSE.leveldb |
| s2geometry | Apache | /contrib/s2geometry/LICENSE |
| sentry-native | MIT | /contrib/sentry-native/LICENSE | | sentry-native | MIT | /contrib/sentry-native/LICENSE |
| simdjson | Apache | /contrib/simdjson/LICENSE | | simdjson | Apache | /contrib/simdjson/LICENSE |
| snappy | Public Domain | /contrib/snappy/COPYING | | snappy | Public Domain | /contrib/snappy/COPYING |

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

@ -123,7 +123,7 @@ For installing CMake and Ninja on Mac OS X first install Homebrew and then insta
/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)" /usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"
brew install cmake ninja brew install cmake ninja
Next, check the version of CMake: `cmake --version`. If it is below 3.3, you should install a newer version from the website: https://cmake.org/download/. Next, check the version of CMake: `cmake --version`. If it is below 3.12, you should install a newer version from the website: https://cmake.org/download/.
## Optional External Libraries {#optional-external-libraries} ## Optional External Libraries {#optional-external-libraries}

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

@ -47,7 +47,7 @@ EXCHANGE TABLES new_table AND old_table;
### ReplicatedMergeTree in Atomic Database {#replicatedmergetree-in-atomic-database} ### ReplicatedMergeTree in Atomic Database {#replicatedmergetree-in-atomic-database}
For [ReplicatedMergeTree](../table-engines/mergetree-family/replication.md#table_engines-replication) tables, it is recommended to not specify engine parameters - path in ZooKeeper and replica name. In this case, configuration parameters will be used [default_replica_path](../../operations/server-configuration-parameters/settings.md#default_replica_path) and [default_replica_name](../../operations/server-configuration-parameters/settings.md#default_replica_name). If you want to specify engine parameters explicitly, it is recommended to use {uuid} macros. This is useful so that unique paths are automatically generated for each table in ZooKeeper. For [ReplicatedMergeTree](../table-engines/mergetree-family/replication.md#table_engines-replication) tables, it is recommended to not specify engine parameters - path in ZooKeeper and replica name. In this case, configuration parameters will be used [default_replica_path](../../operations/server-configuration-parameters/settings.md#default_replica_path) and [default_replica_name](../../operations/server-configuration-parameters/settings.md#default_replica_name). If you want to specify engine parameters explicitly, it is recommended to use `{uuid}` macros. This is useful so that unique paths are automatically generated for each table in ZooKeeper.
## See Also ## See Also

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

@ -22,4 +22,4 @@ You can also use the following database engines:
- [PostgreSQL](../../engines/database-engines/postgresql.md) - [PostgreSQL](../../engines/database-engines/postgresql.md)
[Original article](https://clickhouse.tech/docs/en/database_engines/) <!--hide--> - [Replicated](../../engines/database-engines/replicated.md)

2
docs/en/engines/database-engines/materialize-mysql.md
View File

@ -82,6 +82,8 @@ MySQL DDL queries are converted into the corresponding ClickHouse DDL queries ([
- If `_sign` is not specified in the `SELECT` query, `WHERE _sign=1` is used by default. So the deleted rows are not included into the result set. - If `_sign` is not specified in the `SELECT` query, `WHERE _sign=1` is used by default. So the deleted rows are not included into the result set.
- The result includes columns comments in case they exist in MySQL database tables.
### Index Conversion {#index-conversion} ### Index Conversion {#index-conversion}
MySQL `PRIMARY KEY` and `INDEX` clauses are converted into `ORDER BY` tuples in ClickHouse tables. MySQL `PRIMARY KEY` and `INDEX` clauses are converted into `ORDER BY` tuples in ClickHouse tables.

115
docs/en/engines/database-engines/replicated.md Normal file
View File

@ -0,0 +1,115 @@
# [experimental] Replicated {#replicated}
The engine is based on the [Atomic](../../engines/database-engines/atomic.md) engine. It supports replication of metadata via DDL log being written to ZooKeeper and executed on all of the replicas for a given database.
One ClickHouse server can have multiple replicated databases running and updating at the same time. But there can't be multiple replicas of the same replicated database.
## Creating a Database {#creating-a-database}
``` sql
CREATE DATABASE testdb ENGINE = Replicated('zoo_path', 'shard_name', 'replica_name') [SETTINGS ...]
```
**Engine Parameters**
- `zoo_path` — ZooKeeper path. The same ZooKeeper path corresponds to the same database.
- `shard_name` — Shard name. Database replicas are grouped into shards by `shard_name`.
- `replica_name` — Replica name. Replica names must be different for all replicas of the same shard.
!!! note "Warning"
For [ReplicatedMergeTree](../table-engines/mergetree-family/replication.md#table_engines-replication) tables if no arguments provided, then default arguments are used: `/clickhouse/tables/{uuid}/{shard}` and `{replica}`. These can be changed in the server settings [default_replica_path](../../operations/server-configuration-parameters/settings.md#default_replica_path) and [default_replica_name](../../operations/server-configuration-parameters/settings.md#default_replica_name). Macro `{uuid}` is unfolded to table's uuid, `{shard}` and `{replica}` are unfolded to values from server config, not from database engine arguments. But in the future, it will be possible to use `shard_name` and `replica_name` of Replicated database.
## Specifics and Recommendations {#specifics-and-recommendations}
DDL queries with `Replicated` database work in a similar way to [ON CLUSTER](../../sql-reference/distributed-ddl.md) queries, but with minor differences.
First, the DDL request tries to execute on the initiator (the host that originally received the request from the user). If the request is not fulfilled, then the user immediately receives an error, other hosts do not try to fulfill it. If the request has been successfully completed on the initiator, then all other hosts will automatically retry until they complete it. The initiator will try to wait for the query to be completed on other hosts (no longer than [distributed_ddl_task_timeout](../../operations/settings/settings.md#distributed_ddl_task_timeout)) and will return a table with the query execution statuses on each host.
The behavior in case of errors is regulated by the [distributed_ddl_output_mode](../../operations/settings/settings.md#distributed_ddl_output_mode) setting, for a `Replicated` database it is better to set it to `null_status_on_timeout` — i.e. if some hosts did not have time to execute the request for [distributed_ddl_task_timeout](../../operations/settings/settings.md#distributed_ddl_task_timeout), then do not throw an exception, but show the `NULL` status for them in the table.
The [system.clusters](../../operations/system-tables/clusters.md) system table contains a cluster named like the replicated database, which consists of all replicas of the database. This cluster is updated automatically when creating/deleting replicas, and it can be used for [Distributed](../../engines/table-engines/special/distributed.md#distributed) tables.
When creating a new replica of the database, this replica creates tables by itself. If the replica has been unavailable for a long time and has lagged behind the replication log — it checks its local metadata with the current metadata in ZooKeeper, moves the extra tables with data to a separate non-replicated database (so as not to accidentally delete anything superfluous), creates the missing tables, updates the table names if they have been renamed. The data is replicated at the `ReplicatedMergeTree` level, i.e. if the table is not replicated, the data will not be replicated (the database is responsible only for metadata).
## Usage Example {#usage-example}
Creating a cluster with three hosts:
``` sql
node1 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','shard1','replica1');
node2 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','shard1','other_replica');
node3 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','other_shard','{replica}');
```
Running the DDL-query:
``` sql
CREATE TABLE r.rmt (n UInt64) ENGINE=ReplicatedMergeTree ORDER BY n;
```
``` text
┌─────hosts────────────┬──status─┬─error─┬─num_hosts_remaining─┬─num_hosts_active─┐
│ shard1|replica1 │ 0 │ │ 2 │ 0 │
│ shard1|other_replica │ 0 │ │ 1 │ 0 │
│ other_shard|r1 │ 0 │ │ 0 │ 0 │
└──────────────────────┴─────────┴───────┴─────────────────────┴──────────────────┘
```
Showing the system table:
``` sql
SELECT cluster, shard_num, replica_num, host_name, host_address, port, is_local
FROM system.clusters WHERE cluster='r';
```
``` text
┌─cluster─┬─shard_num─┬─replica_num─┬─host_name─┬─host_address─┬─port─┬─is_local─┐
│ r │ 1 │ 1 │ node3 │ 127.0.0.1 │ 9002 │ 0 │
│ r │ 2 │ 1 │ node2 │ 127.0.0.1 │ 9001 │ 0 │
│ r │ 2 │ 2 │ node1 │ 127.0.0.1 │ 9000 │ 1 │
└─────────┴───────────┴─────────────┴───────────┴──────────────┴──────┴──────────┘
```
Creating a distributed table and inserting the data:
``` sql
node2 :) CREATE TABLE r.d (n UInt64) ENGINE=Distributed('r','r','rmt', n % 2);
node3 :) INSERT INTO r SELECT * FROM numbers(10);
node1 :) SELECT materialize(hostName()) AS host, groupArray(n) FROM r.d GROUP BY host;
```
``` text
┌─hosts─┬─groupArray(n)─┐
│ node1 │ [1,3,5,7,9] │
│ node2 │ [0,2,4,6,8] │
└───────┴───────────────┘
```
Adding replica on the one more host:
``` sql
node4 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','other_shard','r2');
```
The cluster configuration will look like this:
``` text
┌─cluster─┬─shard_num─┬─replica_num─┬─host_name─┬─host_address─┬─port─┬─is_local─┐
│ r │ 1 │ 1 │ node3 │ 127.0.0.1 │ 9002 │ 0 │
│ r │ 1 │ 2 │ node4 │ 127.0.0.1 │ 9003 │ 0 │
│ r │ 2 │ 1 │ node2 │ 127.0.0.1 │ 9001 │ 0 │
│ r │ 2 │ 2 │ node1 │ 127.0.0.1 │ 9000 │ 1 │
└─────────┴───────────┴─────────────┴───────────┴──────────────┴──────┴──────────┘
```
The distributed table also will get data from the new host:
```sql
node2 :) SELECT materialize(hostName()) AS host, groupArray(n) FROM r.d GROUP BY host;
```
```text
┌─hosts─┬─groupArray(n)─┐
│ node2 │ [1,3,5,7,9] │
│ node4 │ [0,2,4,6,8] │
└───────┴───────────────┘
```

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

@ -1,6 +1,6 @@
--- ---
toc_priority: 12 toc_priority: 12
toc_title: MateriaziePostgreSQL toc_title: MaterializedPostgreSQL
--- ---
# MaterializedPostgreSQL {#materialize-postgresql} # MaterializedPostgreSQL {#materialize-postgresql}

2
docs/en/engines/table-engines/mergetree-family/mergetree.md
View File

@ -76,7 +76,7 @@ For a description of parameters, see the [CREATE query description](../../../sql
- `SAMPLE BY` — An expression for sampling. Optional. - `SAMPLE BY` — An expression for sampling. Optional.
If a sampling expression is used, the primary key must contain it. Example: `SAMPLE BY intHash32(UserID) ORDER BY (CounterID, EventDate, intHash32(UserID))`. If a sampling expression is used, the primary key must contain it. The result of sampling expression must be unsigned integer. Example: `SAMPLE BY intHash32(UserID) ORDER BY (CounterID, EventDate, intHash32(UserID))`.
- `TTL` — A list of rules specifying storage duration of rows and defining logic of automatic parts movement [between disks and volumes](#table_engine-mergetree-multiple-volumes). Optional. - `TTL` — A list of rules specifying storage duration of rows and defining logic of automatic parts movement [between disks and volumes](#table_engine-mergetree-multiple-volumes). Optional.

8
docs/en/engines/table-engines/special/distributed.md
View File

@ -37,6 +37,14 @@ Also, it accepts the following settings:
- `max_delay_to_insert` - max delay of inserting data into Distributed table in seconds, if there are a lot of pending bytes for async send. Default 60. - `max_delay_to_insert` - max delay of inserting data into Distributed table in seconds, if there are a lot of pending bytes for async send. Default 60.
- `monitor_batch_inserts` - same as [distributed_directory_monitor_batch_inserts](../../../operations/settings/settings.md#distributed_directory_monitor_batch_inserts)
- `monitor_split_batch_on_failure` - same as [distributed_directory_monitor_split_batch_on_failure](../../../operations/settings/settings.md#distributed_directory_monitor_split_batch_on_failure)
- `monitor_sleep_time_ms` - same as [distributed_directory_monitor_sleep_time_ms](../../../operations/settings/settings.md#distributed_directory_monitor_sleep_time_ms)
- `monitor_max_sleep_time_ms` - same as [distributed_directory_monitor_max_sleep_time_ms](../../../operations/settings/settings.md#distributed_directory_monitor_max_sleep_time_ms)
!!! note "Note" !!! note "Note"
**Durability settings** (`fsync_...`): **Durability settings** (`fsync_...`):

33
docs/en/interfaces/formats.md
View File

@ -1130,17 +1130,18 @@ The table below shows supported data types and how they match ClickHouse [data t
| `boolean`, `int`, `long`, `float`, `double` | [Int64](../sql-reference/data-types/int-uint.md), [UInt64](../sql-reference/data-types/int-uint.md) | `long` | | `boolean`, `int`, `long`, `float`, `double` | [Int64](../sql-reference/data-types/int-uint.md), [UInt64](../sql-reference/data-types/int-uint.md) | `long` |
| `boolean`, `int`, `long`, `float`, `double` | [Float32](../sql-reference/data-types/float.md) | `float` | | `boolean`, `int`, `long`, `float`, `double` | [Float32](../sql-reference/data-types/float.md) | `float` |
| `boolean`, `int`, `long`, `float`, `double` | [Float64](../sql-reference/data-types/float.md) | `double` | | `boolean`, `int`, `long`, `float`, `double` | [Float64](../sql-reference/data-types/float.md) | `double` |
| `bytes`, `string`, `fixed`, `enum` | [String](../sql-reference/data-types/string.md) | `bytes` | | `bytes`, `string`, `fixed`, `enum` | [String](../sql-reference/data-types/string.md) | `bytes` or `string` \* |
| `bytes`, `string`, `fixed` | [FixedString(N)](../sql-reference/data-types/fixedstring.md) | `fixed(N)` | | `bytes`, `string`, `fixed` | [FixedString(N)](../sql-reference/data-types/fixedstring.md) | `fixed(N)` |
| `enum` | [Enum(8\|16)](../sql-reference/data-types/enum.md) | `enum` | | `enum` | [Enum(8\|16)](../sql-reference/data-types/enum.md) | `enum` |
| `array(T)` | [Array(T)](../sql-reference/data-types/array.md) | `array(T)` | | `array(T)` | [Array(T)](../sql-reference/data-types/array.md) | `array(T)` |
| `union(null, T)`, `union(T, null)` | [Nullable(T)](../sql-reference/data-types/date.md) | `union(null, T)` | | `union(null, T)`, `union(T, null)` | [Nullable(T)](../sql-reference/data-types/date.md) | `union(null, T)` |
| `null` | [Nullable(Nothing)](../sql-reference/data-types/special-data-types/nothing.md) | `null` | | `null` | [Nullable(Nothing)](../sql-reference/data-types/special-data-types/nothing.md) | `null` |
| `int (date)` \* | [Date](../sql-reference/data-types/date.md) | `int (date)` \* | | `int (date)` \** | [Date](../sql-reference/data-types/date.md) | `int (date)` \** |
| `long (timestamp-millis)` \* | [DateTime64(3)](../sql-reference/data-types/datetime.md) | `long (timestamp-millis)` \* | | `long (timestamp-millis)` \** | [DateTime64(3)](../sql-reference/data-types/datetime.md) | `long (timestamp-millis)` \* |
| `long (timestamp-micros)` \* | [DateTime64(6)](../sql-reference/data-types/datetime.md) | `long (timestamp-micros)` \* | | `long (timestamp-micros)` \** | [DateTime64(6)](../sql-reference/data-types/datetime.md) | `long (timestamp-micros)` \* |
\* [Avro logical types](https://avro.apache.org/docs/current/spec.html#Logical+Types) \* `bytes` is default, controlled by [output_format_avro_string_column_pattern](../operations/settings/settings.md#settings-output_format_avro_string_column_pattern)
\** [Avro logical types](https://avro.apache.org/docs/current/spec.html#Logical+Types)
Unsupported Avro data types: `record` (non-root), `map` Unsupported Avro data types: `record` (non-root), `map`
@ -1246,12 +1247,14 @@ The table below shows supported data types and how they match ClickHouse [data t
| `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `DOUBLE` | | `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `DOUBLE` |
| `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` | | `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` |
| `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` | | `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` |
| `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `STRING` | | `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` |
| — | [FixedString](../sql-reference/data-types/fixedstring.md) | `STRING` | | — | [FixedString](../sql-reference/data-types/fixedstring.md) | `BINARY` |
| `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` | | `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` |
| `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` | | `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](../sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](../sql-reference/data-types/map.md) | `MAP` |
Arrays can be nested and can have a value of the `Nullable` type as an argument. Arrays can be nested and can have a value of the `Nullable` type as an argument. `Tuple` and `Map` types also can be nested.
ClickHouse supports configurable precision of `Decimal` type. The `INSERT` query treats the Parquet `DECIMAL` type as the ClickHouse `Decimal128` type. ClickHouse supports configurable precision of `Decimal` type. The `INSERT` query treats the Parquet `DECIMAL` type as the ClickHouse `Decimal128` type.
@ -1299,13 +1302,17 @@ The table below shows supported data types and how they match ClickHouse [data t
| `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `FLOAT64` | | `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `FLOAT64` |
| `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` | | `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` |
| `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` | | `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` |
| `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `UTF8` | | `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` |
| `STRING`, `BINARY` | [FixedString](../sql-reference/data-types/fixedstring.md) | `UTF8` | | `STRING`, `BINARY` | [FixedString](../sql-reference/data-types/fixedstring.md) | `BINARY` |
| `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` | | `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` |
| `DECIMAL256` | [Decimal256](../sql-reference/data-types/decimal.md)| `DECIMAL256` | | `DECIMAL256` | [Decimal256](../sql-reference/data-types/decimal.md)| `DECIMAL256` |
| `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` | | `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](../sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](../sql-reference/data-types/map.md) | `MAP` |
Arrays can be nested and can have a value of the `Nullable` type as an argument. Arrays can be nested and can have a value of the `Nullable` type as an argument. `Tuple` and `Map` types also can be nested.
The `DICTIONARY` type is supported for `INSERT` queries, and for `SELECT` queries there is an [output_format_arrow_low_cardinality_as_dictionary](../operations/settings/settings.md#output-format-arrow-low-cardinality-as-dictionary) setting that allows to output [LowCardinality](../sql-reference/data-types/lowcardinality.md) type as a `DICTIONARY` type.
ClickHouse supports configurable precision of the `Decimal` type. The `INSERT` query treats the Arrow `DECIMAL` type as the ClickHouse `Decimal128` type. ClickHouse supports configurable precision of the `Decimal` type. The `INSERT` query treats the Arrow `DECIMAL` type as the ClickHouse `Decimal128` type.
@ -1358,8 +1365,10 @@ The table below shows supported data types and how they match ClickHouse [data t
| `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` | | `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` |
| `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` | | `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` |
| `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` | | `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](../sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](../sql-reference/data-types/map.md) | `MAP` |
Arrays can be nested and can have a value of the `Nullable` type as an argument. Arrays can be nested and can have a value of the `Nullable` type as an argument. `Tuple` and `Map` types also can be nested.
ClickHouse supports configurable precision of the `Decimal` type. The `INSERT` query treats the ORC `DECIMAL` type as the ClickHouse `Decimal128` type. ClickHouse supports configurable precision of the `Decimal` type. The `INSERT` query treats the ORC `DECIMAL` type as the ClickHouse `Decimal128` type.

1
docs/en/introduction/adopters.md
View File

@ -157,5 +157,6 @@ toc_title: Adopters
| <a href="https://signoz.io/" class="favicon">SigNoz</a> | Observability Platform | Main Product | — | — | [Source code](https://github.com/SigNoz/signoz) | | <a href="https://signoz.io/" class="favicon">SigNoz</a> | Observability Platform | Main Product | — | — | [Source code](https://github.com/SigNoz/signoz) |
| <a href="https://chelpipegroup.com/" class="favicon">ChelPipe Group</a> | Analytics | — | — | — | [Blog post, June 2021](https://vc.ru/trade/253172-tyazhelomu-proizvodstvu-user-friendly-sayt-internet-magazin-trub-dlya-chtpz) | | <a href="https://chelpipegroup.com/" class="favicon">ChelPipe Group</a> | Analytics | — | — | — | [Blog post, June 2021](https://vc.ru/trade/253172-tyazhelomu-proizvodstvu-user-friendly-sayt-internet-magazin-trub-dlya-chtpz) |
| <a href="https://zagravagames.com/en/" class="favicon">Zagrava Trading</a> | — | — | — | — | [Job offer, May 2021](https://twitter.com/datastackjobs/status/1394707267082063874) | | <a href="https://zagravagames.com/en/" class="favicon">Zagrava Trading</a> | — | — | — | — | [Job offer, May 2021](https://twitter.com/datastackjobs/status/1394707267082063874) |
| <a href="https://beeline.ru/" class="favicon">Beeline</a> | Telecom | Data Platform | — | — | [Blog post, July 2021](https://habr.com/en/company/beeline/blog/567508/) |
[Original article](https://clickhouse.tech/docs/en/introduction/adopters/) <!--hide--> [Original article](https://clickhouse.tech/docs/en/introduction/adopters/) <!--hide-->

114
docs/en/operations/clickhouse-keeper.md Normal file
View File

@ -0,0 +1,114 @@
---
toc_priority: 66
toc_title: ClickHouse Keeper
---
# [pre-production] clickhouse-keeper
ClickHouse server use [ZooKeeper](https://zookeeper.apache.org/) coordination system for data [replication](../engines/table-engines/mergetree-family/replication.md) and [distributed DDL](../sql-reference/distributed-ddl.md) queries execution. ClickHouse Keeper is an alternative coordination system compatible with ZooKeeper.
!!! warning "Warning"
This feature currently in pre-production stage. We test it in our CI and on small internal installations.
## Implementation details
ZooKeeper is one of the first well-known open-source coordination systems. It's implemented in Java, has quite a simple and powerful data model. ZooKeeper's coordination algorithm called ZAB (ZooKeeper Atomic Broadcast) doesn't provide linearizability guarantees for reads, because each ZooKeeper node serves reads locally. Unlike ZooKeeper `clickhouse-keeper` written in C++ and use [RAFT algorithm](https://raft.github.io/) [implementation](https://github.com/eBay/NuRaft). This algorithm allows to have linearizability for reads and writes, has several open-source implementations in different languages.
By default, `clickhouse-keeper` provides the same guarantees as ZooKeeper (linearizable writes, non-linearizable reads). It has a compatible client-server protocol, so any standard ZooKeeper client can be used to interact with `clickhouse-keeper`. Snapshots and logs have an incompatible format with ZooKeeper, but `clickhouse-keeper-converter` tool allows to convert ZooKeeper data to `clickhouse-keeper` snapshot. Interserver protocol in `clickhouse-keeper` also incompatible with ZooKeeper so mixed ZooKeeper/clickhouse-keeper cluster is impossible.
## Configuration
`clickhouse-keeper` can be used as a standalone replacement for ZooKeeper or as an internal part of the `clickhouse-server`, but in both cases configuration is almost the same `.xml` file. The main `clickhouse-keeper` configuration tag is `<keeper_server>`. Keeper configuration has the following parameters:
- `tcp_port` — the port for a client to connect (default for ZooKeeper is `2181`)
- `tcp_port_secure` — the secure port for a client to connect
- `server_id` — unique server id, each participant of the clickhouse-keeper cluster must have a unique number (1, 2, 3, and so on)
- `log_storage_path` — path to coordination logs, better to store logs on the non-busy device (same for ZooKeeper)
- `snapshot_storage_path` — path to coordination snapshots
Other common parameters are inherited from clickhouse-server config (`listen_host`, `logger` and so on).
Internal coordination settings are located in `<keeper_server>.<coordination_settings>` section:
- `operation_timeout_ms` — timeout for a single client operation
- `session_timeout_ms` — timeout for client session
- `dead_session_check_period_ms` — how often clickhouse-keeper check dead sessions and remove them
- `heart_beat_interval_ms` — how often a clickhouse-keeper leader will send heartbeats to followers
- `election_timeout_lower_bound_ms` — if follower didn't receive heartbeats from the leader in this interval, then it can initiate leader election
- `election_timeout_upper_bound_ms` — if follower didn't receive heartbeats from the leader in this interval, then it must initiate leader election
- `rotate_log_storage_interval` — how many logs to store in a single file
- `reserved_log_items` — how many coordination logs to store before compaction
- `snapshot_distance` — how often clickhouse-keeper will create new snapshots (in the number of logs)
- `snapshots_to_keep` — how many snapshots to keep
- `stale_log_gap` — the threshold when leader consider follower as stale and send snapshot to it instead of logs
- `force_sync` — call `fsync` on each write to coordination log
- `raft_logs_level` — text logging level about coordination (trace, debug, and so on)
- `shutdown_timeout` — wait to finish internal connections and shutdown
- `startup_timeout` — if the server doesn't connect to other quorum participants in the specified timeout it will terminate
Quorum configuration is located in `<keeper_server>.<raft_configuration>` section and contain servers description. The only parameter for the whole quorum is `secure`, which enables encrypted connection for communication between quorum participants. The main parameters for each `<server>` are:
- `id` — server_id in quorum
- `hostname` — hostname where this server placed
- `port` — port where this server listen for connections
Examples of configuration for quorum with three nodes can be found in [integration tests](https://github.com/ClickHouse/ClickHouse/tree/master/tests/integration) with `test_keeper_` prefix. Example configuration for server #1:
```xml
<keeper_server>
<tcp_port>2181</tcp_port>
<server_id>1</server_id>
<log_storage_path>/var/lib/clickhouse/coordination/log</log_storage_path>
<snapshot_storage_path>/var/lib/clickhouse/coordination/snapshots</snapshot_storage_path>
<coordination_settings>
<operation_timeout_ms>10000</operation_timeout_ms>
<session_timeout_ms>30000</session_timeout_ms>
<raft_logs_level>trace</raft_logs_level>
</coordination_settings>
<raft_configuration>
<server>
<id>1</id>
<hostname>zoo1</hostname>
<port>9444</port>
</server>
<server>
<id>2</id>
<hostname>zoo2</hostname>
<port>9444</port>
</server>
<server>
<id>3</id>
<hostname>zoo3</hostname>
<port>9444</port>
</server>
</raft_configuration>
</keeper_server>
```
## How to run
`clickhouse-keeper` is bundled into `clickhouse-server` package, just add configuration of `<keeper_server>` and start clickhouse-server as always. If you want to run standalone `clickhouse-keeper` you can start it in a similar way with:
```bash
clickhouse-keeper --config /etc/your_path_to_config/config.xml --daemon
```
## [experimental] Migration from ZooKeeper
Seamlessly migration from ZooKeeper to `clickhouse-keeper` is impossible you have to stop your ZooKeeper cluster, convert data and start `clickhouse-keeper`. `clickhouse-keeper-converter` tool allows to convert ZooKeeper logs and snapshots to `clickhouse-keeper` snapshot. It works only with ZooKeeper > 3.4. Steps for migration:
1. Stop all ZooKeeper nodes.
2. [optional, but recommended] Found ZooKeeper leader node, start and stop it again. It will force ZooKeeper to create consistent snapshot.
3. Run `clickhouse-keeper-converter` on leader, example
```bash
clickhouse-keeper-converter --zookeeper-logs-dir /var/lib/zookeeper/version-2 --zookeeper-snapshots-dir /var/lib/zookeeper/version-2 --output-dir /path/to/clickhouse/keeper/snapshots
```
4. Copy snapshot to `clickhouse-server` nodes with configured `keeper` or start `clickhouse-keeper` instead of ZooKeeper. Snapshot must persist only on leader node, leader will sync it automatically to other nodes.

19
docs/en/operations/configuration-files.md
View File

@ -22,6 +22,23 @@ Some settings specified in the main configuration file can be overridden in othe
The config can also define “substitutions”. If an element has the `incl` attribute, the corresponding substitution from the file will be used as the value. By default, the path to the file with substitutions is `/etc/metrika.xml`. This can be changed in the [include_from](../operations/server-configuration-parameters/settings.md#server_configuration_parameters-include_from) element in the server config. The substitution values are specified in `/yandex/substitution_name` elements in this file. If a substitution specified in `incl` does not exist, it is recorded in the log. To prevent ClickHouse from logging missing substitutions, specify the `optional="true"` attribute (for example, settings for [macros](../operations/server-configuration-parameters/settings.md)). The config can also define “substitutions”. If an element has the `incl` attribute, the corresponding substitution from the file will be used as the value. By default, the path to the file with substitutions is `/etc/metrika.xml`. This can be changed in the [include_from](../operations/server-configuration-parameters/settings.md#server_configuration_parameters-include_from) element in the server config. The substitution values are specified in `/yandex/substitution_name` elements in this file. If a substitution specified in `incl` does not exist, it is recorded in the log. To prevent ClickHouse from logging missing substitutions, specify the `optional="true"` attribute (for example, settings for [macros](../operations/server-configuration-parameters/settings.md)).
If you want to replace an entire element with a substitution use `include` as element name.
XML substitution example:
```xml
<yandex>
<!-- Appends XML subtree found at `/profiles-in-zookeeper` ZK path to `<profiles>` element. -->
<profiles from_zk="/profiles-in-zookeeper" />
<users>
<!-- Replaces `include` element with the subtree found at `/users-in-zookeeper` ZK path. -->
<include from_zk="/users-in-zookeeper" />
<include from_zk="/other-users-in-zookeeper" />
</users>
</yandex>
```
Substitutions can also be performed from ZooKeeper. To do this, specify the attribute `from_zk = "/path/to/node"`. The element value is replaced with the contents of the node at `/path/to/node` in ZooKeeper. You can also put an entire XML subtree on the ZooKeeper node and it will be fully inserted into the source element. Substitutions can also be performed from ZooKeeper. To do this, specify the attribute `from_zk = "/path/to/node"`. The element value is replaced with the contents of the node at `/path/to/node` in ZooKeeper. You can also put an entire XML subtree on the ZooKeeper node and it will be fully inserted into the source element.
## User Settings {#user-settings} ## User Settings {#user-settings}
@ -32,6 +49,8 @@ Users configuration can be splitted into separate files similar to `config.xml`
Directory name is defined as `users_config` setting without `.xml` postfix concatenated with `.d`. Directory name is defined as `users_config` setting without `.xml` postfix concatenated with `.d`.
Directory `users.d` is used by default, as `users_config` defaults to `users.xml`. Directory `users.d` is used by default, as `users_config` defaults to `users.xml`.
Note that configuration files are first merged taking into account [Override](#override) settings and includes are processed after that.
## XML example {#example} ## XML example {#example}
For example, you can have separate config file for each user like this: For example, you can have separate config file for each user like this:

12
docs/en/operations/settings/merge-tree-settings.md
View File

@ -278,4 +278,16 @@ Possible values:
Default value: `0`. Default value: `0`.
## check_sample_column_is_correct {#check_sample_column_is_correct}
Enables to check column for sampling or sampling expression is correct at table creation.
Possible values:
- true — Check column or sampling expression is correct at table creation.
- false — Do not check column or sampling expression is correct at table creation.
Default value: `true`.
By default, the ClickHouse server check column for sampling or sampling expression at table creation. If you already had tables with incorrect sampling expression, set value `false` to make ClickHouse server do not raise exception when ClickHouse server is starting.
[Original article](https://clickhouse.tech/docs/en/operations/settings/merge_tree_settings/) <!--hide--> [Original article](https://clickhouse.tech/docs/en/operations/settings/merge_tree_settings/) <!--hide-->

104
docs/en/operations/settings/settings.md
View File

@ -509,6 +509,23 @@ Possible values:
Default value: `ALL`. Default value: `ALL`.
## join_algorithm {#settings-join_algorithm}
Specifies [JOIN](../../sql-reference/statements/select/join.md) algorithm.
Possible values:
- `hash` — [Hash join algorithm](https://en.wikipedia.org/wiki/Hash_join) is used.
- `partial_merge` — [Sort-merge algorithm](https://en.wikipedia.org/wiki/Sort-merge_join) is used.
- `prefer_partial_merge` — ClickHouse always tries to use `merge` join if possible.
- `auto` — ClickHouse tries to change `hash` join to `merge` join on the fly to avoid out of memory.
Default value: `hash`.
When using `hash` algorithm the right part of `JOIN` is uploaded into RAM.
When using `partial_merge` algorithm ClickHouse sorts the data and dumps it to the disk. The `merge` algorithm in ClickHouse differs a bit from the classic realization. First ClickHouse sorts the right table by [join key](../../sql-reference/statements/select/join.md#select-join) in blocks and creates min-max index for sorted blocks. Then it sorts parts of left table by `join key` and joins them over right table. The min-max index is also used to skip unneeded right table blocks.
## join_any_take_last_row {#settings-join_any_take_last_row} ## join_any_take_last_row {#settings-join_any_take_last_row}
Changes behaviour of join operations with `ANY` strictness. Changes behaviour of join operations with `ANY` strictness.
@ -1213,7 +1230,15 @@ Default value: `3`.
## output_format_json_quote_64bit_integers {#session_settings-output_format_json_quote_64bit_integers} ## output_format_json_quote_64bit_integers {#session_settings-output_format_json_quote_64bit_integers}
If the value is true, integers appear in quotes when using JSON\* Int64 and UInt64 formats (for compatibility with most JavaScript implementations); otherwise, integers are output without the quotes. Controls quoting of 64-bit or bigger [integers](../../sql-reference/data-types/int-uint.md) (like `UInt64` or `Int128`) when they are output in a [JSON](../../interfaces/formats.md#json) format.
Such integers are enclosed in quotes by default. This behavior is compatible with most JavaScript implementations.
Possible values:
- 0 — Integers are output without quotes.
- 1 — Integers are enclosed in quotes.
Default value: 1.
## output_format_json_quote_denormals {#settings-output_format_json_quote_denormals} ## output_format_json_quote_denormals {#settings-output_format_json_quote_denormals}
@ -1730,7 +1755,7 @@ Default value: 0.
## optimize_functions_to_subcolumns {#optimize-functions-to-subcolumns} ## optimize_functions_to_subcolumns {#optimize-functions-to-subcolumns}
Enables or disables optimization by transforming some functions to reading subcolumns. This reduces the amount of data to read. Enables or disables optimization by transforming some functions to reading subcolumns. This reduces the amount of data to read.
These functions can be transformed: These functions can be transformed:
@ -1961,6 +1986,13 @@ Possible values: 32 (32 bytes) - 1073741824 (1 GiB)
Default value: 32768 (32 KiB) Default value: 32768 (32 KiB)
## output_format_avro_string_column_pattern {#output_format_avro_string_column_pattern}
Regexp of column names of type String to output as Avro `string` (default is `bytes`).
RE2 syntax is supported.
Type: string
## format_avro_schema_registry_url {#format_avro_schema_registry_url} ## format_avro_schema_registry_url {#format_avro_schema_registry_url}
Sets [Confluent Schema Registry](https://docs.confluent.io/current/schema-registry/index.html) URL to use with [AvroConfluent](../../interfaces/formats.md#data-format-avro-confluent) format. Sets [Confluent Schema Registry](https://docs.confluent.io/current/schema-registry/index.html) URL to use with [AvroConfluent](../../interfaces/formats.md#data-format-avro-confluent) format.
@ -1990,6 +2022,16 @@ Possible values:
Default value: 16. Default value: 16.
## merge_selecting_sleep_ms {#merge_selecting_sleep_ms}
Sleep time for merge selecting when no part selected, a lower setting will trigger selecting tasks in background_schedule_pool frequently which result in large amount of requests to zookeeper in large-scale clusters
Possible values:
- Any positive integer.
Default value: 5000
## parallel_distributed_insert_select {#parallel_distributed_insert_select} ## parallel_distributed_insert_select {#parallel_distributed_insert_select}
Enables parallel distributed `INSERT ... SELECT` query. Enables parallel distributed `INSERT ... SELECT` query.
@ -3123,6 +3165,53 @@ SELECT
FROM fuse_tbl FROM fuse_tbl
``` ```
## allow_experimental_database_replicated {#allow_experimental_database_replicated}
Enables to create databases with [Replicated](../../engines/database-engines/replicated.md) engine.
Possible values:
- 0 — Disabled.
- 1 — Enabled.
Default value: `0`.
## database_replicated_initial_query_timeout_sec {#database_replicated_initial_query_timeout_sec}
Sets how long initial DDL query should wait for Replicated database to precess previous DDL queue entries in seconds.
Possible values:
- Positive integer.
- 0 — Unlimited.
Default value: `300`.
## distributed_ddl_task_timeout {#distributed_ddl_task_timeout}
Sets timeout for DDL query responses from all hosts in cluster. If a DDL request has not been performed on all hosts, a response will contain a timeout error and a request will be executed in an async mode. Negative value means infinite.
Possible values:
- Positive integer.
- 0 — Async mode.
- Negative integer — infinite timeout.
Default value: `180`.
## distributed_ddl_output_mode {#distributed_ddl_output_mode}
Sets format of distributed DDL query result.
Possible values:
- `throw` — Returns result set with query execution status for all hosts where query is finished. If query has failed on some hosts, then it will rethrow the first exception. If query is not finished yet on some hosts and [distributed_ddl_task_timeout](#distributed_ddl_task_timeout) exceeded, then it throws `TIMEOUT_EXCEEDED` exception.
- `none` — Is similar to throw, but distributed DDL query returns no result set.
- `null_status_on_timeout` — Returns `NULL` as execution status in some rows of result set instead of throwing `TIMEOUT_EXCEEDED` if query is not finished on the corresponding hosts.
- `never_throw` — Do not throw `TIMEOUT_EXCEEDED` and do not rethrow exceptions if query has failed on some hosts.
Default value: `throw`.
## flatten_nested {#flatten-nested} ## flatten_nested {#flatten-nested}
Sets the data format of a [nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns. Sets the data format of a [nested](../../sql-reference/data-types/nested-data-structures/nested.md) columns.
@ -3202,3 +3291,14 @@ Default value: `1`.
**Usage** **Usage**
If the setting is set to `0`, the table function does not make Nullable columns and inserts default values instead of NULL. This is also applicable for NULL values inside arrays. If the setting is set to `0`, the table function does not make Nullable columns and inserts default values instead of NULL. This is also applicable for NULL values inside arrays.
## output_format_arrow_low_cardinality_as_dictionary {#output-format-arrow-low-cardinality-as-dictionary}
Allows to convert the [LowCardinality](../../sql-reference/data-types/lowcardinality.md) type to the `DICTIONARY` type of the [Arrow](../../interfaces/formats.md#data-format-arrow) format for `SELECT` queries.
Possible values:
- 0 — The `LowCardinality` type is not converted to the `DICTIONARY` type.
- 1 — The `LowCardinality` type is converted to the `DICTIONARY` type.
Default value: `0`.

5
docs/en/operations/system-tables/data_skipping_indices.md
View File

@ -8,12 +8,11 @@ Columns:
- `table` ([String](../../sql-reference/data-types/string.md)) — Table name. - `table` ([String](../../sql-reference/data-types/string.md)) — Table name.
- `name` ([String](../../sql-reference/data-types/string.md)) — Index name. - `name` ([String](../../sql-reference/data-types/string.md)) — Index name.
- `type` ([String](../../sql-reference/data-types/string.md)) — Index type. - `type` ([String](../../sql-reference/data-types/string.md)) — Index type.
- `expr` ([String](../../sql-reference/data-types/string.md)) — Expression used to calculate the index. - `expr` ([String](../../sql-reference/data-types/string.md)) — Expression for the index calculation.
- `granularity` ([UInt64](../../sql-reference/data-types/int-uint.md)) — Number of granules in the block. - `granularity` ([UInt64](../../sql-reference/data-types/int-uint.md)) — The number of granules in the block.
**Example** **Example**
```sql ```sql
SELECT * FROM system.data_skipping_indices LIMIT 2 FORMAT Vertical; SELECT * FROM system.data_skipping_indices LIMIT 2 FORMAT Vertical;
``` ```

2
docs/en/sql-reference/aggregate-functions/reference/median.md
View File

@ -34,7 +34,7 @@ Input table:
Query: Query:
``` sql ``` sql
SELECT medianDeterministic(val, 1) FROM t SELECT medianDeterministic(val, 1) FROM t;
``` ```
Result: Result:

3
docs/en/sql-reference/data-types/lowcardinality.md
View File

@ -47,6 +47,7 @@ Settings:
- [low_cardinality_use_single_dictionary_for_part](../../operations/settings/settings.md#low_cardinality_use_single_dictionary_for_part) - [low_cardinality_use_single_dictionary_for_part](../../operations/settings/settings.md#low_cardinality_use_single_dictionary_for_part)
- [low_cardinality_allow_in_native_format](../../operations/settings/settings.md#low_cardinality_allow_in_native_format) - [low_cardinality_allow_in_native_format](../../operations/settings/settings.md#low_cardinality_allow_in_native_format)
- [allow_suspicious_low_cardinality_types](../../operations/settings/settings.md#allow_suspicious_low_cardinality_types) - [allow_suspicious_low_cardinality_types](../../operations/settings/settings.md#allow_suspicious_low_cardinality_types)
- [output_format_arrow_low_cardinality_as_dictionary](../../operations/settings/settings.md#output-format-arrow-low-cardinality-as-dictionary)
Functions: Functions:
@ -57,5 +58,3 @@ Functions:
- [A Magical Mystery Tour of the LowCardinality Data Type](https://www.altinity.com/blog/2019/3/27/low-cardinality). - [A Magical Mystery Tour of the LowCardinality Data Type](https://www.altinity.com/blog/2019/3/27/low-cardinality).
- [Reducing ClickHouse Storage Cost with the Low Cardinality Type – Lessons from an Instana Engineer](https://www.instana.com/blog/reducing-clickhouse-storage-cost-with-the-low-cardinality-type-lessons-from-an-instana-engineer/). - [Reducing ClickHouse Storage Cost with the Low Cardinality Type – Lessons from an Instana Engineer](https://www.instana.com/blog/reducing-clickhouse-storage-cost-with-the-low-cardinality-type-lessons-from-an-instana-engineer/).
- [String Optimization (video presentation in Russian)](https://youtu.be/rqf-ILRgBdY?list=PL0Z2YDlm0b3iwXCpEFiOOYmwXzVmjJfEt). [Slides in English](https://github.com/yandex/clickhouse-presentations/raw/master/meetup19/string_optimization.pdf). - [String Optimization (video presentation in Russian)](https://youtu.be/rqf-ILRgBdY?list=PL0Z2YDlm0b3iwXCpEFiOOYmwXzVmjJfEt). [Slides in English](https://github.com/yandex/clickhouse-presentations/raw/master/meetup19/string_optimization.pdf).
[Original article](https://clickhouse.tech/docs/en/sql-reference/data-types/lowcardinality/) <!--hide-->

7
docs/en/sql-reference/data-types/map.md
View File

@ -9,11 +9,8 @@ toc_title: Map(key, value)
**Parameters** **Parameters**
- `key` — The key part of the pair. [String](../../sql-reference/data-types/string.md) or [Integer](../../sql-reference/data-types/int-uint.md). - `key` — The key part of the pair. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md), [LowCardinality](../../sql-reference/data-types/lowcardinality.md), or [FixedString](../../sql-reference/data-types/fixedstring.md).
- `value` — The value part of the pair. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md) or [Array](../../sql-reference/data-types/array.md). - `value` — The value part of the pair. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md), [Array](../../sql-reference/data-types/array.md), [LowCardinality](../../sql-reference/data-types/lowcardinality.md), or [FixedString](../../sql-reference/data-types/fixedstring.md).
!!! warning "Warning"
Currently `Map` data type is an experimental feature. To work with it you must set `allow_experimental_map_type = 1`.
To get the value from an `a Map('key', 'value')` column, use `a['key']` syntax. This lookup works now with a linear complexity. To get the value from an `a Map('key', 'value')` column, use `a['key']` syntax. This lookup works now with a linear complexity.

22
docs/en/sql-reference/functions/ext-dict-functions.md
View File

@ -12,7 +12,7 @@ For information on connecting and configuring external dictionaries, see [Extern
## dictGet, dictGetOrDefault, dictGetOrNull {#dictget} ## dictGet, dictGetOrDefault, dictGetOrNull {#dictget}
Retrieves values from an external dictionary. Retrieves values from an external dictionary.
``` sql ``` sql
dictGet('dict_name', attr_names, id_expr) dictGet('dict_name', attr_names, id_expr)
@ -24,7 +24,7 @@ dictGetOrNull('dict_name', attr_name, id_expr)
- `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal). - `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal).
- `attr_names` — Name of the column of the dictionary, [String literal](../../sql-reference/syntax.md#syntax-string-literal), or tuple of column names, [Tuple](../../sql-reference/data-types/tuple.md)([String literal](../../sql-reference/syntax.md#syntax-string-literal)). - `attr_names` — Name of the column of the dictionary, [String literal](../../sql-reference/syntax.md#syntax-string-literal), or tuple of column names, [Tuple](../../sql-reference/data-types/tuple.md)([String literal](../../sql-reference/syntax.md#syntax-string-literal)).
- `id_expr` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a [UInt64](../../sql-reference/data-types/int-uint.md) or [Tuple](../../sql-reference/data-types/tuple.md)-type value depending on the dictionary configuration. - `id_expr` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning dictionary key-type value or [Tuple](../../sql-reference/data-types/tuple.md)-type value depending on the dictionary configuration.
- `default_value_expr` — Values returned if the dictionary does not contain a row with the `id_expr` key. [Expression](../../sql-reference/syntax.md#syntax-expressions) or [Tuple](../../sql-reference/data-types/tuple.md)([Expression](../../sql-reference/syntax.md#syntax-expressions)), returning the value (or values) in the data types configured for the `attr_names` attribute. - `default_value_expr` — Values returned if the dictionary does not contain a row with the `id_expr` key. [Expression](../../sql-reference/syntax.md#syntax-expressions) or [Tuple](../../sql-reference/data-types/tuple.md)([Expression](../../sql-reference/syntax.md#syntax-expressions)), returning the value (or values) in the data types configured for the `attr_names` attribute.
**Returned value** **Returned value**
@ -138,7 +138,7 @@ Configure the external dictionary:
<name>c2</name> <name>c2</name>
<type>String</type> <type>String</type>
<null_value></null_value> <null_value></null_value>
</attribute> </attribute>
</structure> </structure>
<lifetime>0</lifetime> <lifetime>0</lifetime>
</dictionary> </dictionary>
@ -237,7 +237,7 @@ dictHas('dict_name', id_expr)
**Arguments** **Arguments**
- `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal). - `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal).
- `id_expr` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a [UInt64](../../sql-reference/data-types/int-uint.md) or [Tuple](../../sql-reference/data-types/tuple.md)-type value depending on the dictionary configuration. - `id_expr` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning dictionary key-type value or [Tuple](../../sql-reference/data-types/tuple.md)-type value depending on the dictionary configuration.
**Returned value** **Returned value**
@ -292,16 +292,16 @@ Type: `UInt8`.
Returns first-level children as an array of indexes. It is the inverse transformation for [dictGetHierarchy](#dictgethierarchy). Returns first-level children as an array of indexes. It is the inverse transformation for [dictGetHierarchy](#dictgethierarchy).
**Syntax** **Syntax**
``` sql ``` sql
dictGetChildren(dict_name, key) dictGetChildren(dict_name, key)
``` ```
**Arguments** **Arguments**
- `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal). - `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal).
- `key` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a [UInt64](../../sql-reference/data-types/int-uint.md)-type value. - `key` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a [UInt64](../../sql-reference/data-types/int-uint.md)-type value.
**Returned values** **Returned values**
@ -339,7 +339,7 @@ SELECT dictGetChildren('hierarchy_flat_dictionary', number) FROM system.numbers
## dictGetDescendant {#dictgetdescendant} ## dictGetDescendant {#dictgetdescendant}
Returns all descendants as if [dictGetChildren](#dictgetchildren) function was applied `level` times recursively. Returns all descendants as if [dictGetChildren](#dictgetchildren) function was applied `level` times recursively.
**Syntax** **Syntax**
@ -347,9 +347,9 @@ Returns all descendants as if [dictGetChildren](#dictgetchildren) function was a
dictGetDescendants(dict_name, key, level) dictGetDescendants(dict_name, key, level)
``` ```
**Arguments** **Arguments**
- `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal). - `dict_name` — Name of the dictionary. [String literal](../../sql-reference/syntax.md#syntax-string-literal).
- `key` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a [UInt64](../../sql-reference/data-types/int-uint.md)-type value. - `key` — Key value. [Expression](../../sql-reference/syntax.md#syntax-expressions) returning a [UInt64](../../sql-reference/data-types/int-uint.md)-type value.
- `level` — Hierarchy level. If `level = 0` returns all descendants to the end. [UInt8](../../sql-reference/data-types/int-uint.md). - `level` — Hierarchy level. If `level = 0` returns all descendants to the end. [UInt8](../../sql-reference/data-types/int-uint.md).

2
docs/en/sql-reference/functions/functions-for-nulls.md
View File

@ -211,7 +211,7 @@ SELECT nullIf(1, 2);
## assumeNotNull {#assumenotnull} ## assumeNotNull {#assumenotnull}
Results in a value of type [Nullable](../../sql-reference/data-types/nullable.md) for a non- `Nullable`, if the value is not `NULL`. Results in an equivalent non-`Nullable` value for a [Nullable](../../sql-reference/data-types/nullable.md) type. In case the original value is `NULL` the result is undetermined. See also `ifNull` and `coalesce` functions.
``` sql ``` sql
assumeNotNull(x) assumeNotNull(x)

35
docs/en/sql-reference/functions/geo/h3.md
View File

@ -195,6 +195,41 @@ Result:
└────────────────────┘ └────────────────────┘
``` ```
## h3ToGeo {#h3togeo}
Returns `(lon, lat)` that corresponds to the provided H3 index.
**Syntax**
``` sql
h3ToGeo(h3Index)
```
**Arguments**
- `h3Index` — H3 Index. Type: [UInt64](../../../sql-reference/data-types/int-uint.md).
**Returned values**
- `lon` — Longitude. Type: [Float64](../../../sql-reference/data-types/float.md).
- `lat` — Latitude. Type: [Float64](../../../sql-reference/data-types/float.md).
**Example**
Query:
``` sql
SELECT h3ToGeo(644325524701193974) coordinates;
```
Result:
``` text
┌─coordinates───────────────────────────┐
│ (37.79506616830252,55.71290243145668) │
└───────────────────────────────────────┘
```
## h3kRing {#h3kring} ## h3kRing {#h3kring}
Lists all the [H3](#h3index) hexagons in the raduis of `k` from the given hexagon in random order. Lists all the [H3](#h3index) hexagons in the raduis of `k` from the given hexagon in random order.

46
docs/en/sql-reference/functions/json-functions.md
View File

@ -306,3 +306,49 @@ Result:
└───────────────────────────────────────────────────────────────────────────────────────────────────────┘ └───────────────────────────────────────────────────────────────────────────────────────────────────────┘
``` ```
## toJSONString {#tojsonstring}
Serializes a value to its JSON representation. Various data types and nested structures are supported.
64-bit [integers](../../sql-reference/data-types/int-uint.md) or bigger (like `UInt64` or `Int128`) are enclosed in quotes by default. [output_format_json_quote_64bit_integers](../../operations/settings/settings.md#session_settings-output_format_json_quote_64bit_integers) controls this behavior.
Special values `NaN` and `inf` are replaced with `null`. Enable [output_format_json_quote_denormals](../../operations/settings/settings.md#settings-output_format_json_quote_denormals) setting to show them.
When serializing an [Enum](../../sql-reference/data-types/enum.md) value, the function outputs its name.
**Syntax**
``` sql
toJSONString(value)
```
**Arguments**
- `value` — Value to serialize. Value may be of any data type.
**Returned value**
- JSON representation of the value.
Type: [String](../../sql-reference/data-types/string.md).
**Example**
The first example shows serialization of a [Map](../../sql-reference/data-types/map.md).
The second example shows some special values wrapped into a [Tuple](../../sql-reference/data-types/tuple.md).
Query:
``` sql
SELECT toJSONString(map('key1', 1, 'key2', 2));
SELECT toJSONString(tuple(1.25, NULL, NaN, +inf, -inf, [])) SETTINGS output_format_json_quote_denormals = 1;
```
Result:
``` text
{"key1":1,"key2":2}
[1.25,null,"nan","inf","-inf",[]]
```
**See Also**
- [output_format_json_quote_64bit_integers](../../operations/settings/settings.md#session_settings-output_format_json_quote_64bit_integers)
- [output_format_json_quote_denormals](../../operations/settings/settings.md#settings-output_format_json_quote_denormals)

2
docs/en/sql-reference/functions/tuple-functions.md
View File

@ -87,6 +87,8 @@ Result:
└───────┴───────┘ └───────┴───────┘
``` ```
Note: the names are implementation specific and are subject to change. You should not assume specific names of the columns after application of the `untuple`.
Example of using an `EXCEPT` expression: Example of using an `EXCEPT` expression:
Query: Query:

30
docs/en/sql-reference/functions/type-conversion-functions.md
View File

@ -465,27 +465,29 @@ Result:
## CAST(x, T) {#type_conversion_function-cast} ## CAST(x, T) {#type_conversion_function-cast}
Converts input value `x` to the `T` data type. Unlike to `reinterpret` function, type conversion is performed in a natural way. Converts an input value to the specified data type. Unlike the [reinterpret](#type_conversion_function-reinterpret) function, `CAST` tries to present the same value using the new data type. If the conversion can not be done then an exception is raised.
Several syntax variants are supported.
The syntax `CAST(x AS t)` is also supported.
!!! note "Note"
If value `x` does not fit the bounds of type `T`, the function overflows. For example, `CAST(-1, 'UInt8')` returns `255`.
**Syntax** **Syntax**
``` sql ``` sql
CAST(x, T) CAST(x, T)
CAST(x AS t)
x::t
``` ```
**Arguments** **Arguments**
- `x` — Any type. - `x` — A value to convert. May be of any type.
- `T` — Destination type. [String](../../sql-reference/data-types/string.md). - `T` — The name of the target data type. [String](../../sql-reference/data-types/string.md).
- `t` — The target data type.
**Returned value** **Returned value**
- Destination type value. - Converted value.
!!! note "Note"
If the input value does not fit the bounds of the target type, the result overflows. For example, `CAST(-1, 'UInt8')` returns `255`.
**Examples** **Examples**
@ -494,16 +496,16 @@ Query:
```sql ```sql
SELECT SELECT
CAST(toInt8(-1), 'UInt8') AS cast_int_to_uint, CAST(toInt8(-1), 'UInt8') AS cast_int_to_uint,
CAST(toInt8(1), 'Float32') AS cast_int_to_float, CAST(1.5 AS Decimal(3,2)) AS cast_float_to_decimal,
CAST('1', 'UInt32') AS cast_string_to_int; '1'::Int32 AS cast_string_to_int;
``` ```
Result: Result:
``` ```
┌─cast_int_to_uint─┬─cast_int_to_float─┬─cast_string_to_int─┐ ┌─cast_int_to_uint─┬─cast_float_to_decimal─┬─cast_string_to_int─┐
│ 255 │ 1 │ 1 │ │ 255 │ 1.50 │ 1 │
└──────────────────┴───────────────────┴────────────────────┘ └──────────────────┴───────────────────────┴────────────────────┘
``` ```
Query: Query:

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

@ -189,7 +189,7 @@ CREATE TABLE codec_example
dt Date CODEC(ZSTD), dt Date CODEC(ZSTD),
ts DateTime CODEC(LZ4HC), ts DateTime CODEC(LZ4HC),
float_value Float32 CODEC(NONE), float_value Float32 CODEC(NONE),
double_value Float64 CODEC(LZ4HC(9)) double_value Float64 CODEC(LZ4HC(9)),
value Float32 CODEC(Delta, ZSTD) value Float32 CODEC(Delta, ZSTD)
) )
ENGINE = <Engine> ENGINE = <Engine>

61
docs/en/sql-reference/statements/select/join.md
View File

@ -36,14 +36,23 @@ Additional join types available in ClickHouse:
- `LEFT ANY JOIN`, `RIGHT ANY JOIN` and `INNER ANY JOIN`, partially (for opposite side of `LEFT` and `RIGHT`) or completely (for `INNER` and `FULL`) disables the cartesian product for standard `JOIN` types. - `LEFT ANY JOIN`, `RIGHT ANY JOIN` and `INNER ANY JOIN`, partially (for opposite side of `LEFT` and `RIGHT`) or completely (for `INNER` and `FULL`) disables the cartesian product for standard `JOIN` types.
- `ASOF JOIN` and `LEFT ASOF JOIN`, joining sequences with a non-exact match. `ASOF JOIN` usage is described below. - `ASOF JOIN` and `LEFT ASOF JOIN`, joining sequences with a non-exact match. `ASOF JOIN` usage is described below.
## Setting {#join-settings} ## Settings {#join-settings}
!!! note "Note" The default join type can be overriden using [join_default_strictness](../../../operations/settings/settings.md#settings-join_default_strictness) setting.
The default join type can be overriden using [join_default_strictness](../../../operations/settings/settings.md#settings-join_default_strictness) setting.
Also the behavior of ClickHouse server for `ANY JOIN` operations depends on the [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys) setting. The behavior of ClickHouse server for `ANY JOIN` operations depends on the [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys) setting.
### ASOF JOIN Usage {#asof-join-usage} **See also**
- [join_algorithm](../../../operations/settings/settings.md#settings-join_algorithm)
- [join_any_take_last_row](../../../operations/settings/settings.md#settings-join_any_take_last_row)
- [join_use_nulls](../../../operations/settings/settings.md#join_use_nulls)
- [partial_merge_join_optimizations](../../../operations/settings/settings.md#partial_merge_join_optimizations)
- [partial_merge_join_rows_in_right_blocks](../../../operations/settings/settings.md#partial_merge_join_rows_in_right_blocks)
- [join_on_disk_max_files_to_merge](../../../operations/settings/settings.md#join_on_disk_max_files_to_merge)
- [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys)
## ASOF JOIN Usage {#asof-join-usage}
`ASOF JOIN` is useful when you need to join records that have no exact match. `ASOF JOIN` is useful when you need to join records that have no exact match.
@ -93,7 +102,7 @@ For example, consider the following tables:
!!! note "Note" !!! note "Note"
`ASOF` join is **not** supported in the [Join](../../../engines/table-engines/special/join.md) table engine. `ASOF` join is **not** supported in the [Join](../../../engines/table-engines/special/join.md) table engine.
## Distributed Join {#global-join} ## Distributed JOIN {#global-join}
There are two ways to execute join involving distributed tables: There are two ways to execute join involving distributed tables:
@ -102,6 +111,42 @@ There are two ways to execute join involving distributed tables:
Be careful when using `GLOBAL`. For more information, see the [Distributed subqueries](../../../sql-reference/operators/in.md#select-distributed-subqueries) section. Be careful when using `GLOBAL`. For more information, see the [Distributed subqueries](../../../sql-reference/operators/in.md#select-distributed-subqueries) section.
## Implicit Type Conversion {#implicit-type-conversion}
`INNER JOIN`, `LEFT JOIN`, `RIGHT JOIN`, and `FULL JOIN` queries support the implicit type conversion for "join keys". However the query can not be executed, if join keys from the left and the right tables cannot be converted to a single type (for example, there is no data type that can hold all values from both `UInt64` and `Int64`, or `String` and `Int32`).
**Example**
Consider the table `t_1`:
```text
┌─a─┬─b─┬─toTypeName(a)─┬─toTypeName(b)─┐
│ 1 │ 1 │ UInt16 │ UInt8 │
│ 2 │ 2 │ UInt16 │ UInt8 │
└───┴───┴───────────────┴───────────────┘
```
and the table `t_2`:
```text
┌──a─┬────b─┬─toTypeName(a)─┬─toTypeName(b)───┐
│ -1 │ 1 │ Int16 │ Nullable(Int64) │
│ 1 │ -1 │ Int16 │ Nullable(Int64) │
│ 1 │ 1 │ Int16 │ Nullable(Int64) │
└────┴──────┴───────────────┴─────────────────┘
```
The query
```sql
SELECT a, b, toTypeName(a), toTypeName(b) FROM t_1 FULL JOIN t_2 USING (a, b);
```
returns the set:
```text
┌──a─┬────b─┬─toTypeName(a)─┬─toTypeName(b)───┐
│ 1 │ 1 │ Int32 │ Nullable(Int64) │
│ 2 │ 2 │ Int32 │ Nullable(Int64) │
│ -1 │ 1 │ Int32 │ Nullable(Int64) │
│ 1 │ -1 │ Int32 │ Nullable(Int64) │
└────┴──────┴───────────────┴─────────────────┘
```
## Usage Recommendations {#usage-recommendations} ## Usage Recommendations {#usage-recommendations}
### Processing of Empty or NULL Cells {#processing-of-empty-or-null-cells} ### Processing of Empty or NULL Cells {#processing-of-empty-or-null-cells}
@ -139,9 +184,9 @@ If you need a `JOIN` for joining with dimension tables (these are relatively sma
### Memory Limitations {#memory-limitations} ### Memory Limitations {#memory-limitations}
By default, ClickHouse uses the [hash join](https://en.wikipedia.org/wiki/Hash_join) algorithm. ClickHouse takes the `<right_table>` and creates a hash table for it in RAM. After some threshold of memory consumption, ClickHouse falls back to merge join algorithm. By default, ClickHouse uses the [hash join](https://en.wikipedia.org/wiki/Hash_join) algorithm. ClickHouse takes the right_table and creates a hash table for it in RAM. If `join_algorithm = 'auto'` is enabled, then after some threshold of memory consumption, ClickHouse falls back to [merge](https://en.wikipedia.org/wiki/Sort-merge_join) join algorithm. For `JOIN` algorithms description see the [join_algorithm](../../../operations/settings/settings.md#settings-join_algorithm) setting.
If you need to restrict join operation memory consumption use the following settings: If you need to restrict `JOIN` operation memory consumption use the following settings:
- [max_rows_in_join](../../../operations/settings/query-complexity.md#settings-max_rows_in_join) — Limits number of rows in the hash table. - [max_rows_in_join](../../../operations/settings/query-complexity.md#settings-max_rows_in_join) — Limits number of rows in the hash table.
- [max_bytes_in_join](../../../operations/settings/query-complexity.md#settings-max_bytes_in_join) — Limits size of the hash table. - [max_bytes_in_join](../../../operations/settings/query-complexity.md#settings-max_bytes_in_join) — Limits size of the hash table.

10
docs/en/whats-new/security-changelog.md
View File

@ -3,6 +3,16 @@ toc_priority: 76
toc_title: Security Changelog toc_title: Security Changelog
--- ---
## Fixed in ClickHouse 21.4.3.21, 2021-04-12 {#fixed-in-clickhouse-release-21-4-3-21-2021-04-12}
### CVE-2021-25263 {#cve-2021-25263}
An attacker that has CREATE DICTIONARY privilege, can read arbitary file outside permitted directory.
Fix has been pushed to versions 20.8.18.32-lts, 21.1.9.41-stable, 21.2.9.41-stable, 21.3.6.55-lts, 21.4.3.21-stable and later.
Credits: [Vyacheslav Egoshin](https://twitter.com/vegoshin)
## Fixed in ClickHouse Release 19.14.3.3, 2019-09-10 {#fixed-in-clickhouse-release-19-14-3-3-2019-09-10} ## Fixed in ClickHouse Release 19.14.3.3, 2019-09-10 {#fixed-in-clickhouse-release-19-14-3-3-2019-09-10}
### CVE-2019-15024 {#cve-2019-15024} ### CVE-2019-15024 {#cve-2019-15024}

1
docs/ru/development/build-osx.md
View File

@ -1 +0,0 @@
../../en/development/build-osx.md

125
docs/ru/development/build-osx.md Normal file
View File

@ -0,0 +1,125 @@
---
toc_priority: 65
toc_title: Сборка на Mac OS X
---
# Как собрать ClickHouse на Mac OS X {#how-to-build-clickhouse-on-mac-os-x}
Сборка должна запускаться с x86_64 (Intel) на macOS версии 10.15 (Catalina) и выше в последней версии компилятора Xcode's native AppleClang, Homebrew's vanilla Clang или в GCC-компиляторах.
## Установка Homebrew {#install-homebrew}
``` bash
$ /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
```
## Установка Xcode и инструментов командной строки {#install-xcode-and-command-line-tools}
1. Установите из App Store последнюю версию [Xcode](https://apps.apple.com/am/app/xcode/id497799835?mt=12).
2. Запустите ее, чтобы принять лицензионное соглашение. Необходимые компоненты установятся автоматически.
3. Затем убедитесь, что в системе выбрана последняя версия инструментов командной строки:
``` bash
$ sudo rm -rf /Library/Developer/CommandLineTools
$ sudo xcode-select --install
```
4. Перезагрузитесь.
## Установка компиляторов, инструментов и библиотек {#install-required-compilers-tools-and-libraries}
``` bash
$ brew update
$ brew install cmake ninja libtool gettext llvm gcc
```
## Просмотр исходников ClickHouse {#checkout-clickhouse-sources}
``` bash
$ git clone --recursive git@github.com:ClickHouse/ClickHouse.git # or https://github.com/ClickHouse/ClickHouse.git
```
## Сборка ClickHouse {#build-clickhouse}
Чтобы запустить сборку в компиляторе Xcode's native AppleClang:
``` bash
$ cd ClickHouse
$ rm -rf build
$ mkdir build
$ cd build
$ cmake -DCMAKE_BUILD_TYPE=RelWithDebInfo -DENABLE_JEMALLOC=OFF ..
$ cmake --build . --config RelWithDebInfo
$ cd ..
```
Чтобы запустить сборку в компиляторе Homebrew's vanilla Clang:
``` bash
$ cd ClickHouse
$ rm -rf build
$ mkdir build
$ cd build
$ cmake -DCMAKE_C_COMPILER=$(brew --prefix llvm)/bin/clang -DCMAKE_CXX_COMPILER==$(brew --prefix llvm)/bin/clang++ -DCMAKE_BUILD_TYPE=RelWithDebInfo -DENABLE_JEMALLOC=OFF ..
$ cmake -DCMAKE_C_COMPILER=$(brew --prefix llvm)/bin/clang -DCMAKE_CXX_COMPILER=$(brew --prefix llvm)/bin/clang++ -DCMAKE_BUILD_TYPE=RelWithDebInfo -DENABLE_JEMALLOC=OFF ..
$ cmake --build . --config RelWithDebInfo
$ cd ..
```
Чтобы собрать с помощью компилятора Homebrew's vanilla GCC:
``` bash
$ cd ClickHouse
$ rm -rf build
$ mkdir build
$ cd build
$ cmake -DCMAKE_C_COMPILER=$(brew --prefix gcc)/bin/gcc-10 -DCMAKE_CXX_COMPILER=$(brew --prefix gcc)/bin/g++-10 -DCMAKE_BUILD_TYPE=RelWithDebInfo -DENABLE_JEMALLOC=OFF ..
$ cmake --build . --config RelWithDebInfo
$ cd ..
```
## Предупреждения {#caveats}
Если будете запускать `clickhouse-server`, убедитесь, что увеличили системную переменную `maxfiles`.
!!! info "Note"
Вам понадобится команда `sudo`.
1. Создайте файл `/Library/LaunchDaemons/limit.maxfiles.plist` и поместите в него следующее:
``` xml
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN"
"http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
<key>Label</key>
<string>limit.maxfiles</string>
<key>ProgramArguments</key>
<array>
<string>launchctl</string>
<string>limit</string>
<string>maxfiles</string>
<string>524288</string>
<string>524288</string>
</array>
<key>RunAtLoad</key>
<true/>
<key>ServiceIPC</key>
<false/>
</dict>
</plist>
```
2. Выполните команду:
``` bash
$ sudo chown root:wheel /Library/LaunchDaemons/limit.maxfiles.plist
```
3. Перезагрузитесь.
4. Чтобы проверить, как это работает, выполните команду `ulimit -n`.
[Original article](https://clickhouse.tech/docs/en/development/build_osx/) <!--hide-->

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

@ -128,7 +128,7 @@ Ninja - система запуска сборочных задач.
/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)" /usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"
brew install cmake ninja brew install cmake ninja
Проверьте версию CMake: `cmake --version`. Если версия меньше 3.3, то установите новую версию с сайта https://cmake.org/download/ Проверьте версию CMake: `cmake --version`. Если версия меньше 3.12, то установите новую версию с сайта https://cmake.org/download/
## Необязательные внешние библиотеки {#neobiazatelnye-vneshnie-biblioteki} ## Необязательные внешние библиотеки {#neobiazatelnye-vneshnie-biblioteki}

2
docs/ru/engines/database-engines/index.md
View File

@ -20,3 +20,5 @@ toc_title: "Введение"
- [PostgreSQL](../../engines/database-engines/postgresql.md) - [PostgreSQL](../../engines/database-engines/postgresql.md)
- [Replicated](../../engines/database-engines/replicated.md)

6
docs/ru/engines/database-engines/materialize-mysql.md
View File

@ -1,3 +1,4 @@
--- ---
toc_priority: 29 toc_priority: 29
toc_title: MaterializeMySQL toc_title: MaterializeMySQL
@ -49,6 +50,7 @@ ENGINE = MaterializeMySQL('host:port', ['database' | database], 'user', 'passwor
| DATE, NEWDATE | [Date](../../sql-reference/data-types/date.md) | | DATE, NEWDATE | [Date](../../sql-reference/data-types/date.md) |
| DATETIME, TIMESTAMP | [DateTime](../../sql-reference/data-types/datetime.md) | | DATETIME, TIMESTAMP | [DateTime](../../sql-reference/data-types/datetime.md) |
| DATETIME2, TIMESTAMP2 | [DateTime64](../../sql-reference/data-types/datetime64.md) | | DATETIME2, TIMESTAMP2 | [DateTime64](../../sql-reference/data-types/datetime64.md) |
| ENUM | [Enum](../../sql-reference/data-types/enum.md) |
| STRING | [String](../../sql-reference/data-types/string.md) | | STRING | [String](../../sql-reference/data-types/string.md) |
| VARCHAR, VAR_STRING | [String](../../sql-reference/data-types/string.md) | | VARCHAR, VAR_STRING | [String](../../sql-reference/data-types/string.md) |
| BLOB | [String](../../sql-reference/data-types/string.md) | | BLOB | [String](../../sql-reference/data-types/string.md) |
@ -79,7 +81,9 @@ DDL-запросы в MySQL конвертируются в соответств
- Если в запросе `SELECT` напрямую не указан столбец `_version`, то используется модификатор [FINAL](../../sql-reference/statements/select/from.md#select-from-final). Таким образом, выбираются только строки с `MAX(_version)`. - Если в запросе `SELECT` напрямую не указан столбец `_version`, то используется модификатор [FINAL](../../sql-reference/statements/select/from.md#select-from-final). Таким образом, выбираются только строки с `MAX(_version)`.
- Если в запросе `SELECT` напрямую не указан столбец `_sign`, то по умолчанию используется `WHERE _sign=1`. Таким образом, удаленные строки не включаются в результирующий набор. - Если в запросе `SELECT` напрямую не указан столбец `_sign`, то по умолчанию используется `WHERE _sign=1`. Таким образом, удаленные строки не включаются в результирующий набор.
- Результат включает комментарии к столбцам, если они существуют в таблицах базы данных MySQL.
### Конвертация индексов {#index-conversion} ### Конвертация индексов {#index-conversion}

119
docs/ru/engines/database-engines/replicated.md Normal file
View File

@ -0,0 +1,119 @@
# [экспериментальный] Replicated {#replicated}
Движок основан на движке [Atomic](../../engines/database-engines/atomic.md). Он поддерживает репликацию метаданных через журнал DDL, записываемый в ZooKeeper и выполняемый на всех репликах для данной базы данных.
На одном сервере ClickHouse может одновременно работать и обновляться несколько реплицированных баз данных. Но не может существовать нескольких реплик одной и той же реплицированной базы данных.
## Создание базы данных {#creating-a-database}
``` sql
CREATE DATABASE testdb ENGINE = Replicated('zoo_path', 'shard_name', 'replica_name') [SETTINGS ...]
```
**Параметры движка**
- `zoo_path` — путь в ZooKeeper. Один и тот же путь ZooKeeper соответствует одной и той же базе данных.
- `shard_name` — Имя шарда. Реплики базы данных группируются в шарды по имени.
- `replica_name` — Имя реплики. Имена реплик должны быть разными для всех реплик одного и того же шарда.
!!! note "Предупреждение"
Для таблиц [ReplicatedMergeTree](../table-engines/mergetree-family/replication.md#table_engines-replication) если аргументы не заданы, то используются аргументы по умолчанию: `/clickhouse/tables/{uuid}/{shard}` и `{replica}`. Они могут быть изменены в серверных настройках: [default_replica_path](../../operations/server-configuration-parameters/settings.md#default_replica_path) и [default_replica_name](../../operations/server-configuration-parameters/settings.md#default_replica_name). Макрос `{uuid}` раскрывается в `UUID` таблицы, `{shard}` и `{replica}` — в значения из конфига сервера. В будущем появится возможность использовать значения `shard_name` и `replica_name` аргументов движка базы данных `Replicated`.
## Особенности и рекомендации {#specifics-and-recommendations}
DDL-запросы с базой данных `Replicated` работают похожим образом на [ON CLUSTER](../../sql-reference/distributed-ddl.md) запросы, но с небольшими отличиями.
Сначала DDL-запрос пытается выполниться на инициаторе (том хосте, который изначально получил запрос от пользователя). Если запрос не выполнился, то пользователь сразу получает ошибку, другие хосты не пытаются его выполнить. Если запрос успешно выполнился на инициаторе, то все остальные хосты будут автоматически делать попытки выполнить его.
Инициатор попытается дождаться выполнения запроса на других хостах (не дольше [distributed_ddl_task_timeout](../../operations/settings/settings.md#distributed_ddl_task_timeout)) и вернёт таблицу со статусами выполнения запроса на каждом хосте.
Поведение в случае ошибок регулируется настройкой [distributed_ddl_output_mode](../../operations/settings/settings.md#distributed_ddl_output_mode), для `Replicated` лучше выставлять её в `null_status_on_timeout` — т.е. если какие-то хосты не успели выполнить запрос за [distributed_ddl_task_timeout](../../operations/settings/settings.md#distributed_ddl_task_timeout), то вместо исключения для них будет показан статус `NULL` в таблице.
В системной таблице [system.clusters](../../operations/system-tables/clusters.md) есть кластер с именем, как у реплицируемой базы, который состоит из всех реплик базы. Этот кластер обновляется автоматически при создании/удалении реплик, и его можно использовать для [Distributed](../../engines/table-engines/special/distributed.md#distributed) таблиц.
При создании новой реплики базы, эта реплика сама создаёт таблицы. Если реплика долго была недоступна и отстала от лога репликации — она сверяет свои локальные метаданные с актуальными метаданными в ZooKeeper, перекладывает лишние таблицы с данными в отдельную нереплицируемую базу (чтобы случайно не удалить что-нибудь лишнее), создаёт недостающие таблицы, обновляет имена таблиц, если были переименования. Данные реплицируются на уровне `ReplicatedMergeTree`, т.е. если таблица не реплицируемая, то данные реплицироваться не будут (база отвечает только за метаданные).
## Примеры использования {#usage-example}
Создадим реплицируемую базу на трех хостах:
``` sql
node1 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','shard1','replica1');
node2 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','shard1','other_replica');
node3 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','other_shard','{replica}');
```
Выполним DDL-запрос на одном из хостов:
``` sql
CREATE TABLE r.rmt (n UInt64) ENGINE=ReplicatedMergeTree ORDER BY n;
```
Запрос выполнится на всех остальных хостах:
``` text
┌─────hosts────────────┬──status─┬─error─┬─num_hosts_remaining─┬─num_hosts_active─┐
│ shard1|replica1 │ 0 │ │ 2 │ 0 │
│ shard1|other_replica │ 0 │ │ 1 │ 0 │
│ other_shard|r1 │ 0 │ │ 0 │ 0 │
└──────────────────────┴─────────┴───────┴─────────────────────┴──────────────────┘
```
Кластер в системной таблице `system.clusters`:
``` sql
SELECT cluster, shard_num, replica_num, host_name, host_address, port, is_local
FROM system.clusters WHERE cluster='r';
```
``` text
┌─cluster─┬─shard_num─┬─replica_num─┬─host_name─┬─host_address─┬─port─┬─is_local─┐
│ r │ 1 │ 1 │ node3 │ 127.0.0.1 │ 9002 │ 0 │
│ r │ 2 │ 1 │ node2 │ 127.0.0.1 │ 9001 │ 0 │
│ r │ 2 │ 2 │ node1 │ 127.0.0.1 │ 9000 │ 1 │
└─────────┴───────────┴─────────────┴───────────┴──────────────┴──────┴──────────┘
```
Создадим распределенную таблицу и вставим в нее данные:
``` sql
node2 :) CREATE TABLE r.d (n UInt64) ENGINE=Distributed('r','r','rmt', n % 2);
node3 :) INSERT INTO r SELECT * FROM numbers(10);
node1 :) SELECT materialize(hostName()) AS host, groupArray(n) FROM r.d GROUP BY host;
```
``` text
┌─hosts─┬─groupArray(n)─┐
│ node1 │ [1,3,5,7,9] │
│ node2 │ [0,2,4,6,8] │
└───────┴───────────────┘
```
Добавление реплики:
``` sql
node4 :) CREATE DATABASE r ENGINE=Replicated('some/path/r','other_shard','r2');
```
Новая реплика автоматически создаст все таблицы, которые есть в базе, а старые реплики перезагрузят из ZooKeeper-а конфигурацию кластера:
``` text
┌─cluster─┬─shard_num─┬─replica_num─┬─host_name─┬─host_address─┬─port─┬─is_local─┐
│ r │ 1 │ 1 │ node3 │ 127.0.0.1 │ 9002 │ 0 │
│ r │ 1 │ 2 │ node4 │ 127.0.0.1 │ 9003 │ 0 │
│ r │ 2 │ 1 │ node2 │ 127.0.0.1 │ 9001 │ 0 │
│ r │ 2 │ 2 │ node1 │ 127.0.0.1 │ 9000 │ 1 │
└─────────┴───────────┴─────────────┴───────────┴──────────────┴──────┴──────────┘
```
Распределенная таблица также получит данные от нового хоста:
```sql
node2 :) SELECT materialize(hostName()) AS host, groupArray(n) FROM r.d GROUP BY host;
```
```text
┌─hosts─┬─groupArray(n)─┐
│ node2 │ [1,3,5,7,9] │
│ node4 │ [0,2,4,6,8] │
└───────┴───────────────┘
```

6
docs/ru/getting-started/install.md
View File

@ -100,9 +100,9 @@ sudo ./clickhouse install
Для других операционных систем и архитектуры AArch64 сборки ClickHouse предоставляются в виде кросс-компилированного бинарного файла из последнего коммита ветки `master` (с задержкой в несколько часов). Для других операционных систем и архитектуры AArch64 сборки ClickHouse предоставляются в виде кросс-компилированного бинарного файла из последнего коммита ветки `master` (с задержкой в несколько часов).
- [macOS](https://builds.clickhouse.tech/master/macos/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/macos/clickhouse' && chmod a+x ./clickhouse` - [macOS](https://builds.clickhouse.tech/master/macos/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/macos/clickhouse' && chmod a+x ./clickhouse`
- [AArch64](https://builds.clickhouse.tech/master/aarch64/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/aarch64/clickhouse' && chmod a+x ./clickhouse` - [FreeBSD](https://builds.clickhouse.tech/master/freebsd/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/freebsd/clickhouse' && chmod a+x ./clickhouse`
- [FreeBSD](https://builds.clickhouse.tech/master/freebsd/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/freebsd/clickhouse' && chmod a+x ./clickhouse` - [AArch64](https://builds.clickhouse.tech/master/aarch64/clickhouse) — `curl -O 'https://builds.clickhouse.tech/master/aarch64/clickhouse' && chmod a+x ./clickhouse`
После скачивания можно воспользоваться `clickhouse client` для подключения к серверу или `clickhouse local` для обработки локальных данных. После скачивания можно воспользоваться `clickhouse client` для подключения к серверу или `clickhouse local` для обработки локальных данных.

23
docs/ru/interfaces/formats.md
View File

@ -1165,12 +1165,14 @@ SELECT * FROM topic1_stream;
| `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `DOUBLE` | | `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `DOUBLE` |
| `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` | | `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` |
| `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` | | `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` |
| `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `STRING` | | `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` |
| — | [FixedString](../sql-reference/data-types/fixedstring.md) | `STRING` | | — | [FixedString](../sql-reference/data-types/fixedstring.md) | `BINARY` |
| `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` | | `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` |
| `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` | | `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](../sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](../sql-reference/data-types/map.md) | `MAP` |
Массивы могут быть вложенными и иметь в качестве аргумента значение типа `Nullable`. Массивы могут быть вложенными и иметь в качестве аргумента значение типа `Nullable`. Типы `Tuple` и `Map` также могут быть вложенными.
ClickHouse поддерживает настраиваемую точность для формата `Decimal`. При выполнении запроса `INSERT` ClickHouse обрабатывает тип данных Parquet `DECIMAL` как `Decimal128`. ClickHouse поддерживает настраиваемую точность для формата `Decimal`. При выполнении запроса `INSERT` ClickHouse обрабатывает тип данных Parquet `DECIMAL` как `Decimal128`.
@ -1218,12 +1220,17 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Parquet" > {some_
| `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `FLOAT64` | | `DOUBLE` | [Float64](../sql-reference/data-types/float.md) | `FLOAT64` |
| `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` | | `DATE32` | [Date](../sql-reference/data-types/date.md) | `UINT16` |
| `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` | | `DATE64`, `TIMESTAMP` | [DateTime](../sql-reference/data-types/datetime.md) | `UINT32` |
| `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `UTF8` | | `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` |
| `STRING`, `BINARY` | [FixedString](../sql-reference/data-types/fixedstring.md) | `UTF8` | | `STRING`, `BINARY` | [FixedString](../sql-reference/data-types/fixedstring.md) | `BINARY` |
| `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` | | `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` |
| `DECIMAL256` | [Decimal256](../sql-reference/data-types/decimal.md)| `DECIMAL256` |
| `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` | | `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](../sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](../sql-reference/data-types/map.md) | `MAP` |
Массивы могут быть вложенными и иметь в качестве аргумента значение типа `Nullable`. Массивы могут быть вложенными и иметь в качестве аргумента значение типа `Nullable`. Типы `Tuple` и `Map` также могут быть вложенными.
Тип `DICTIONARY` поддерживается для запросов `INSERT`. Для запросов `SELECT` есть настройка [output_format_arrow_low_cardinality_as_dictionary](../operations/settings/settings.md#output-format-arrow-low-cardinality-as-dictionary), которая позволяет выводить тип [LowCardinality](../sql-reference/data-types/lowcardinality.md) как `DICTIONARY`.
ClickHouse поддерживает настраиваемую точность для формата `Decimal`. При выполнении запроса `INSERT` ClickHouse обрабатывает тип данных Arrow `DECIMAL` как `Decimal128`. ClickHouse поддерживает настраиваемую точность для формата `Decimal`. При выполнении запроса `INSERT` ClickHouse обрабатывает тип данных Arrow `DECIMAL` как `Decimal128`.
@ -1276,8 +1283,10 @@ $ clickhouse-client --query="SELECT * FROM {some_table} FORMAT Arrow" > {filenam
| `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` | | `STRING`, `BINARY` | [String](../sql-reference/data-types/string.md) | `BINARY` |
| `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` | | `DECIMAL` | [Decimal](../sql-reference/data-types/decimal.md) | `DECIMAL` |
| `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` | | `LIST` | [Array](../sql-reference/data-types/array.md) | `LIST` |
| `STRUCT` | [Tuple](../sql-reference/data-types/tuple.md) | `STRUCT` |
| `MAP` | [Map](../sql-reference/data-types/map.md) | `MAP` |
Массивы могут быть вложенными и иметь в качестве аргумента значение типа `Nullable`. Массивы могут быть вложенными и иметь в качестве аргумента значение типа `Nullable`. Типы `Tuple` и `Map` также могут быть вложенными.
ClickHouse поддерживает настраиваемую точность для формата `Decimal`. При выполнении запроса `INSERT` ClickHouse обрабатывает тип данных ORC `DECIMAL` как `Decimal128`. ClickHouse поддерживает настраиваемую точность для формата `Decimal`. При выполнении запроса `INSERT` ClickHouse обрабатывает тип данных ORC `DECIMAL` как `Decimal128`.

84
docs/ru/operations/settings/settings.md
View File

@ -490,6 +490,23 @@ ClickHouse может парсить только базовый формат `Y
Значение по умолчанию: `ALL`. Значение по умолчанию: `ALL`.
## join_algorithm {#settings-join_algorithm}
Определяет алгоритм выполнения запроса [JOIN](../../sql-reference/statements/select/join.md).
Возможные значения:
- `hash` — используется [алгоритм соединения хешированием](https://ru.wikipedia.org/wiki/Алгоритм_соединения_хешированием).
- `partial_merge` — используется [алгоритм соединения слиянием сортированных списков](https://ru.wikipedia.org/wiki/Алгоритм_соединения_слиянием_сортированных_списков).
- `prefer_partial_merge` — используется алгоритм соединения слиянием сортированных списков, когда это возможно.
- `auto` — сервер ClickHouse пытается на лету заменить алгоритм `hash` на `merge`, чтобы избежать переполнения памяти.
Значение по умолчанию: `hash`.
При использовании алгоритма `hash` правая часть `JOIN` загружается в оперативную память.
При использовании алгоритма `partial_merge` сервер сортирует данные и сбрасывает их на диск. Работа алгоритма `merge` в ClickHouse немного отличается от классической реализации. Сначала ClickHouse сортирует правую таблицу по блокам на основе [ключей соединения](../../sql-reference/statements/select/join.md#select-join) и для отсортированных блоков строит индексы min-max. Затем он сортирует куски левой таблицы на основе ключей соединения и объединяет их с правой таблицей операцией `JOIN`. Созданные min-max индексы используются для пропуска тех блоков из правой таблицы, которые не участвуют в данной операции `JOIN`.
## join_any_take_last_row {#settings-join_any_take_last_row} ## join_any_take_last_row {#settings-join_any_take_last_row}
Изменяет поведение операций, выполняемых со строгостью `ANY`. Изменяет поведение операций, выполняемых со строгостью `ANY`.
@ -1204,8 +1221,15 @@ load_balancing = round_robin
Работает для форматов JSONEachRow и TSKV. Работает для форматов JSONEachRow и TSKV.
## output_format_json_quote_64bit_integers {#session_settings-output_format_json_quote_64bit_integers} ## output_format_json_quote_64bit_integers {#session_settings-output_format_json_quote_64bit_integers}
Управляет кавычками при выводе 64-битных или более [целых чисел](../../sql-reference/data-types/int-uint.md) (например, `UInt64` или `Int128`) в формате [JSON](../../interfaces/formats.md#json).
По умолчанию такие числа заключаются в кавычки. Это поведение соответствует большинству реализаций JavaScript.
Если значение истинно, то при использовании JSON\* форматов UInt64 и Int64 числа выводятся в кавычках (из соображений совместимости с большинством реализаций JavaScript), иначе - без кавычек. Возможные значения:
- 0 — числа выводятся без кавычек.
- 1 — числа выводятся в кавычках.
Значение по умолчанию: 1.
## output_format_json_quote_denormals {#settings-output_format_json_quote_denormals} ## output_format_json_quote_denormals {#settings-output_format_json_quote_denormals}
@ -2979,6 +3003,53 @@ SELECT
FROM fuse_tbl FROM fuse_tbl
``` ```
## allow_experimental_database_replicated {#allow_experimental_database_replicated}
Позволяет создавать базы данных с движком [Replicated](../../engines/database-engines/replicated.md).
Возможные значения:
- 0 — Disabled.
- 1 — Enabled.
Значение по умолчанию: `0`.
## database_replicated_initial_query_timeout_sec {#database_replicated_initial_query_timeout_sec}
Устанавливает, как долго начальный DDL-запрос должен ждать, пока реплицированная база данных прецессирует предыдущие записи очереди DDL в секундах.
Возможные значения:
- Положительное целое число.
- 0 — Не ограничено.
Значение по умолчанию: `300`.
## distributed_ddl_task_timeout {#distributed_ddl_task_timeout}
Устанавливает тайм-аут для ответов на DDL-запросы от всех хостов в кластере. Если DDL-запрос не был выполнен на всех хостах, ответ будет содержать ошибку тайм-аута, и запрос будет выполнен в асинхронном режиме.
Возможные значения:
- Положительное целое число.
- 0 — Асинхронный режим.
- Отрицательное число — бесконечный тайм-аут.
Значение по умолчанию: `180`.
## distributed_ddl_output_mode {#distributed_ddl_output_mode}
Задает формат результата распределенного DDL-запроса.
Возможные значения:
- `throw` — возвращает набор результатов со статусом выполнения запросов для всех хостов, где завершен запрос. Если запрос не выполнился на некоторых хостах, то будет выброшено исключение. Если запрос еще не закончен на некоторых хостах и таймаут [distributed_ddl_task_timeout](#distributed_ddl_task_timeout) превышен, то выбрасывается исключение `TIMEOUT_EXCEEDED`.
- `none` — идентично `throw`, но распределенный DDL-запрос не возвращает набор результатов.
- `null_status_on_timeout` — возвращает `NULL` в качестве статуса выполнения в некоторых строках набора результатов вместо выбрасывания `TIMEOUT_EXCEEDED`, если запрос не закончен на соответствующих хостах.
- `never_throw` — не выбрасывает исключение и `TIMEOUT_EXCEEDED`, если запрос не удался на некоторых хостах.
Значение по умолчанию: `throw`.
## flatten_nested {#flatten-nested} ## flatten_nested {#flatten-nested}
Устанавливает формат данных у [вложенных](../../sql-reference/data-types/nested-data-structures/nested.md) столбцов. Устанавливает формат данных у [вложенных](../../sql-reference/data-types/nested-data-structures/nested.md) столбцов.
@ -3059,3 +3130,14 @@ SETTINGS index_granularity = 8192 │
**Использование** **Использование**
Если установлено значение `0`, то табличная функция не делает Nullable столбцы, а вместо NULL выставляет значения по умолчанию для скалярного типа. Это также применимо для значений NULL внутри массивов. Если установлено значение `0`, то табличная функция не делает Nullable столбцы, а вместо NULL выставляет значения по умолчанию для скалярного типа. Это также применимо для значений NULL внутри массивов.
## output_format_arrow_low_cardinality_as_dictionary {#output-format-arrow-low-cardinality-as-dictionary}
Позволяет конвертировать тип [LowCardinality](../../sql-reference/data-types/lowcardinality.md) в тип `DICTIONARY` формата [Arrow](../../interfaces/formats.md#data-format-arrow) для запросов `SELECT`.
Возможные значения:
- 0 — тип `LowCardinality` не конвертируется в тип `DICTIONARY`.
- 1 — тип `LowCardinality` конвертируется в тип `DICTIONARY`.
Значение по умолчанию: `0`.

38
docs/ru/operations/system-tables/data_skipping_indices.md Normal file
View File

@ -0,0 +1,38 @@
# system.data_skipping_indices {#system-data-skipping-indices}
Содержит информацию о существующих индексах пропуска данных во всех таблицах.
Столбцы:
- `database` ([String](../../sql-reference/data-types/string.md)) — имя базы данных.
- `table` ([String](../../sql-reference/data-types/string.md)) — имя таблицы.
- `name` ([String](../../sql-reference/data-types/string.md)) — имя индекса.
- `type` ([String](../../sql-reference/data-types/string.md)) — тип индекса.
- `expr` ([String](../../sql-reference/data-types/string.md)) — выражение, используемое для вычисления индекса.
- `granularity` ([UInt64](../../sql-reference/data-types/int-uint.md)) — количество гранул в блоке данных.
**Пример**
```sql
SELECT * FROM system.data_skipping_indices LIMIT 2 FORMAT Vertical;
```
```text
Row 1:
──────
database: default
table: user_actions
name: clicks_idx
type: minmax
expr: clicks
granularity: 1
Row 2:
──────
database: default
table: users
name: contacts_null_idx
type: minmax
expr: assumeNotNull(contacts_null)
granularity: 1
```

4
docs/ru/sql-reference/aggregate-functions/reference/median.md
View File

@ -4,7 +4,6 @@
Функции: Функции:
- `median` — синоним для [quantile](../../../sql-reference/aggregate-functions/reference/quantile.md#quantile). - `median` — синоним для [quantile](../../../sql-reference/aggregate-functions/reference/quantile.md#quantile).
- `medianDeterministic` — синоним для [quantileDeterministic](../../../sql-reference/aggregate-functions/reference/quantiledeterministic.md#quantiledeterministic). - `medianDeterministic` — синоним для [quantileDeterministic](../../../sql-reference/aggregate-functions/reference/quantiledeterministic.md#quantiledeterministic).
- `medianExact` — синоним для [quantileExact](../../../sql-reference/aggregate-functions/reference/quantileexact.md#quantileexact). - `medianExact` — синоним для [quantileExact](../../../sql-reference/aggregate-functions/reference/quantileexact.md#quantileexact).
@ -31,7 +30,7 @@
Запрос: Запрос:
``` sql ``` sql
SELECT medianDeterministic(val, 1) FROM t SELECT medianDeterministic(val, 1) FROM t;
``` ```
Результат: Результат:
@ -41,4 +40,3 @@ SELECT medianDeterministic(val, 1) FROM t
│ 1.5 │ │ 1.5 │
└─────────────────────────────┘ └─────────────────────────────┘
``` ```

24
docs/ru/sql-reference/data-types/lowcardinality.md
View File

@ -15,7 +15,7 @@ LowCardinality(data_type)
**Параметры** **Параметры**
- `data_type` — [String](string.md), [FixedString](fixedstring.md), [Date](date.md), [DateTime](datetime.md) и числа за исключением типа [Decimal](decimal.md). `LowCardinality` неэффективен для некоторых типов данных, см. описание настройки [allow_suspicious_low_cardinality_types](../../operations/settings/settings.md#allow_suspicious_low_cardinality_types). - `data_type` — [String](string.md), [FixedString](fixedstring.md), [Date](date.md), [DateTime](datetime.md) и числа за исключением типа [Decimal](decimal.md). `LowCardinality` неэффективен для некоторых типов данных, см. описание настройки [allow_suspicious_low_cardinality_types](../../operations/settings/settings.md#allow_suspicious_low_cardinality_types).
## Описание {#lowcardinality-dscr} ## Описание {#lowcardinality-dscr}
@ -23,11 +23,11 @@ LowCardinality(data_type)
Эффективность использования типа данных `LowCarditality` зависит от разнообразия данных. Если словарь содержит менее 10 000 различных значений, ClickHouse в основном показывает более высокую эффективность чтения и хранения данных. Если же словарь содержит более 100 000 различных значений, ClickHouse может работать хуже, чем при использовании обычных типов данных. Эффективность использования типа данных `LowCarditality` зависит от разнообразия данных. Если словарь содержит менее 10 000 различных значений, ClickHouse в основном показывает более высокую эффективность чтения и хранения данных. Если же словарь содержит более 100 000 различных значений, ClickHouse может работать хуже, чем при использовании обычных типов данных.
При работе со строками, использование `LowCardinality` вместо [Enum](enum.md) обеспечивает большую гибкость в использовании и часто показывает такую же или более высокую эффективность. При работе со строками использование `LowCardinality` вместо [Enum](enum.md) обеспечивает большую гибкость в использовании и часто показывает такую же или более высокую эффективность.
## Пример ## Пример
Создать таблицу со столбцами типа `LowCardinality`: Создание таблицы со столбцами типа `LowCardinality`:
```sql ```sql
CREATE TABLE lc_t CREATE TABLE lc_t
@ -43,18 +43,18 @@ ORDER BY id
Настройки: Настройки:
- [low_cardinality_max_dictionary_size](../../operations/settings/settings.md#low_cardinality_max_dictionary_size) - [low_cardinality_max_dictionary_size](../../operations/settings/settings.md#low_cardinality_max_dictionary_size)
- [low_cardinality_use_single_dictionary_for_part](../../operations/settings/settings.md#low_cardinality_use_single_dictionary_for_part) - [low_cardinality_use_single_dictionary_for_part](../../operations/settings/settings.md#low_cardinality_use_single_dictionary_for_part)
- [low_cardinality_allow_in_native_format](../../operations/settings/settings.md#low_cardinality_allow_in_native_format) - [low_cardinality_allow_in_native_format](../../operations/settings/settings.md#low_cardinality_allow_in_native_format)
- [allow_suspicious_low_cardinality_types](../../operations/settings/settings.md#allow_suspicious_low_cardinality_types) - [allow_suspicious_low_cardinality_types](../../operations/settings/settings.md#allow_suspicious_low_cardinality_types)
- [output_format_arrow_low_cardinality_as_dictionary](../../operations/settings/settings.md#output-format-arrow-low-cardinality-as-dictionary)
Функции: Функции:
- [toLowCardinality](../functions/type-conversion-functions.md#tolowcardinality) - [toLowCardinality](../functions/type-conversion-functions.md#tolowcardinality)
## Смотрите также ## Смотрите также
- [A Magical Mystery Tour of the LowCardinality Data Type](https://www.altinity.com/blog/2019/3/27/low-cardinality). - [A Magical Mystery Tour of the LowCardinality Data Type](https://www.altinity.com/blog/2019/3/27/low-cardinality).
- [Reducing Clickhouse Storage Cost with the Low Cardinality Type – Lessons from an Instana Engineer](https://www.instana.com/blog/reducing-clickhouse-storage-cost-with-the-low-cardinality-type-lessons-from-an-instana-engineer/). - [Reducing Clickhouse Storage Cost with the Low Cardinality Type – Lessons from an Instana Engineer](https://www.instana.com/blog/reducing-clickhouse-storage-cost-with-the-low-cardinality-type-lessons-from-an-instana-engineer/).
- [String Optimization (video presentation in Russian)](https://youtu.be/rqf-ILRgBdY?list=PL0Z2YDlm0b3iwXCpEFiOOYmwXzVmjJfEt). [Slides in English](https://github.com/yandex/clickhouse-presentations/raw/master/meetup19/string_optimization.pdf). - [String Optimization (video presentation in Russian)](https://youtu.be/rqf-ILRgBdY?list=PL0Z2YDlm0b3iwXCpEFiOOYmwXzVmjJfEt). [Slides in English](https://github.com/yandex/clickhouse-presentations/raw/master/meetup19/string_optimization.pdf).

7
docs/ru/sql-reference/data-types/map.md
View File

@ -9,11 +9,8 @@ toc_title: Map(key, value)
**Параметры** **Параметры**
- `key` — ключ. [String](../../sql-reference/data-types/string.md) или [Integer](../../sql-reference/data-types/int-uint.md). - `key` — ключ. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md), [LowCardinality](../../sql-reference/data-types/lowcardinality.md) или [FixedString](../../sql-reference/data-types/fixedstring.md).
- `value` — значение. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md) или [Array](../../sql-reference/data-types/array.md). - `value` — значение. [String](../../sql-reference/data-types/string.md), [Integer](../../sql-reference/data-types/int-uint.md), [Array](../../sql-reference/data-types/array.md), [LowCardinality](../../sql-reference/data-types/lowcardinality.md) или [FixedString](../../sql-reference/data-types/fixedstring.md).
!!! warning "Предупреждение"
Сейчас использование типа данных `Map` является экспериментальной возможностью. Чтобы использовать этот тип данных, включите настройку `allow_experimental_map_type = 1`.
Чтобы получить значение из колонки `a Map('key', 'value')`, используйте синтаксис `a['key']`. В настоящее время такая подстановка работает по алгоритму с линейной сложностью. Чтобы получить значение из колонки `a Map('key', 'value')`, используйте синтаксис `a['key']`. В настоящее время такая подстановка работает по алгоритму с линейной сложностью.

48
docs/ru/sql-reference/functions/json-functions.md
View File

@ -306,3 +306,51 @@ SELECT JSONExtractKeysAndValuesRaw('{"a": [-100, 200.0], "b":{"c": {"d": "hello"
│ [('d','"hello"'),('f','"world"')] │ │ [('d','"hello"'),('f','"world"')] │
└───────────────────────────────────────────────────────────────────────────────────────────────────────┘ └───────────────────────────────────────────────────────────────────────────────────────────────────────┘
``` ```
## toJSONString {#tojsonstring}
Сериализует значение в JSON представление. Поддерживаются различные типы данных и вложенные структуры.
По умолчанию 64-битные [целые числа](../../sql-reference/data-types/int-uint.md) и более (например, `UInt64` или `Int128`) заключаются в кавычки. Настройка [output_format_json_quote_64bit_integers](../../operations/settings/settings.md#session_settings-output_format_json_quote_64bit_integers) управляет этим поведением.
Специальные значения `NaN` и `inf` заменяются на `null`. Чтобы они отображались, включите настройку [output_format_json_quote_denormals](../../operations/settings/settings.md#settings-output_format_json_quote_denormals).
Когда сериализуется значение [Enum](../../sql-reference/data-types/enum.md), то функция выводит его имя.
**Синтаксис**
``` sql
toJSONString(value)
```
**Аргументы**
- `value` — значение, которое необходимо сериализовать. Может быть любого типа.
**Возвращаемое значение**
- JSON представление значения.
Тип: [String](../../sql-reference/data-types/string.md).
**Пример**
Первый пример показывает сериализацию [Map](../../sql-reference/data-types/map.md).
Во втором примере есть специальные значения, обернутые в [Tuple](../../sql-reference/data-types/tuple.md).
Запрос:
``` sql
SELECT toJSONString(map('key1', 1, 'key2', 2));
SELECT toJSONString(tuple(1.25, NULL, NaN, +inf, -inf, [])) SETTINGS output_format_json_quote_denormals = 1;
```
Результат:
``` text
{"key1":1,"key2":2}
[1.25,null,"nan","inf","-inf",[]]
```
**Смотрите также**
- [output_format_json_quote_64bit_integers](../../operations/settings/settings.md#session_settings-output_format_json_quote_64bit_integers)
- [output_format_json_quote_denormals](../../operations/settings/settings.md#settings-output_format_json_quote_denormals)

32
docs/ru/sql-reference/functions/type-conversion-functions.md
View File

@ -462,27 +462,29 @@ SELECT reinterpret(toInt8(-1), 'UInt8') as int_to_uint,
## CAST(x, T) {#type_conversion_function-cast} ## CAST(x, T) {#type_conversion_function-cast}
Преобразует входное значение `x` в указанный тип данных `T`. В отличии от функции `reinterpret` использует внешнее представление значения `x`. Преобразует входное значение к указанному типу данных. В отличие от функции [reinterpret](#type_conversion_function-reinterpret) `CAST` пытается представить то же самое значение в новом типе данных. Если преобразование невозможно, то возникает исключение.
Поддерживается несколько вариантов синтаксиса.
Поддерживается также синтаксис `CAST(x AS t)`.
!!! warning "Предупреждение"
Если значение `x` не может быть преобразовано к типу `T`, возникает переполнение. Например, `CAST(-1, 'UInt8')` возвращает 255.
**Синтаксис** **Синтаксис**
``` sql ``` sql
CAST(x, T) CAST(x, T)
CAST(x AS t)
x::t
``` ```
**Аргументы** **Аргументы**
- `x` — любой тип данных. - `x` — значение, которое нужно преобразовать. Может быть любого типа.
- `T` — конечный тип данных. [String](../../sql-reference/data-types/string.md). - `T` — имя типа данных. [String](../../sql-reference/data-types/string.md).
- `t` — тип данных.
**Возвращаемое значение** **Возвращаемое значение**
- Значение конечного типа данных. - Преобразованное значение.
!!! note "Примечание"
Если входное значение выходит за границы нового типа, то результат переполняется. Например, `CAST(-1, 'UInt8')` возвращает `255`.
**Примеры** **Примеры**
@ -491,16 +493,16 @@ CAST(x, T)
```sql ```sql
SELECT SELECT
CAST(toInt8(-1), 'UInt8') AS cast_int_to_uint, CAST(toInt8(-1), 'UInt8') AS cast_int_to_uint,
CAST(toInt8(1), 'Float32') AS cast_int_to_float, CAST(1.5 AS Decimal(3,2)) AS cast_float_to_decimal,
CAST('1', 'UInt32') AS cast_string_to_int '1'::Int32 AS cast_string_to_int;
``` ```
Результат: Результат:
``` ```
┌─cast_int_to_uint─┬─cast_int_to_float─┬─cast_string_to_int─┐ ┌─cast_int_to_uint─┬─cast_float_to_decimal─┬─cast_string_to_int─┐
│ 255 │ 1 │ 1 │ │ 255 │ 1.50 │ 1 │
└──────────────────┴───────────────────┴────────────────────┘ └──────────────────┴───────────────────────┴────────────────────┘
``` ```
Запрос: Запрос:
@ -524,7 +526,7 @@ SELECT
Преобразование в FixedString(N) работает только для аргументов типа [String](../../sql-reference/data-types/string.md) или [FixedString](../../sql-reference/data-types/fixedstring.md). Преобразование в FixedString(N) работает только для аргументов типа [String](../../sql-reference/data-types/string.md) или [FixedString](../../sql-reference/data-types/fixedstring.md).
Поддерживается преобразование к типу [Nullable](../../sql-reference/functions/type-conversion-functions.md) и обратно. Поддерживается преобразование к типу [Nullable](../../sql-reference/data-types/nullable.md) и обратно.
**Примеры** **Примеры**

16
docs/ru/sql-reference/statements/alter/partition.md
View File

@ -17,7 +17,7 @@ toc_title: PARTITION
- [CLEAR INDEX IN PARTITION](#alter_clear-index-partition) — очистить построенные вторичные индексы для заданной партиции; - [CLEAR INDEX IN PARTITION](#alter_clear-index-partition) — очистить построенные вторичные индексы для заданной партиции;
- [FREEZE PARTITION](#alter_freeze-partition) — создать резервную копию партиции; - [FREEZE PARTITION](#alter_freeze-partition) — создать резервную копию партиции;
- [UNFREEZE PARTITION](#alter_unfreeze-partition) — удалить резервную копию партиции; - [UNFREEZE PARTITION](#alter_unfreeze-partition) — удалить резервную копию партиции;
- [FETCH PARTITION](#alter_fetch-partition) — скачать партицию с другого сервера; - [FETCH PARTITION\|PART](#alter_fetch-partition) — скачать партицию/кусок с другого сервера;
- [MOVE PARTITION\|PART](#alter_move-partition) — переместить партицию/кускок на другой диск или том. - [MOVE PARTITION\|PART](#alter_move-partition) — переместить партицию/кускок на другой диск или том.
- [UPDATE IN PARTITION](#update-in-partition) — обновить данные внутри партиции по условию. - [UPDATE IN PARTITION](#update-in-partition) — обновить данные внутри партиции по условию.
- [DELETE IN PARTITION](#delete-in-partition) — удалить данные внутри партиции по условию. - [DELETE IN PARTITION](#delete-in-partition) — удалить данные внутри партиции по условию.
@ -209,29 +209,35 @@ ALTER TABLE 'table_name' UNFREEZE [PARTITION 'part_expr'] WITH NAME 'backup_name
Удаляет с диска "замороженные" партиции с указанным именем. Если секция `PARTITION` опущена, запрос удаляет резервную копию всех партиций сразу. Удаляет с диска "замороженные" партиции с указанным именем. Если секция `PARTITION` опущена, запрос удаляет резервную копию всех партиций сразу.
## FETCH PARTITION {#alter_fetch-partition} ## FETCH PARTITION\|PART {#alter_fetch-partition}
``` sql ``` sql
ALTER TABLE table_name FETCH PARTITION partition_expr FROM 'path-in-zookeeper' ALTER TABLE table_name FETCH PARTITION|PART partition_expr FROM 'path-in-zookeeper'
``` ```
Загружает партицию с другого сервера. Этот запрос работает только для реплицированных таблиц. Загружает партицию с другого сервера. Этот запрос работает только для реплицированных таблиц.
Запрос выполняет следующее: Запрос выполняет следующее:
1. Загружает партицию с указанного шарда. Путь к шарду задается в секции `FROM` (‘path-in-zookeeper’). Обратите внимание, нужно задавать путь к шарду в ZooKeeper. 1. Загружает партицию/кусок с указанного шарда. Путь к шарду задается в секции `FROM` (‘path-in-zookeeper’). Обратите внимание, нужно задавать путь к шарду в ZooKeeper.
2. Помещает загруженные данные в директорию `detached` таблицы `table_name`. Чтобы прикрепить эти данные к таблице, используйте запрос [ATTACH PARTITION\|PART](#alter_attach-partition). 2. Помещает загруженные данные в директорию `detached` таблицы `table_name`. Чтобы прикрепить эти данные к таблице, используйте запрос [ATTACH PARTITION\|PART](#alter_attach-partition).
Например: Например:
1. FETCH PARTITION
``` sql ``` sql
ALTER TABLE users FETCH PARTITION 201902 FROM '/clickhouse/tables/01-01/visits'; ALTER TABLE users FETCH PARTITION 201902 FROM '/clickhouse/tables/01-01/visits';
ALTER TABLE users ATTACH PARTITION 201902; ALTER TABLE users ATTACH PARTITION 201902;
``` ```
2. FETCH PART
``` sql
ALTER TABLE users FETCH PART 201901_2_2_0 FROM '/clickhouse/tables/01-01/visits';
ALTER TABLE users ATTACH PART 201901_2_2_0;
```
Следует иметь в виду: Следует иметь в виду:
- Запрос `ALTER TABLE t FETCH PARTITION` не реплицируется. Он загружает партицию в директорию `detached` только на локальном сервере. - Запрос `ALTER TABLE t FETCH PARTITION|PART` не реплицируется. Он загружает партицию в директорию `detached` только на локальном сервере.
- Запрос `ALTER TABLE t ATTACH` реплицируется — он добавляет данные в таблицу сразу на всех репликах. На одной из реплик данные будут добавлены из директории `detached`, а на других — из соседних реплик. - Запрос `ALTER TABLE t ATTACH` реплицируется — он добавляет данные в таблицу сразу на всех репликах. На одной из реплик данные будут добавлены из директории `detached`, а на других — из соседних реплик.
Перед загрузкой данных система проверяет, существует ли партиция и совпадает ли её структура со структурой таблицы. При этом автоматически выбирается наиболее актуальная реплика среди всех живых реплик. Перед загрузкой данных система проверяет, существует ли партиция и совпадает ли её структура со структурой таблицы. При этом автоматически выбирается наиболее актуальная реплика среди всех живых реплик.

2
docs/ru/sql-reference/statements/grant.md
View File

@ -282,7 +282,7 @@ GRANT INSERT(x,y) ON db.table TO john
- `ALTER MATERIALIZE TTL`. Уровень: `TABLE`. Алиасы: `MATERIALIZE TTL` - `ALTER MATERIALIZE TTL`. Уровень: `TABLE`. Алиасы: `MATERIALIZE TTL`
- `ALTER SETTINGS`. Уровень: `TABLE`. Алиасы: `ALTER SETTING`, `ALTER MODIFY SETTING`, `MODIFY SETTING` - `ALTER SETTINGS`. Уровень: `TABLE`. Алиасы: `ALTER SETTING`, `ALTER MODIFY SETTING`, `MODIFY SETTING`
- `ALTER MOVE PARTITION`. Уровень: `TABLE`. Алиасы: `ALTER MOVE PART`, `MOVE PARTITION`, `MOVE PART` - `ALTER MOVE PARTITION`. Уровень: `TABLE`. Алиасы: `ALTER MOVE PART`, `MOVE PARTITION`, `MOVE PART`
- `ALTER FETCH PARTITION`. Уровень: `TABLE`. Алиасы: `FETCH PARTITION` - `ALTER FETCH PARTITION`. Уровень: `TABLE`. Алиасы: `ALTER FETCH PART`, `FETCH PARTITION`, `FETCH PART`
- `ALTER FREEZE PARTITION`. Уровень: `TABLE`. Алиасы: `FREEZE PARTITION` - `ALTER FREEZE PARTITION`. Уровень: `TABLE`. Алиасы: `FREEZE PARTITION`
- `ALTER VIEW` Уровень: `GROUP` - `ALTER VIEW` Уровень: `GROUP`
- `ALTER VIEW REFRESH `. Уровень: `VIEW`. Алиасы: `ALTER LIVE VIEW REFRESH`, `REFRESH VIEW` - `ALTER VIEW REFRESH `. Уровень: `VIEW`. Алиасы: `ALTER LIVE VIEW REFRESH`, `REFRESH VIEW`

65
docs/ru/sql-reference/statements/select/join.md
View File

@ -4,7 +4,7 @@ toc_title: JOIN
# Секция JOIN {#select-join} # Секция JOIN {#select-join}
Join создаёт новую таблицу путем объединения столбцов из одной или нескольких таблиц с использованием общих для каждой из них значений. Это обычная операция в базах данных с поддержкой SQL, которая соответствует join из [реляционной алгебры](https://en.wikipedia.org/wiki/Relational_algebra#Joins_and_join-like_operators). Частный случай соединения одной таблицы часто называют «self-join». `JOIN` создаёт новую таблицу путем объединения столбцов из одной или нескольких таблиц с использованием общих для каждой из них значений. Это обычная операция в базах данных с поддержкой SQL, которая соответствует join из [реляционной алгебры](https://en.wikipedia.org/wiki/Relational_algebra#Joins_and_join-like_operators). Частный случай соединения одной таблицы часто называют self-join.
Синтаксис: Синтаксис:
@ -38,12 +38,21 @@ FROM <left_table>
## Настройки {#join-settings} ## Настройки {#join-settings}
!!! note "Примечание" Значение строгости по умолчанию может быть переопределено с помощью настройки [join_default_strictness](../../../operations/settings/settings.md#settings-join_default_strictness).
Значение строгости по умолчанию может быть переопределено с помощью настройки [join_default_strictness](../../../operations/settings/settings.md#settings-join_default_strictness).
Поведение сервера ClickHouse для операций `ANY JOIN` зависит от параметра [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys). Поведение сервера ClickHouse для операций `ANY JOIN` зависит от параметра [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys).
### Использование ASOF JOIN {#asof-join-usage} **См. также**
- [join_algorithm](../../../operations/settings/settings.md#settings-join_algorithm)
- [join_any_take_last_row](../../../operations/settings/settings.md#settings-join_any_take_last_row)
- [join_use_nulls](../../../operations/settings/settings.md#join_use_nulls)
- [partial_merge_join_optimizations](../../../operations/settings/settings.md#partial_merge_join_optimizations)
- [partial_merge_join_rows_in_right_blocks](../../../operations/settings/settings.md#partial_merge_join_rows_in_right_blocks)
- [join_on_disk_max_files_to_merge](../../../operations/settings/settings.md#join_on_disk_max_files_to_merge)
- [any_join_distinct_right_table_keys](../../../operations/settings/settings.md#any_join_distinct_right_table_keys)
## Использование ASOF JOIN {#asof-join-usage}
`ASOF JOIN` применим в том случае, когда необходимо объединять записи, которые не имеют точного совпадения. `ASOF JOIN` применим в том случае, когда необходимо объединять записи, которые не имеют точного совпадения.
@ -95,7 +104,7 @@ USING (equi_column1, ... equi_columnN, asof_column)
Чтобы задать значение строгости по умолчанию, используйте сессионный параметр [join_default_strictness](../../../operations/settings/settings.md#settings-join_default_strictness). Чтобы задать значение строгости по умолчанию, используйте сессионный параметр [join_default_strictness](../../../operations/settings/settings.md#settings-join_default_strictness).
#### Распределённый join {#global-join} ## Распределённый JOIN {#global-join}
Есть два пути для выполнения соединения с участием распределённых таблиц: Есть два пути для выполнения соединения с участием распределённых таблиц:
@ -104,6 +113,42 @@ USING (equi_column1, ... equi_columnN, asof_column)
Будьте аккуратны при использовании `GLOBAL`. За дополнительной информацией обращайтесь в раздел [Распределенные подзапросы](../../../sql-reference/operators/in.md#select-distributed-subqueries). Будьте аккуратны при использовании `GLOBAL`. За дополнительной информацией обращайтесь в раздел [Распределенные подзапросы](../../../sql-reference/operators/in.md#select-distributed-subqueries).
## Неявные преобразования типов {#implicit-type-conversion}
Запросы `INNER JOIN`, `LEFT JOIN`, `RIGHT JOIN` и `FULL JOIN` поддерживают неявные преобразования типов для ключей соединения. Однако запрос не может быть выполнен, если не существует типа, к которому можно привести значения ключей с обеих сторон (например, нет типа, который бы одновременно вмещал в себя значения `UInt64` и `Int64`, или `String` и `Int32`).
**Пример**
Рассмотрим таблицу `t_1`:
```text
┌─a─┬─b─┬─toTypeName(a)─┬─toTypeName(b)─┐
│ 1 │ 1 │ UInt16 │ UInt8 │
│ 2 │ 2 │ UInt16 │ UInt8 │
└───┴───┴───────────────┴───────────────┘
```
и таблицу `t_2`:
```text
┌──a─┬────b─┬─toTypeName(a)─┬─toTypeName(b)───┐
│ -1 │ 1 │ Int16 │ Nullable(Int64) │
│ 1 │ -1 │ Int16 │ Nullable(Int64) │
│ 1 │ 1 │ Int16 │ Nullable(Int64) │
└────┴──────┴───────────────┴─────────────────┘
```
Запрос
```sql
SELECT a, b, toTypeName(a), toTypeName(b) FROM t_1 FULL JOIN t_2 USING (a, b);
```
вернёт результат:
```text
┌──a─┬────b─┬─toTypeName(a)─┬─toTypeName(b)───┐
│ 1 │ 1 │ Int32 │ Nullable(Int64) │
│ 2 │ 2 │ Int32 │ Nullable(Int64) │
│ -1 │ 1 │ Int32 │ Nullable(Int64) │
│ 1 │ -1 │ Int32 │ Nullable(Int64) │
└────┴──────┴───────────────┴─────────────────┘
```
## Рекомендации по использованию {#usage-recommendations} ## Рекомендации по использованию {#usage-recommendations}
### Обработка пустых ячеек и NULL {#processing-of-empty-or-null-cells} ### Обработка пустых ячеек и NULL {#processing-of-empty-or-null-cells}
@ -142,12 +187,14 @@ USING (equi_column1, ... equi_columnN, asof_column)
### Ограничения по памяти {#memory-limitations} ### Ограничения по памяти {#memory-limitations}
По умолчанию ClickHouse использует алгоритм [hash join](https://en.wikipedia.org/wiki/Hash_join). ClickHouse берет `<right_table>` и создает для него хэш-таблицу в оперативной памяти. После некоторого порога потребления памяти ClickHouse переходит к алгоритму merge join. По умолчанию ClickHouse использует алгоритм [hash join](https://ru.wikipedia.org/wiki/Алгоритм_соединения_хешированием). ClickHouse берет правую таблицу и создает для нее хеш-таблицу в оперативной памяти. При включённой настройке `join_algorithm = 'auto'`, после некоторого порога потребления памяти ClickHouse переходит к алгоритму [merge join](https://ru.wikipedia.org/wiki/Алгоритм_соединения_слиянием_сортированных_списков). Описание алгоритмов `JOIN` см. в настройке [join_algorithm](../../../operations/settings/settings.md#settings-join_algorithm).
- [max_rows_in_join](../../../operations/settings/query-complexity.md#settings-max_rows_in_join) — ограничивает количество строк в хэш-таблице. Если вы хотите ограничить потребление памяти во время выполнения операции `JOIN`, используйте настройки:
- [max_bytes_in_join](../../../operations/settings/query-complexity.md#settings-max_bytes_in_join) — ограничивает размер хэш-таблицы.
По достижении любого из этих ограничений, ClickHouse действует в соответствии с настройкой [join_overflow_mode](../../../operations/settings/query-complexity.md#settings-join_overflow_mode). - [max_rows_in_join](../../../operations/settings/query-complexity.md#settings-max_rows_in_join) — ограничивает количество строк в хеш-таблице.
- [max_bytes_in_join](../../../operations/settings/query-complexity.md#settings-max_bytes_in_join) — ограничивает размер хеш-таблицы.
По достижении любого из этих ограничений ClickHouse действует в соответствии с настройкой [join_overflow_mode](../../../operations/settings/query-complexity.md#settings-join_overflow_mode).
## Примеры {#examples} ## Примеры {#examples}

11
docs/ru/whats-new/security-changelog.md
View File

@ -5,6 +5,17 @@ toc_title: Security Changelog
# Security Changelog {#security-changelog} # Security Changelog {#security-changelog}
## Исправлено в релизе 21.4.3.21, 2021-04-12 {#fixed-in-clickhouse-release-21-4-3-21-2019-09-10}
### CVE-2021-25263 {#cve-2021-25263}
Злоумышленник с доступом к созданию словарей может читать файлы на файловой системе сервера Clickhouse.
Злоумышленник может обойти некорректную проверку пути к файлу словаря и загрузить часть любого файла как словарь. При этом, манипулируя опциями парсинга файла, можно получить следующую часть файла и пошагово прочитать весь файл.
Исправление доступно в версиях 20.8.18.32-lts, 21.1.9.41-stable, 21.2.9.41-stable, 21.3.6.55-lts, 21.4.3.21-stable и выше.
Обнаружено благодаря: [Вячеславу Егошину](https://twitter.com/vegoshin)
## Исправлено в релизе 19.14.3.3, 2019-09-10 {#ispravleno-v-relize-19-14-3-3-2019-09-10} ## Исправлено в релизе 19.14.3.3, 2019-09-10 {#ispravleno-v-relize-19-14-3-3-2019-09-10}
### CVE-2019-15024 {#cve-2019-15024} ### CVE-2019-15024 {#cve-2019-15024}

6
docs/zh/engines/database-engines/atomic.md
View File

@ -6,12 +6,12 @@ toc_title: Atomic
# Atomic {#atomic} # Atomic {#atomic}
It is supports non-blocking `DROP` and `RENAME TABLE` queries and atomic `EXCHANGE TABLES t1 AND t2` queries. Atomic database engine is used by default. 它支持非阻塞 DROP 和 RENAME TABLE 查询以及原子 EXCHANGE TABLES t1 AND t2 查询。默认情况下使用Atomic数据库引擎。
## Creating a Database {#creating-a-database} ## 创建数据库 {#creating-a-database}
```sql ```sql
CREATE DATABASE test ENGINE = Atomic; CREATE DATABASE test ENGINE = Atomic;
``` ```
[Original article](https://clickhouse.tech/docs/en/engines/database_engines/atomic/) <!--hide--> [原文](https://clickhouse.tech/docs/en/engines/database_engines/atomic/) <!--hide-->

4
docs/zh/engines/table-engines/mergetree-family/collapsingmergetree.md
View File

@ -1,4 +1,4 @@
# 折叠树 {#table_engine-collapsingmergetree} # CollapsingMergeTree {#table_engine-collapsingmergetree}
该引擎继承于 [MergeTree](mergetree.md)，并在数据块合并算法中添加了折叠行的逻辑。 该引擎继承于 [MergeTree](mergetree.md)，并在数据块合并算法中添加了折叠行的逻辑。
@ -203,4 +203,4 @@ SELECT * FROM UAct FINAL
这种查询数据的方法是非常低效的。不要在大表中使用它。 这种查询数据的方法是非常低效的。不要在大表中使用它。
[来源文章](https://clickhouse.tech/docs/en/operations/table_engines/collapsingmergetree/) <!--hide--> [原文](https://clickhouse.tech/docs/en/operations/table_engines/collapsingmergetree/) <!--hide-->

2
docs/zh/engines/table-engines/mergetree-family/versionedcollapsingmergetree.md
View File

@ -3,7 +3,7 @@ toc_priority: 37
toc_title: "版本折叠MergeTree" toc_title: "版本折叠MergeTree"
--- ---
# 版本折叠MergeTree {#versionedcollapsingmergetree} # VersionedCollapsingMergeTree {#versionedcollapsingmergetree}
这个引擎: 这个引擎:

4
docs/zh/interfaces/tcp.md
View File

@ -5,6 +5,6 @@ toc_title: 原生接口(TCP)
# 原生接口（TCP）{#native-interface-tcp} # 原生接口（TCP）{#native-interface-tcp}
原生接口用于[命令行客户端](cli.md)，用于分布式查询处理期间的服务器间通信，以及其他C++程序。可惜的是，原生的ClickHouse协议还没有正式的规范，但它可以从ClickHouse[源代码](https://github.com/ClickHouse/ClickHouse/tree/master/src/Client)通过拦截和分析TCP流量进行反向工程。 原生接口协议用于[命令行客户端](cli.md)，用于分布式查询处理期间的服务器间通信，以及其他C++ 程序。不幸的是，原生ClickHouse协议还没有正式的规范，但它可以从ClickHouse源代码[从这里开始](https://github.com/ClickHouse/ClickHouse/tree/master/src/Client)或通过拦截和分析TCP流量进行逆向工程。
[来源文章](https://clickhouse.tech/docs/zh/interfaces/tcp/) <!--hide--> [原文](https://clickhouse.tech/docs/en/interfaces/tcp/) <!--hide-->

10
docs/zh/interfaces/third-party/gui.md vendored
View File

@ -57,9 +57,9 @@ ClickHouse Web 界面 [Tabix](https://github.com/tabixio/tabix).
- 表格预览。 - 表格预览。
- 自动完成。 - 自动完成。
### ﾂ环板-ｮﾂ嘉ｯﾂ偲 {#clickhouse-cli} ### clickhouse-cli {#clickhouse-cli}
[ﾂ环板-ｮﾂ嘉ｯﾂ偲](https://github.com/hatarist/clickhouse-cli) 是ClickHouse的替代命令行客户端，用Python 3编写。 [clickhouse-cli](https://github.com/hatarist/clickhouse-cli) 是ClickHouse的替代命令行客户端，用Python 3编写。
特征： 特征：
@ -68,15 +68,15 @@ ClickHouse Web 界面 [Tabix](https://github.com/tabixio/tabix).
- 寻呼机支持数据输出。 - 寻呼机支持数据输出。
- 自定义PostgreSQL类命令。 - 自定义PostgreSQL类命令。
### ﾂ暗ｪﾂ氾环催ﾂ団ﾂ法ﾂ人 {#clickhouse-flamegraph} ### clickhouse-flamegraph {#clickhouse-flamegraph}
[clickhouse-flamegraph](https://github.com/Slach/clickhouse-flamegraph) 是一个可视化的专业工具`system.trace_log`如[flamegraph](http://www.brendangregg.com/flamegraphs.html). [clickhouse-flamegraph](https://github.com/Slach/clickhouse-flamegraph) 是一个可视化的专业工具`system.trace_log`如[flamegraph](http://www.brendangregg.com/flamegraphs.html).
## 商业 {#shang-ye} ## 商业 {#shang-ye}
### ﾂ环板Softwareｮﾂ嘉ｯ {#holistics-software} ### Holistics {#holistics-software}
[整体学](https://www.holistics.io/) 在2019年被Gartner FrontRunners列为可用性最高排名第二的商业智能工具之一。 Holistics是一个基于SQL的全栈数据平台和商业智能工具，用于设置您的分析流程。 [Holistics](https://www.holistics.io/) 在2019年被Gartner FrontRunners列为可用性最高排名第二的商业智能工具之一。 Holistics是一个基于SQL的全栈数据平台和商业智能工具，用于设置您的分析流程。
特征： 特征：

20
docs/zh/operations/index.md
View File

@ -5,9 +5,21 @@ toc_title: "操作"
# 操作 {#operations} # 操作 {#operations}
Clickhouse运维手册主要包含下面几部分： ClickHouse操作手册由以下主要部分组成：
- 安装要求 - [安装要求](../operations/requirements.md)
- [监控](../operations/monitoring.md)
- [故障排除](../operations/troubleshooting.md)
- [使用建议](../operations/tips.md)
- [更新程序](../operations/update.md)
- [访问权限](../operations/access-rights.md)
- [数据备份](../operations/backup.md)
- [配置文件](../operations/configuration-files.md)
- [配额](../operations/quotas.md)
- [系统表](../operations/system-tables/index.md)
- [服务器配置参数](../operations/server-configuration-parameters/index.md)
- [如何用ClickHouse测试你的硬件](../operations/performance-test.md)
- [设置](../operations/settings/index.md)
- [实用工具](../operations/utilities/index.md)
[原文](https://clickhouse.tech/docs/en/operations/) <!--hide-->
[原始文章](https://clickhouse.tech/docs/en/operations/) <!--hide-->

4
docs/zh/sql-reference/functions/bitmap-functions.md
View File

@ -81,7 +81,7 @@ SELECT bitmapToArray(bitmapSubsetInRange(bitmapBuild([0,1,2,3,4,5,6,7,8,9,10,11,
**示例** **示例**
``` sql ``` sql
SELECT bitmapToArray(bitmapSubsetInRange(bitmapBuild([0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,100,200,500]), toUInt32(30), toUInt32(200))) AS res SELECT bitmapToArray(bitmapSubsetLimit(bitmapBuild([0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,100,200,500]), toUInt32(30), toUInt32(200))) AS res
``` ```
┌─res───────────────────────┐ ┌─res───────────────────────┐
@ -174,7 +174,7 @@ SELECT bitmapToArray(bitmapAnd(bitmapBuild([1,2,3]),bitmapBuild([3,4,5]))) AS re
│ [3] │ │ [3] │
└─────┘ └─────┘
## 位图 {#bitmapor} ## 位图或 {#bitmapor}
为两个位图对象进行或操作，返回一个新的位图对象。 为两个位图对象进行或操作，返回一个新的位图对象。

65
docs/zh/sql-reference/table-functions/mysql.md
View File

@ -1,13 +1,8 @@
---
machine_translated: true
machine_translated_rev: 72537a2d527c63c07aa5d2361a8829f3895cf2bd
toc_priority: 42
toc_title: mysql
---
# mysql {#mysql} # mysql {#mysql}
允许 `SELECT` 要对存储在远程MySQL服务器上的数据执行的查询。 允许对存储在远程MySQL服务器上的数据执行`SELECT`和`INSERT`查询。
**语法**
``` sql ``` sql
mysql('host:port', 'database', 'table', 'user', 'password'[, replace_query, 'on_duplicate_clause']); mysql('host:port', 'database', 'table', 'user', 'password'[, replace_query, 'on_duplicate_clause']);
@ -15,31 +10,44 @@ mysql('host:port', 'database', 'table', 'user', 'password'[, replace_query, 'on_
**参数** **参数**
- `host:port` — MySQL server address. - `host:port` — MySQL服务器地址.
- `database` — Remote database name. - `database` — 远程数据库名称.
- `table` — Remote table name. - `table` — 远程表名称.
- `user` — MySQL user. - `user` — MySQL用户.
- `password` — User password. - `password` — 用户密码.
- `replace_query` — Flag that converts `INSERT INTO` 查询到 `REPLACE INTO`. 如果 `replace_query=1`，查询被替换。 - `replace_query` — 将INSERT INTO` 查询转换为 `REPLACE INTO`的标志。如果 `replace_query=1`，查询被替换。
- `on_duplicate_clause` — The `ON DUPLICATE KEY on_duplicate_clause` 表达式被添加到 `INSERT` 查询。 - `on_duplicate_clause` — 添加 `ON DUPLICATE KEY on_duplicate_clause` 表达式到 `INSERT` 查询。明确规定只能使用 `replace_query = 0` ，如果你同时设置replace_query = 1`和`on_duplicate_clause`，ClickHouse将产生异常。
Example: `INSERT INTO t (c1,c2) VALUES ('a', 2) ON DUPLICATE KEY UPDATE c2 = c2 + 1`, where `on_duplicate_clause` is `UPDATE c2 = c2 + 1`. See the MySQL documentation to find which `on_duplicate_clause` you can use with the `ON DUPLICATE KEY` clause. 示例：`INSERT INTO t (c1,c2) VALUES ('a', 2) ON DUPLICATE KEY UPDATE c2 = c2 + 1`
To specify `on_duplicate_clause` you need to pass `0` to the `replace_query` parameter. If you simultaneously pass `replace_query = 1` and `on_duplicate_clause`, ClickHouse generates an exception. `on_duplicate_clause`这里是`UPDATE c2 = c2 + 1`。请查阅MySQL文档，来找到可以和`ON DUPLICATE KEY`一起使用的 `on_duplicate_clause`子句。
简单 `WHERE` 条款如 `=, !=, >, >=, <, <=` 当前在MySQL服务器上执行。 简单的 `WHERE` 子句如 `=, !=, >, >=, <, <=` 将即时在MySQL服务器上执行。其余的条件和 `LIMIT` 只有在对MySQL的查询完成后，才会在ClickHouse中执行采样约束。
其余的条件和 `LIMIT` 只有在对MySQL的查询完成后，才会在ClickHouse中执行采样约束。 支持使用`|`并列进行多副本查询，示例如下：
```sql
SELECT name FROM mysql(`mysql{1|2|3}:3306`, 'mysql_database', 'mysql_table', 'user', 'password');
```
或
```sql
SELECT name FROM mysql(`mysql1:3306|mysql2:3306|mysql3:3306`, 'mysql_database', 'mysql_table', 'user', 'password');
```
**返回值** **返回值**
与原始MySQL表具有相同列的table对象。 与原始MySQL表具有相同列的表对象。
!!! note "注意"
在`INSERT`查询中为了区分`mysql(...)`与带有列名列表的表名的表函数，你必须使用关键字`FUNCTION`或`TABLE FUNCTION`。查看如下示例。
## 用法示例 {#usage-example} ## 用法示例 {#usage-example}
@ -66,7 +74,7 @@ mysql> select * from test;
1 row in set (0,00 sec) 1 row in set (0,00 sec)
``` ```
从ClickHouse中选择数据: 从ClickHouse中查询数据:
``` sql ``` sql
SELECT * FROM mysql('localhost:3306', 'test', 'test', 'bayonet', '123') SELECT * FROM mysql('localhost:3306', 'test', 'test', 'bayonet', '123')
@ -78,6 +86,21 @@ SELECT * FROM mysql('localhost:3306', 'test', 'test', 'bayonet', '123')
└────────┴──────────────┴───────┴────────────────┘ └────────┴──────────────┴───────┴────────────────┘
``` ```
替换和插入：
```sql
INSERT INTO FUNCTION mysql('localhost:3306', 'test', 'test', 'bayonet', '123', 1) (int_id, float) VALUES (1, 3);
INSERT INTO TABLE FUNCTION mysql('localhost:3306', 'test', 'test', 'bayonet', '123', 0, 'UPDATE int_id = int_id + 1') (int_id, float) VALUES (1, 4);
SELECT * FROM mysql('localhost:3306', 'test', 'test', 'bayonet', '123');
```
```text
┌─int_id─┬─float─┐
│ 1 │ 3 │
│ 2 │ 4 │
└────────┴───────┘
```
## 另请参阅 {#see-also} ## 另请参阅 {#see-also}
- [该 ‘MySQL’ 表引擎](../../engines/table-engines/integrations/mysql.md) - [该 ‘MySQL’ 表引擎](../../engines/table-engines/integrations/mysql.md)

125
programs/client/Client.cpp
View File

@ -26,6 +26,7 @@
#include <boost/algorithm/string/replace.hpp> #include <boost/algorithm/string/replace.hpp>
#include <Poco/String.h> #include <Poco/String.h>
#include <Poco/Util/Application.h> #include <Poco/Util/Application.h>
#include <Columns/ColumnString.h>
#include <common/find_symbols.h> #include <common/find_symbols.h>
#include <common/LineReader.h> #include <common/LineReader.h>
#include <Common/ClickHouseRevision.h> #include <Common/ClickHouseRevision.h>
@ -301,26 +302,9 @@ private:
} }
catch (const Exception & e) catch (const Exception & e)
{ {
bool print_stack_trace = config().getBool("stacktrace", false); bool print_stack_trace = config().getBool("stacktrace", false) && e.code() != ErrorCodes::NETWORK_ERROR;
std::string text = e.displayText(); std::cerr << getExceptionMessage(e, print_stack_trace, true) << std::endl << std::endl;
/** If exception is received from server, then stack trace is embedded in message.
* If exception is thrown on client, then stack trace is in separate field.
*/
auto embedded_stack_trace_pos = text.find("Stack trace");
if (std::string::npos != embedded_stack_trace_pos && !print_stack_trace)
text.resize(embedded_stack_trace_pos);
std::cerr << "Code: " << e.code() << ". " << text << std::endl << std::endl;
/// Don't print the stack trace on the client if it was logged on the server.
/// Also don't print the stack trace in case of network errors.
if (print_stack_trace && e.code() != ErrorCodes::NETWORK_ERROR && std::string::npos == embedded_stack_trace_pos)
{
std::cerr << "Stack trace:" << std::endl << e.getStackTraceString();
}
/// If exception code isn't zero, we should return non-zero return code anyway. /// If exception code isn't zero, we should return non-zero return code anyway.
return e.code() ? e.code() : -1; return e.code() ? e.code() : -1;
@ -430,6 +414,7 @@ private:
{TokenType::ClosingRoundBracket, Replxx::Color::BROWN}, {TokenType::ClosingRoundBracket, Replxx::Color::BROWN},
{TokenType::OpeningSquareBracket, Replxx::Color::BROWN}, {TokenType::OpeningSquareBracket, Replxx::Color::BROWN},
{TokenType::ClosingSquareBracket, Replxx::Color::BROWN}, {TokenType::ClosingSquareBracket, Replxx::Color::BROWN},
{TokenType::DoubleColon, Replxx::Color::BROWN},
{TokenType::OpeningCurlyBrace, Replxx::Color::INTENSE}, {TokenType::OpeningCurlyBrace, Replxx::Color::INTENSE},
{TokenType::ClosingCurlyBrace, Replxx::Color::INTENSE}, {TokenType::ClosingCurlyBrace, Replxx::Color::INTENSE},
@ -486,6 +471,52 @@ private:
} }
#endif #endif
/// Make query to get all server warnings
std::vector<String> loadWarningMessages()
{
std::vector<String> messages;
connection->sendQuery(connection_parameters.timeouts, "SELECT message FROM system.warnings", "" /* query_id */, QueryProcessingStage::Complete);
while (true)
{
Packet packet = connection->receivePacket();
switch (packet.type)
{
case Protocol::Server::Data:
if (packet.block)
{
const ColumnString & column = typeid_cast<const ColumnString &>(*packet.block.getByPosition(0).column);
size_t rows = packet.block.rows();
for (size_t i = 0; i < rows; ++i)
messages.emplace_back(column.getDataAt(i).toString());
}
continue;
case Protocol::Server::Progress:
continue;
case Protocol::Server::ProfileInfo:
continue;
case Protocol::Server::Totals:
continue;
case Protocol::Server::Extremes:
continue;
case Protocol::Server::Log:
continue;
case Protocol::Server::Exception:
packet.exception->rethrow();
return messages;
case Protocol::Server::EndOfStream:
return messages;
default:
throw Exception(ErrorCodes::UNKNOWN_PACKET_FROM_SERVER, "Unknown packet {} from server {}",
packet.type, connection->getDescription());
}
}
}
int mainImpl() int mainImpl()
{ {
UseSSL use_ssl; UseSSL use_ssl;
@ -564,6 +595,26 @@ private:
suggest->load(connection_parameters, config().getInt("suggestion_limit")); suggest->load(connection_parameters, config().getInt("suggestion_limit"));
} }
/// Load Warnings at the beginning of connection
if (!config().has("no-warnings"))
{
try
{
std::vector<String> messages = loadWarningMessages();
if (!messages.empty())
{
std::cout << "Warnings:" << std::endl;
for (const auto & message : messages)
std::cout << "* " << message << std::endl;
std::cout << std::endl;
}
}
catch (...)
{
/// Ignore exception
}
}
/// Load command history if present. /// Load command history if present.
if (config().has("history_file")) if (config().has("history_file"))
history_file = config().getString("history_file"); history_file = config().getString("history_file");
@ -632,17 +683,10 @@ private:
} }
catch (const Exception & e) catch (const Exception & e)
{ {
// We don't need to handle the test hints in the interactive /// We don't need to handle the test hints in the interactive mode.
// mode.
std::cerr << std::endl
<< "Exception on client:" << std::endl
<< "Code: " << e.code() << ". " << e.displayText() << std::endl;
if (config().getBool("stacktrace", false))
std::cerr << "Stack trace:" << std::endl << e.getStackTraceString() << std::endl;
std::cerr << std::endl;
bool print_stack_trace = config().getBool("stacktrace", false);
std::cerr << "Exception on client:" << std::endl << getExceptionMessage(e, print_stack_trace, true) << std::endl << std::endl;
client_exception = std::make_unique<Exception>(e); client_exception = std::make_unique<Exception>(e);
} }
@ -939,18 +983,11 @@ private:
{ {
if (server_exception) if (server_exception)
{ {
std::string text = server_exception->displayText(); bool print_stack_trace = config().getBool("stacktrace", false);
auto embedded_stack_trace_pos = text.find("Stack trace");
if (std::string::npos != embedded_stack_trace_pos && !config().getBool("stacktrace", false))
{
text.resize(embedded_stack_trace_pos);
}
std::cerr << "Received exception from server (version " << server_version << "):" << std::endl std::cerr << "Received exception from server (version " << server_version << "):" << std::endl
<< "Code: " << server_exception->code() << ". " << text << std::endl; << getExceptionMessage(*server_exception, print_stack_trace, true) << std::endl;
if (is_interactive) if (is_interactive)
{
std::cerr << std::endl; std::cerr << std::endl;
}
} }
if (client_exception) if (client_exception)
@ -1409,8 +1446,7 @@ private:
{ {
// Just report it, we'll terminate below. // Just report it, we'll terminate below.
fmt::print(stderr, fmt::print(stderr,
"Error while reconnecting to the server: Code: {}: {}\n", "Error while reconnecting to the server: {}\n",
getCurrentExceptionCode(),
getCurrentExceptionMessage(true)); getCurrentExceptionMessage(true));
assert(!connection->isConnected()); assert(!connection->isConnected());
@ -2528,6 +2564,7 @@ public:
("opentelemetry-traceparent", po::value<std::string>(), "OpenTelemetry traceparent header as described by W3C Trace Context recommendation") ("opentelemetry-traceparent", po::value<std::string>(), "OpenTelemetry traceparent header as described by W3C Trace Context recommendation")
("opentelemetry-tracestate", po::value<std::string>(), "OpenTelemetry tracestate header as described by W3C Trace Context recommendation") ("opentelemetry-tracestate", po::value<std::string>(), "OpenTelemetry tracestate header as described by W3C Trace Context recommendation")
("history_file", po::value<std::string>(), "path to history file") ("history_file", po::value<std::string>(), "path to history file")
("no-warnings", "disable warnings when client connects to server")
; ;
Settings cmd_settings; Settings cmd_settings;
@ -2595,8 +2632,7 @@ public:
} }
catch (const Exception & e) catch (const Exception & e)
{ {
std::string text = e.displayText(); std::cerr << getExceptionMessage(e, false) << std::endl;
std::cerr << "Code: " << e.code() << ". " << text << std::endl;
std::cerr << "Table №" << i << std::endl << std::endl; std::cerr << "Table №" << i << std::endl << std::endl;
/// Avoid the case when error exit code can possibly overflow to normal (zero). /// Avoid the case when error exit code can possibly overflow to normal (zero).
auto exit_code = e.code() % 256; auto exit_code = e.code() % 256;
@ -2688,6 +2724,8 @@ public:
config().setBool("highlight", options["highlight"].as<bool>()); config().setBool("highlight", options["highlight"].as<bool>());
if (options.count("history_file")) if (options.count("history_file"))
config().setString("history_file", options["history_file"].as<std::string>()); config().setString("history_file", options["history_file"].as<std::string>());
if (options.count("no-warnings"))
config().setBool("no-warnings", true);
if ((query_fuzzer_runs = options["query-fuzzer-runs"].as<int>())) if ((query_fuzzer_runs = options["query-fuzzer-runs"].as<int>()))
{ {
@ -2739,8 +2777,7 @@ int mainEntryClickHouseClient(int argc, char ** argv)
} }
catch (const DB::Exception & e) catch (const DB::Exception & e)
{ {
std::string text = e.displayText(); std::cerr << DB::getExceptionMessage(e, false) << std::endl;
std::cerr << "Code: " << e.code() << ". " << text << std::endl;
return 1; return 1;
} }
catch (...) catch (...)

18
programs/local/LocalServer.cpp
View File

@ -395,24 +395,32 @@ void LocalServer::processQueries()
/// Use the same query_id (and thread group) for all queries /// Use the same query_id (and thread group) for all queries
CurrentThread::QueryScope query_scope_holder(context); CurrentThread::QueryScope query_scope_holder(context);
///Set progress show /// Set progress show
need_render_progress = config().getBool("progress", false); need_render_progress = config().getBool("progress", false);
std::function<void()> finalize_progress;
if (need_render_progress) if (need_render_progress)
{ {
/// Set progress callback, which can be run from multiple threads.
context->setProgressCallback([&](const Progress & value) context->setProgressCallback([&](const Progress & value)
{ {
/// Write progress only if progress was updated /// Write progress only if progress was updated
if (progress_indication.updateProgress(value)) if (progress_indication.updateProgress(value))
progress_indication.writeProgress(); progress_indication.writeProgress();
}); });
/// Set finalizing callback for progress, which is called right before finalizing query output.
finalize_progress = [&]()
{
progress_indication.clearProgressOutput();
};
/// Set callback for file processing progress.
progress_indication.setFileProgressCallback(context);
} }
bool echo_queries = config().hasOption("echo") || config().hasOption("verbose"); bool echo_queries = config().hasOption("echo") || config().hasOption("verbose");
if (need_render_progress)
progress_indication.setFileProgressCallback(context);
std::exception_ptr exception; std::exception_ptr exception;
for (const auto & query : queries) for (const auto & query : queries)
@ -432,7 +440,7 @@ void LocalServer::processQueries()
try try
{ {
executeQuery(read_buf, write_buf, /* allow_into_outfile = */ true, context, {}); executeQuery(read_buf, write_buf, /* allow_into_outfile = */ true, context, {}, {}, finalize_progress);
} }
catch (...) catch (...)
{ {

31
programs/server/Server.cpp
View File

@ -478,17 +478,6 @@ int Server::main(const std::vector<std::string> & /*args*/)
CurrentMetrics::set(CurrentMetrics::Revision, ClickHouseRevision::getVersionRevision()); CurrentMetrics::set(CurrentMetrics::Revision, ClickHouseRevision::getVersionRevision());
CurrentMetrics::set(CurrentMetrics::VersionInteger, ClickHouseRevision::getVersionInteger()); CurrentMetrics::set(CurrentMetrics::VersionInteger, ClickHouseRevision::getVersionInteger());
if (ThreadFuzzer::instance().isEffective())
LOG_WARNING(log, "ThreadFuzzer is enabled. Application will run slowly and unstable.");
#if !defined(NDEBUG) || !defined(__OPTIMIZE__)
LOG_WARNING(log, "Server was built in debug mode. It will work slowly.");
#endif
#if defined(SANITIZER)
LOG_WARNING(log, "Server was built with sanitizer. It will work slowly.");
#endif
/** Context contains all that query execution is dependent: /** Context contains all that query execution is dependent:
* settings, available functions, data types, aggregate functions, databases, ... * settings, available functions, data types, aggregate functions, databases, ...
*/ */
@ -498,6 +487,18 @@ int Server::main(const std::vector<std::string> & /*args*/)
global_context->makeGlobalContext(); global_context->makeGlobalContext();
global_context->setApplicationType(Context::ApplicationType::SERVER); global_context->setApplicationType(Context::ApplicationType::SERVER);
#if !defined(NDEBUG) || !defined(__OPTIMIZE__)
global_context->addWarningMessage("Server was built in debug mode. It will work slowly.");
#endif
if (ThreadFuzzer::instance().isEffective())
global_context->addWarningMessage("ThreadFuzzer is enabled. Application will run slowly and unstable.");
#if defined(SANITIZER)
global_context->addWarningMessage("Server was built with sanitizer. It will work slowly.");
#endif
// Initialize global thread pool. Do it before we fetch configs from zookeeper // Initialize global thread pool. Do it before we fetch configs from zookeeper
// nodes (`from_zk`), because ZooKeeper interface uses the pool. We will // nodes (`from_zk`), because ZooKeeper interface uses the pool. We will
// ignore `max_thread_pool_size` in configs we fetch from ZK, but oh well. // ignore `max_thread_pool_size` in configs we fetch from ZK, but oh well.
@ -553,8 +554,10 @@ int Server::main(const std::vector<std::string> & /*args*/)
if (ptrace(PTRACE_TRACEME, 0, nullptr, nullptr) == -1) if (ptrace(PTRACE_TRACEME, 0, nullptr, nullptr) == -1)
{ {
/// Program is run under debugger. Modification of it's binary image is ok for breakpoints. /// Program is run under debugger. Modification of it's binary image is ok for breakpoints.
LOG_WARNING(log, "Server is run under debugger and its binary image is modified (most likely with breakpoints).", global_context->addWarningMessage(
calculated_binary_hash); fmt::format("Server is run under debugger and its binary image is modified (most likely with breakpoints).",
calculated_binary_hash)
);
} }
else else
{ {
@ -637,7 +640,7 @@ int Server::main(const std::vector<std::string> & /*args*/)
} }
else else
{ {
LOG_WARNING(log, message); global_context->addWarningMessage(message);
} }
} }

50
programs/server/play.html
View File

@ -9,7 +9,7 @@
Do not use any JavaScript or CSS frameworks or preprocessors. Do not use any JavaScript or CSS frameworks or preprocessors.
This HTML page should not require any build systems (node.js, npm, gulp, etc.) This HTML page should not require any build systems (node.js, npm, gulp, etc.)
This HTML page should not be minified, instead it should be reasonably minimalistic by itself. This HTML page should not be minified, instead it should be reasonably minimalistic by itself.
This HTML page should not load any external resources This HTML page should not load any external resources on load.
(CSS and JavaScript must be embedded directly to the page. No external fonts or images should be loaded). (CSS and JavaScript must be embedded directly to the page. No external fonts or images should be loaded).
This UI should look as lightweight, clean and fast as possible. This UI should look as lightweight, clean and fast as possible.
All UI elements must be aligned in pixel-perfect way. All UI elements must be aligned in pixel-perfect way.
@ -343,13 +343,18 @@
/// Save query in history only if it is different. /// Save query in history only if it is different.
let previous_query = ''; let previous_query = '';
/// Substitute the address of the server where the page is served. const current_url = new URL(window.location);
if (location.protocol != 'file:') {
const server_address = current_url.searchParams.get('url');
if (server_address) {
document.getElementById('url').value = server_address;
} else if (location.protocol != 'file:') {
/// Substitute the address of the server where the page is served.
document.getElementById('url').value = location.origin; document.getElementById('url').value = location.origin;
} }
/// Substitute user name if it's specified in the query string /// Substitute user name if it's specified in the query string
let user_from_url = (new URL(window.location)).searchParams.get('user'); const user_from_url = current_url.searchParams.get('user');
if (user_from_url) { if (user_from_url) {
document.getElementById('user').value = user_from_url; document.getElementById('user').value = user_from_url;
} }
@ -361,7 +366,9 @@
let user = document.getElementById('user').value; let user = document.getElementById('user').value;
let password = document.getElementById('password').value; let password = document.getElementById('password').value;
let url = document.getElementById('url').value + let server_address = document.getElementById('url').value;
let url = server_address +
/// Ask server to allow cross-domain requests. /// Ask server to allow cross-domain requests.
'?add_http_cors_header=1' + '?add_http_cors_header=1' +
'&user=' + encodeURIComponent(user) + '&user=' + encodeURIComponent(user) +
@ -390,11 +397,18 @@
response: this.response.length > 100000 ? null : this.response /// Lower than the browser's limit. response: this.response.length > 100000 ? null : this.response /// Lower than the browser's limit.
}; };
let title = "ClickHouse Query: " + query; let title = "ClickHouse Query: " + query;
let url = window.location.pathname + '?user=' + encodeURIComponent(user) + '#' + window.btoa(query);
let history_url = window.location.pathname + '?user=' + encodeURIComponent(user);
if (server_address != location.origin) {
/// Save server's address in URL if it's not identical to the address of the play UI.
history_url += '&url=' + encodeURIComponent(server_address);
}
history_url += '#' + window.btoa(query);
if (previous_query == '') { if (previous_query == '') {
history.replaceState(state, title, url); history.replaceState(state, title, history_url);
} else { } else {
history.pushState(state, title, url); history.pushState(state, title, history_url);
} }
document.title = title; document.title = title;
previous_query = query; previous_query = query;
@ -599,10 +613,16 @@
} }
/// Huge JS libraries should be loaded only if needed. /// Huge JS libraries should be loaded only if needed.
function loadJS(src) { function loadJS(src, integrity) {
return new Promise((resolve, reject) => { return new Promise((resolve, reject) => {
const script = document.createElement('script'); const script = document.createElement('script');
script.src = src; script.src = src;
if (integrity) {
script.crossOrigin = 'anonymous';
script.integrity = integrity;
} else {
console.warn('no integrity for', src)
}
script.addEventListener('load', function() { resolve(true); }); script.addEventListener('load', function() { resolve(true); });
document.head.appendChild(script); document.head.appendChild(script);
}); });
@ -613,10 +633,14 @@
if (load_dagre_promise) { return load_dagre_promise; } if (load_dagre_promise) { return load_dagre_promise; }
load_dagre_promise = Promise.all([ load_dagre_promise = Promise.all([
loadJS('https://dagrejs.github.io/project/dagre/v0.8.5/dagre.min.js'), loadJS('https://dagrejs.github.io/project/dagre/v0.8.5/dagre.min.js',
loadJS('https://dagrejs.github.io/project/graphlib-dot/v0.6.4/graphlib-dot.min.js'), 'sha384-2IH3T69EIKYC4c+RXZifZRvaH5SRUdacJW7j6HtE5rQbvLhKKdawxq6vpIzJ7j9M'),
loadJS('https://dagrejs.github.io/project/dagre-d3/v0.6.4/dagre-d3.min.js'), loadJS('https://dagrejs.github.io/project/graphlib-dot/v0.6.4/graphlib-dot.min.js',
loadJS('https://cdn.jsdelivr.net/npm/d3@7.0.0'), 'sha384-Q7oatU+b+y0oTkSoiRH9wTLH6sROySROCILZso/AbMMm9uKeq++r8ujD4l4f+CWj'),
loadJS('https://dagrejs.github.io/project/dagre-d3/v0.6.4/dagre-d3.min.js',
'sha384-9N1ty7Yz7VKL3aJbOk+8ParYNW8G5W+MvxEfFL9G7CRYPmkHI9gJqyAfSI/8190W'),
loadJS('https://cdn.jsdelivr.net/npm/d3@7.0.0',
'sha384-S+Kf0r6YzKIhKA8d1k2/xtYv+j0xYUU3E7+5YLrcPVab6hBh/r1J6cq90OXhw80u'),
]); ]);
return load_dagre_promise; return load_dagre_promise;

7
src/Access/AccessControlManager.cpp
View File

@ -64,7 +64,12 @@ public:
std::lock_guard lock{mutex}; std::lock_guard lock{mutex};
auto x = cache.get(params); auto x = cache.get(params);
if (x) if (x)
return *x; {
if ((*x)->getUser())
return *x;
/// No user, probably the user has been dropped while it was in the cache.
cache.remove(params);
}
auto res = std::shared_ptr<ContextAccess>(new ContextAccess(manager, params)); auto res = std::shared_ptr<ContextAccess>(new ContextAccess(manager, params));
cache.add(params, res); cache.add(params, res);
return res; return res;

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