diff --git a/docker/packager/README.md b/docker/packager/README.md index e0b7f38ea58..3604e8585a4 100644 --- a/docker/packager/README.md +++ b/docker/packager/README.md @@ -28,7 +28,6 @@ lrwxrwxrwx 1 root root 10 clickhouse-benchmark -> clickhouse lrwxrwxrwx 1 root root 10 clickhouse-clang -> clickhouse lrwxrwxrwx 1 root root 10 clickhouse-client -> clickhouse lrwxrwxrwx 1 root root 10 clickhouse-compressor -> clickhouse -lrwxrwxrwx 1 root root 10 clickhouse-copier -> clickhouse lrwxrwxrwx 1 root root 10 clickhouse-extract-from-config -> clickhouse lrwxrwxrwx 1 root root 10 clickhouse-format -> clickhouse lrwxrwxrwx 1 root root 10 clickhouse-lld -> clickhouse diff --git a/docs/en/operations/backup.md b/docs/en/operations/backup.md index 2d9bf2a2ee8..8639af468c2 100644 --- a/docs/en/operations/backup.md +++ b/docs/en/operations/backup.md @@ -170,7 +170,7 @@ RESTORE TABLE test.table PARTITIONS '2', '3' ### Backups as tar archives -Backups can also be stored as tar archives. The functionality is the same as for zip, except that a password is not supported. +Backups can also be stored as tar archives. The functionality is the same as for zip, except that a password is not supported. Write a backup as a tar: ``` @@ -444,10 +444,6 @@ Often data that is ingested into ClickHouse is delivered through some sort of pe Some local filesystems provide snapshot functionality (for example, [ZFS](https://en.wikipedia.org/wiki/ZFS)), but they might not be the best choice for serving live queries. A possible solution is to create additional replicas with this kind of filesystem and exclude them from the [Distributed](../engines/table-engines/special/distributed.md) tables that are used for `SELECT` queries. Snapshots on such replicas will be out of reach of any queries that modify data. As a bonus, these replicas might have special hardware configurations with more disks attached per server, which would be cost-effective. -### clickhouse-copier {#clickhouse-copier} - -[clickhouse-copier](../operations/utilities/clickhouse-copier.md) is a versatile tool that was initially created to re-shard petabyte-sized tables. It can also be used for backup and restore purposes because it reliably copies data between ClickHouse tables and clusters. - For smaller volumes of data, a simple `INSERT INTO ... SELECT ...` to remote tables might work as well. ### Manipulations with Parts {#manipulations-with-parts} diff --git a/docs/en/operations/utilities/clickhouse-copier.md b/docs/en/operations/utilities/clickhouse-copier.md deleted file mode 100644 index 0d329487504..00000000000 --- a/docs/en/operations/utilities/clickhouse-copier.md +++ /dev/null @@ -1,187 +0,0 @@ ---- -slug: /en/operations/utilities/clickhouse-copier -sidebar_position: 59 -sidebar_label: clickhouse-copier ---- - -# clickhouse-copier - -Copies data from the tables in one cluster to tables in another (or the same) cluster. - -:::note -To get a consistent copy, the data in the source tables and partitions should not change during the entire process. -::: - -You can run multiple `clickhouse-copier` instances on different servers to perform the same job. ClickHouse Keeper, or ZooKeeper, is used for syncing the processes. - -After starting, `clickhouse-copier`: - -- Connects to ClickHouse Keeper and receives: - - - Copying jobs. - - The state of the copying jobs. - -- It performs the jobs. - - Each running process chooses the “closest” shard of the source cluster and copies the data into the destination cluster, resharding the data if necessary. - -`clickhouse-copier` tracks the changes in ClickHouse Keeper and applies them on the fly. - -To reduce network traffic, we recommend running `clickhouse-copier` on the same server where the source data is located. - -## Running Clickhouse-copier {#running-clickhouse-copier} - -The utility should be run manually: - -``` bash -$ clickhouse-copier --daemon --config keeper.xml --task-path /task/path --base-dir /path/to/dir -``` - -Parameters: - -- `daemon` — Starts `clickhouse-copier` in daemon mode. -- `config` — The path to the `keeper.xml` file with the parameters for the connection to ClickHouse Keeper. -- `task-path` — The path to the ClickHouse Keeper node. This node is used for syncing `clickhouse-copier` processes and storing tasks. Tasks are stored in `$task-path/description`. -- `task-file` — Optional path to file with task configuration for initial upload to ClickHouse Keeper. -- `task-upload-force` — Force upload `task-file` even if node already exists. Default is false. -- `base-dir` — The path to logs and auxiliary files. When it starts, `clickhouse-copier` creates `clickhouse-copier_YYYYMMHHSS_` subdirectories in `$base-dir`. If this parameter is omitted, the directories are created in the directory where `clickhouse-copier` was launched. - -## Format of keeper.xml {#format-of-zookeeper-xml} - -``` xml - - - trace - 100M - 3 - - - - - 127.0.0.1 - 2181 - - - -``` - -## Configuration of Copying Tasks {#configuration-of-copying-tasks} - -``` xml - - - - - - - false - - 127.0.0.1 - 9000 - - - - ... - - - - ... - - - - - 2 - - - - 1 - - - - - 0 - - - - - 3 - - 1 - - - - - - - - source_cluster - test - hits - - - destination_cluster - test - hits2 - - - - ENGINE=ReplicatedMergeTree('/clickhouse/tables/{cluster}/{shard}/hits2', '{replica}') - PARTITION BY toMonday(date) - ORDER BY (CounterID, EventDate) - - - - jumpConsistentHash(intHash64(UserID), 2) - - - CounterID != 0 - - - - '2018-02-26' - '2018-03-05' - ... - - - - - - ... - - ... - - -``` - -`clickhouse-copier` tracks the changes in `/task/path/description` and applies them on the fly. For instance, if you change the value of `max_workers`, the number of processes running tasks will also change. diff --git a/docs/en/operations/utilities/index.md b/docs/en/operations/utilities/index.md index 8959073d00e..912a5b9ccb1 100644 --- a/docs/en/operations/utilities/index.md +++ b/docs/en/operations/utilities/index.md @@ -2,13 +2,11 @@ slug: /en/operations/utilities/ sidebar_position: 56 sidebar_label: List of tools and utilities -pagination_next: 'en/operations/utilities/clickhouse-copier' --- # List of tools and utilities - [clickhouse-local](../../operations/utilities/clickhouse-local.md) — Allows running SQL queries on data without starting the ClickHouse server, similar to how `awk` does this. -- [clickhouse-copier](../../operations/utilities/clickhouse-copier.md) — Copies (and reshards) data from one cluster to another cluster. - [clickhouse-benchmark](../../operations/utilities/clickhouse-benchmark.md) — Loads server with the custom queries and settings. - [clickhouse-format](../../operations/utilities/clickhouse-format.md) — Enables formatting input queries. - [ClickHouse obfuscator](../../operations/utilities/clickhouse-obfuscator.md) — Obfuscates data. diff --git a/docs/en/sql-reference/statements/alter/column.md b/docs/en/sql-reference/statements/alter/column.md index 0989c151d18..a23710b12bd 100644 --- a/docs/en/sql-reference/statements/alter/column.md +++ b/docs/en/sql-reference/statements/alter/column.md @@ -335,7 +335,7 @@ The `ALTER` query lets you create and delete separate elements (columns) in nest There is no support for deleting columns in the primary key or the sampling key (columns that are used in the `ENGINE` expression). Changing the type for columns that are included in the primary key is only possible if this change does not cause the data to be modified (for example, you are allowed to add values to an Enum or to change a type from `DateTime` to `UInt32`). -If the `ALTER` query is not sufficient to make the table changes you need, you can create a new table, copy the data to it using the [INSERT SELECT](/docs/en/sql-reference/statements/insert-into.md/#inserting-the-results-of-select) query, then switch the tables using the [RENAME](/docs/en/sql-reference/statements/rename.md/#rename-table) query and delete the old table. You can use the [clickhouse-copier](/docs/en/operations/utilities/clickhouse-copier.md) as an alternative to the `INSERT SELECT` query. +If the `ALTER` query is not sufficient to make the table changes you need, you can create a new table, copy the data to it using the [INSERT SELECT](/docs/en/sql-reference/statements/insert-into.md/#inserting-the-results-of-select) query, then switch the tables using the [RENAME](/docs/en/sql-reference/statements/rename.md/#rename-table) query and delete the old table. The `ALTER` query blocks all reads and writes for the table. In other words, if a long `SELECT` is running at the time of the `ALTER` query, the `ALTER` query will wait for it to complete. At the same time, all new queries to the same table will wait while this `ALTER` is running. diff --git a/docs/ru/getting-started/tutorial.md b/docs/ru/getting-started/tutorial.md index 34064b6cf2f..8c827137e6d 100644 --- a/docs/ru/getting-started/tutorial.md +++ b/docs/ru/getting-started/tutorial.md @@ -585,10 +585,6 @@ ENGINE = Distributed(perftest_3shards_1replicas, tutorial, hits_local, rand()); INSERT INTO tutorial.hits_all SELECT * FROM tutorial.hits_v1; ``` -:::danger Внимание! -Этот подход не годится для сегментирования больших таблиц. Есть инструмент [clickhouse-copier](../operations/utilities/clickhouse-copier.md), специально предназначенный для перераспределения любых больших таблиц. -::: - Как и следовало ожидать, вычислительно сложные запросы работают втрое быстрее, если они выполняются на трёх серверах, а не на одном. В данном случае мы использовали кластер из трёх сегментов с одной репликой для каждого. diff --git a/docs/ru/operations/backup.md b/docs/ru/operations/backup.md index 9ff13bbc8a6..50ee6b45e09 100644 --- a/docs/ru/operations/backup.md +++ b/docs/ru/operations/backup.md @@ -24,12 +24,6 @@ sidebar_label: "Резервное копирование данных" Некоторые локальные файловые системы позволяют делать снимки (например, [ZFS](https://en.wikipedia.org/wiki/ZFS)), но они могут быть не лучшим выбором для обслуживания живых запросов. Возможным решением является создание дополнительных реплик с такой файловой системой и исключение их из [Distributed](../engines/table-engines/special/distributed.md) таблиц, используемых для запросов `SELECT`. Снимки на таких репликах будут недоступны для запросов, изменяющих данные. В качестве бонуса, эти реплики могут иметь особые конфигурации оборудования с большим количеством дисков, подключенных к серверу, что будет экономически эффективным. -## clickhouse-copier {#clickhouse-copier} - -[clickhouse-copier](utilities/clickhouse-copier.md) — это универсальный инструмент, который изначально был создан для перешардирования таблиц с петабайтами данных. Его также можно использовать для резервного копирования и восстановления, поскольку он надёжно копирует данные между таблицами и кластерами ClickHouse. - -Для небольших объёмов данных можно применять `INSERT INTO ... SELECT ...` в удалённые таблицы. - ## Манипуляции с партициями {#manipuliatsii-s-partitsiiami} ClickHouse позволяет использовать запрос `ALTER TABLE ... FREEZE PARTITION ...` для создания локальной копии партиций таблицы. Это реализуется с помощью жестких ссылок (hardlinks) на каталог `/var/lib/clickhouse/shadow/`, поэтому такая копия обычно не занимает дополнительное место на диске для старых данных. Созданные копии файлов не обрабатываются сервером ClickHouse, поэтому вы можете просто оставить их там: у вас будет простая резервная копия, которая не требует дополнительной внешней системы, однако при аппаратных проблемах вы можете утратить и актуальные данные и сохраненную копию. По этой причине, лучше удаленно скопировать их в другое место, а затем удалить локальную копию. Распределенные файловые системы и хранилища объектов по-прежнему являются хорошими вариантами для этого, однако можно использовать и обычные присоединенные файловые серверы с достаточно большой ёмкостью (в этом случае передача будет происходить через сетевую файловую систему или, возможно, [rsync](https://en.wikipedia.org/wiki/Rsync)). diff --git a/docs/ru/operations/utilities/clickhouse-copier.md b/docs/ru/operations/utilities/clickhouse-copier.md deleted file mode 100644 index da86ef2d35d..00000000000 --- a/docs/ru/operations/utilities/clickhouse-copier.md +++ /dev/null @@ -1,183 +0,0 @@ ---- -slug: /ru/operations/utilities/clickhouse-copier -sidebar_position: 59 -sidebar_label: clickhouse-copier ---- - -# clickhouse-copier {#clickhouse-copier} - -Копирует данные из таблиц одного кластера в таблицы другого (или этого же) кластера. - -Можно запустить несколько `clickhouse-copier` для разных серверах для выполнения одного и того же задания. Для синхронизации между процессами используется ZooKeeper. - -После запуска, `clickhouse-copier`: - -- Соединяется с ZooKeeper и получает: - - - Задания на копирование. - - Состояние заданий на копирование. - -- Выполняет задания. - - Каждый запущенный процесс выбирает "ближайший" шард исходного кластера и копирует данные в кластер назначения, при необходимости перешардируя их. - -`clickhouse-copier` отслеживает изменения в ZooKeeper и применяет их «на лету». - -Для снижения сетевого трафика рекомендуем запускать `clickhouse-copier` на том же сервере, где находятся исходные данные. - -## Запуск Clickhouse-copier {#zapusk-clickhouse-copier} - -Утилиту следует запускать вручную следующим образом: - -``` bash -$ clickhouse-copier --daemon --config zookeeper.xml --task-path /task/path --base-dir /path/to/dir -``` - -Параметры запуска: - -- `daemon` - запускает `clickhouse-copier` в режиме демона. -- `config` - путь к файлу `zookeeper.xml` с параметрами соединения с ZooKeeper. -- `task-path` - путь к ноде ZooKeeper. Нода используется для синхронизации между процессами `clickhouse-copier` и для хранения заданий. Задания хранятся в `$task-path/description`. -- `task-file` - необязательный путь к файлу с описанием конфигурация заданий для загрузки в ZooKeeper. -- `task-upload-force` - Загрузить `task-file` в ZooKeeper даже если уже было загружено. -- `base-dir` - путь к логам и вспомогательным файлам. При запуске `clickhouse-copier` создает в `$base-dir` подкаталоги `clickhouse-copier_YYYYMMHHSS_`. Если параметр не указан, то каталоги будут создаваться в каталоге, где `clickhouse-copier` был запущен. - -## Формат Zookeeper.xml {#format-zookeeper-xml} - -``` xml - - - trace - 100M - 3 - - - - - 127.0.0.1 - 2181 - - - -``` - -## Конфигурация заданий на копирование {#konfiguratsiia-zadanii-na-kopirovanie} - -``` xml - - - - - - - false - - 127.0.0.1 - 9000 - - - - ... - - - - ... - - - - - 2 - - - - 1 - - - - - 0 - - - - - 3 - - 1 - - - - - - - - source_cluster - test - hits - - - destination_cluster - test - hits2 - - - - ENGINE=ReplicatedMergeTree('/clickhouse/tables/{cluster}/{shard}/hits2', '{replica}') - PARTITION BY toMonday(date) - ORDER BY (CounterID, EventDate) - - - - jumpConsistentHash(intHash64(UserID), 2) - - - CounterID != 0 - - - - '2018-02-26' - '2018-03-05' - ... - - - - - - ... - - ... - - -``` - -`clickhouse-copier` отслеживает изменения `/task/path/description` и применяет их «на лету». Если вы поменяете, например, значение `max_workers`, то количество процессов, выполняющих задания, также изменится. diff --git a/docs/ru/operations/utilities/index.md b/docs/ru/operations/utilities/index.md index 9eb90a3037c..e4b01a0276d 100644 --- a/docs/ru/operations/utilities/index.md +++ b/docs/ru/operations/utilities/index.md @@ -7,7 +7,6 @@ sidebar_position: 56 # Утилиты ClickHouse {#utility-clickhouse} - [clickhouse-local](clickhouse-local.md) - позволяет выполнять SQL-запросы над данными без остановки сервера ClickHouse, подобно утилите `awk`. -- [clickhouse-copier](clickhouse-copier.md) - копирует (и перешардирует) данные с одного кластера на другой. - [clickhouse-benchmark](../../operations/utilities/clickhouse-benchmark.md) — устанавливает соединение с сервером ClickHouse и запускает циклическое выполнение указанных запросов. - [clickhouse-format](../../operations/utilities/clickhouse-format.md) — позволяет форматировать входящие запросы. - [ClickHouse obfuscator](../../operations/utilities/clickhouse-obfuscator.md) — обфусцирует данные. diff --git a/docs/ru/sql-reference/statements/alter/column.md b/docs/ru/sql-reference/statements/alter/column.md index 385a9835eca..2ea045f4ae3 100644 --- a/docs/ru/sql-reference/statements/alter/column.md +++ b/docs/ru/sql-reference/statements/alter/column.md @@ -94,7 +94,7 @@ RENAME COLUMN [IF EXISTS] name to new_name Переименовывает столбец `name` в `new_name`. Если указано выражение `IF EXISTS`, то запрос не будет возвращать ошибку при условии, что столбец `name` не существует. Поскольку переименование не затрагивает физические данные колонки, запрос выполняется практически мгновенно. -**ЗАМЕЧЕНИЕ**: Столбцы, являющиеся частью основного ключа или ключа сортировки (заданные с помощью `ORDER BY` или `PRIMARY KEY`), не могут быть переименованы. Попытка переименовать эти слобцы приведет к `SQL Error [524]`. +**ЗАМЕЧЕНИЕ**: Столбцы, являющиеся частью основного ключа или ключа сортировки (заданные с помощью `ORDER BY` или `PRIMARY KEY`), не могут быть переименованы. Попытка переименовать эти слобцы приведет к `SQL Error [524]`. Пример: @@ -254,7 +254,7 @@ SELECT groupArray(x), groupArray(s) FROM tmp; Отсутствует возможность удалять столбцы, входящие в первичный ключ или ключ для сэмплирования (в общем, входящие в выражение `ENGINE`). Изменение типа у столбцов, входящих в первичный ключ возможно только в том случае, если это изменение не приводит к изменению данных (например, разрешено добавление значения в Enum или изменение типа с `DateTime` на `UInt32`). -Если возможностей запроса `ALTER` не хватает для нужного изменения таблицы, вы можете создать новую таблицу, скопировать туда данные с помощью запроса [INSERT SELECT](../insert-into.md#inserting-the-results-of-select), затем поменять таблицы местами с помощью запроса [RENAME](../rename.md#rename-table), и удалить старую таблицу. В качестве альтернативы для запроса `INSERT SELECT`, можно использовать инструмент [clickhouse-copier](../../../sql-reference/statements/alter/index.md). +Если возможностей запроса `ALTER` не хватает для нужного изменения таблицы, вы можете создать новую таблицу, скопировать туда данные с помощью запроса [INSERT SELECT](../insert-into.md#inserting-the-results-of-select), затем поменять таблицы местами с помощью запроса [RENAME](../rename.md#rename-table), и удалить старую таблицу. Запрос `ALTER` блокирует все чтения и записи для таблицы. То есть если на момент запроса `ALTER` выполнялся долгий `SELECT`, то запрос `ALTER` сначала дождётся его выполнения. И в это время все новые запросы к той же таблице будут ждать, пока завершится этот `ALTER`. diff --git a/docs/zh/getting-started/tutorial.md b/docs/zh/getting-started/tutorial.md index 989cf5f57d8..d0c9bda83ef 100644 --- a/docs/zh/getting-started/tutorial.md +++ b/docs/zh/getting-started/tutorial.md @@ -582,8 +582,6 @@ ENGINE = Distributed(perftest_3shards_1replicas, tutorial, hits_local, rand()); INSERT INTO tutorial.hits_all SELECT * FROM tutorial.hits_v1; ``` -!!! warning "注意:" - 这种方法不适合大型表的分片。 有一个单独的工具 [clickhouse-copier](../operations/utilities/clickhouse-copier.md) 这可以重新分片任意大表。 正如您所期望的那样，如果计算量大的查询使用3台服务器而不是一个，则运行速度快N倍。 diff --git a/docs/zh/operations/backup.md b/docs/zh/operations/backup.md index 6d491f9c2f7..48e852b4228 100644 --- a/docs/zh/operations/backup.md +++ b/docs/zh/operations/backup.md @@ -24,12 +24,6 @@ sidebar_label: "\u6570\u636E\u5907\u4EFD" 某些本地文件系统提供快照功能（例如, [ZFS](https://en.wikipedia.org/wiki/ZFS)），但它们可能不是提供实时查询的最佳选择。 一个可能的解决方案是使用这种文件系统创建额外的副本，并将它们与用于`SELECT` 查询的 [分布式](../engines/table-engines/special/distributed.md) 表分离。 任何修改数据的查询都无法访问此类副本上的快照。 作为回报，这些副本可能具有特殊的硬件配置，每个服务器附加更多的磁盘，这将是经济高效的。 -## clickhouse-copier {#clickhouse-copier} - -[clickhouse-copier](utilities/clickhouse-copier.md) 是一个多功能工具，最初创建它是为了用于重新切分pb大小的表。 因为它能够在ClickHouse表和集群之间可靠地复制数据，所以它也可用于备份和还原数据。 - -对于较小的数据量，一个简单的 `INSERT INTO ... SELECT ...` 到远程表也可以工作。 - ## part操作 {#manipulations-with-parts} ClickHouse允许使用 `ALTER TABLE ... FREEZE PARTITION ...` 查询以创建表分区的本地副本。 这是利用硬链接(hardlink)到 `/var/lib/clickhouse/shadow/` 文件夹中实现的，所以它通常不会因为旧数据而占用额外的磁盘空间。 创建的文件副本不由ClickHouse服务器处理，所以你可以把它们留在那里：你将有一个简单的备份，不需要任何额外的外部系统，但它仍然容易出现硬件问题。 出于这个原因，最好将它们远程复制到另一个位置，然后删除本地副本。 分布式文件系统和对象存储仍然是一个不错的选择，但是具有足够大容量的正常附加文件服务器也可以工作（在这种情况下，传输将通过网络文件系统或者也许是 [rsync](https://en.wikipedia.org/wiki/Rsync) 来进行). diff --git a/docs/zh/operations/utilities/clickhouse-copier.md b/docs/zh/operations/utilities/clickhouse-copier.md deleted file mode 100644 index b01edd9257c..00000000000 --- a/docs/zh/operations/utilities/clickhouse-copier.md +++ /dev/null @@ -1,172 +0,0 @@ ---- -slug: /zh/operations/utilities/clickhouse-copier ---- -# clickhouse-copier {#clickhouse-copier} - -将数据从一个群集中的表复制到另一个（或相同）群集中的表。 - -您可以运行多个 `clickhouse-copier` 不同服务器上的实例执行相同的作业。 ZooKeeper用于同步进程。 - -开始后, `clickhouse-copier`: - -- 连接到ZooKeeper并且接收: - - - 复制作业。 - - 复制作业的状态。 - -- 它执行的工作。 - - 每个正在运行的进程都会选择源集群的“最接近”分片，然后将数据复制到目标集群，并在必要时重新分片数据。 - -`clickhouse-copier` 跟踪ZooKeeper中的更改，并实时应用它们。 - -为了减少网络流量，我们建议运行 `clickhouse-copier` 在源数据所在的同一服务器上。 - -## 运行Clickhouse-copier {#running-clickhouse-copier} - -该实用程序应手动运行: - -``` bash -clickhouse-copier --daemon --config zookeeper.xml --task-path /task/path --base-dir /path/to/dir -``` - -参数: - -- `daemon` — 在守护进程模式下启动`clickhouse-copier`。 -- `config` — `zookeeper.xml`文件的路径，其中包含用于连接ZooKeeper的参数。 -- `task-path` — ZooKeeper节点的路径。 该节点用于同步`clickhouse-copier`进程和存储任务。 任务存储在`$task-path/description`中。 -- `task-file` — 可选的非必须参数, 指定一个包含任务配置的参数文件, 用于初始上传到ZooKeeper。 -- `task-upload-force` — 即使节点已经存在，也强制上载`task-file`。 -- `base-dir` — 日志和辅助文件的路径。 启动时，`clickhouse-copier`在`$base-dir`中创建`clickhouse-copier_YYYYMMHHSS_`子目录。 如果省略此参数，则会在启动`clickhouse-copier`的目录中创建目录。 - - - -## Zookeeper.xml格式 {#format-of-zookeeper-xml} - -``` xml - - - trace - 100M - 3 - - - - - 127.0.0.1 - 2181 - - - -``` - -## 复制任务的配置 {#configuration-of-copying-tasks} - -``` xml - - - - - - false - - 127.0.0.1 - 9000 - - - ... - - - - ... - - - - - 2 - - - - 1 - - - - - 0 - - - - - 3 - - 1 - - - - - - - - source_cluster - test - hits - - - destination_cluster - test - hits2 - - - - ENGINE=ReplicatedMergeTree('/clickhouse/tables/{cluster}/{shard}/hits2', '{replica}') - PARTITION BY toMonday(date) - ORDER BY (CounterID, EventDate) - - - - jumpConsistentHash(intHash64(UserID), 2) - - - CounterID != 0 - - - - '2018-02-26' - '2018-03-05' - ... - - - - - - ... - - ... - - -``` - -`clickhouse-copier` 跟踪更改 `/task/path/description` 并在飞行中应用它们。 例如，如果你改变的值 `max_workers`，运行任务的进程数也会发生变化。 diff --git a/docs/zh/operations/utilities/index.md b/docs/zh/operations/utilities/index.md index af158baf275..cebe312450c 100644 --- a/docs/zh/operations/utilities/index.md +++ b/docs/zh/operations/utilities/index.md @@ -4,5 +4,4 @@ slug: /zh/operations/utilities/ # 实用工具 {#clickhouse-utility} - [本地查询](clickhouse-local.md) — 在不停止ClickHouse服务的情况下，对数据执行查询操作(类似于 `awk` 命令)。 -- [跨集群复制](clickhouse-copier.md) — 在不同集群间复制数据。 - [性能测试](clickhouse-benchmark.md) — 连接到Clickhouse服务器，执行性能测试。 diff --git a/docs/zh/sql-reference/statements/alter.md b/docs/zh/sql-reference/statements/alter.md index 002d5102fa3..48665ae04ab 100644 --- a/docs/zh/sql-reference/statements/alter.md +++ b/docs/zh/sql-reference/statements/alter.md @@ -150,7 +150,7 @@ ALTER TABLE visits MODIFY COLUMN browser Array(String) 不支持对primary key或者sampling key中的列（在 `ENGINE` 表达式中用到的列）进行删除操作。改变包含在primary key中的列的类型时，如果操作不会导致数据的变化（例如，往Enum中添加一个值，或者将`DateTime` 类型改成 `UInt32`），那么这种操作是可行的。 -如果 `ALTER` 操作不足以完成你想要的表变动操作，你可以创建一张新的表，通过 [INSERT SELECT](../../sql-reference/statements/insert-into.md#inserting-the-results-of-select)将数据拷贝进去，然后通过 [RENAME](../../sql-reference/statements/misc.md#misc_operations-rename)将新的表改成和原有表一样的名称，并删除原有的表。你可以使用 [clickhouse-copier](../../operations/utilities/clickhouse-copier.md) 代替 `INSERT SELECT`。 +如果 `ALTER` 操作不足以完成你想要的表变动操作，你可以创建一张新的表，通过 [INSERT SELECT](../../sql-reference/statements/insert-into.md#inserting-the-results-of-select)将数据拷贝进去，然后通过 [RENAME](../../sql-reference/statements/misc.md#misc_operations-rename)将新的表改成和原有表一样的名称，并删除原有的表。 `ALTER` 操作会阻塞对表的所有读写操作。换句话说，当一个大的 `SELECT` 语句和 `ALTER`同时执行时，`ALTER`会等待，直到 `SELECT` 执行结束。与此同时，当 `ALTER` 运行时，新的 sql 语句将会等待。 diff --git a/packages/clickhouse-server.yaml b/packages/clickhouse-server.yaml index 7894129b8e3..dc183ead102 100644 --- a/packages/clickhouse-server.yaml +++ b/packages/clickhouse-server.yaml @@ -50,8 +50,6 @@ contents: dst: /etc/init.d/clickhouse-server - src: clickhouse-server.service dst: /lib/systemd/system/clickhouse-server.service -- src: root/usr/bin/clickhouse-copier - dst: /usr/bin/clickhouse-copier - src: root/usr/bin/clickhouse-server dst: /usr/bin/clickhouse-server # clickhouse-keeper part diff --git a/programs/CMakeLists.txt b/programs/CMakeLists.txt index 62bcf068879..d945fdf4a6f 100644 --- a/programs/CMakeLists.txt +++ b/programs/CMakeLists.txt @@ -122,7 +122,6 @@ add_subdirectory (local) add_subdirectory (benchmark) add_subdirectory (extract-from-config) add_subdirectory (compressor) -add_subdirectory (copier) add_subdirectory (format) add_subdirectory (obfuscator) add_subdirectory (install) @@ -200,7 +199,6 @@ clickhouse_program_install(clickhouse-server server) clickhouse_program_install(clickhouse-client client chc) clickhouse_program_install(clickhouse-local local chl ch) clickhouse_program_install(clickhouse-benchmark benchmark) -clickhouse_program_install(clickhouse-copier copier) clickhouse_program_install(clickhouse-extract-from-config extract-from-config) clickhouse_program_install(clickhouse-compressor compressor) clickhouse_program_install(clickhouse-format format) diff --git a/programs/copier/Aliases.h b/programs/copier/Aliases.h deleted file mode 100644 index 02be3441acd..00000000000 --- a/programs/copier/Aliases.h +++ /dev/null @@ -1,15 +0,0 @@ -#pragma once - -#include - -#include - -#include - -namespace DB -{ - using ConfigurationPtr = Poco::AutoPtr; - - using DatabaseAndTableName = std::pair; - using ListOfDatabasesAndTableNames = std::vector; -} diff --git a/programs/copier/CMakeLists.txt b/programs/copier/CMakeLists.txt deleted file mode 100644 index 2c17e70bc5e..00000000000 --- a/programs/copier/CMakeLists.txt +++ /dev/null @@ -1,28 +0,0 @@ -set(CLICKHOUSE_COPIER_SOURCES - "${CMAKE_CURRENT_SOURCE_DIR}/ClusterCopierApp.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/ClusterCopier.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/Internals.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/ShardPartition.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/ShardPartitionPiece.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/StatusAccumulator.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/TaskCluster.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/TaskShard.cpp" - "${CMAKE_CURRENT_SOURCE_DIR}/TaskTable.cpp") - -set (CLICKHOUSE_COPIER_LINK - PRIVATE - clickhouse_common_zookeeper - clickhouse_common_config - clickhouse_parsers - clickhouse_functions - clickhouse_table_functions - clickhouse_aggregate_functions - string_utils - - PUBLIC - daemon -) - -set(CLICKHOUSE_COPIER_INCLUDE SYSTEM PRIVATE ${CMAKE_CURRENT_SOURCE_DIR}) - -clickhouse_program_add(copier) diff --git a/programs/copier/ClusterCopier.cpp b/programs/copier/ClusterCopier.cpp deleted file mode 100644 index 59505d08f5c..00000000000 --- a/programs/copier/ClusterCopier.cpp +++ /dev/null @@ -1,2076 +0,0 @@ -#include "ClusterCopier.h" - -#include "Internals.h" -#include "StatusAccumulator.h" - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -namespace CurrentMetrics -{ - extern const Metric LocalThread; - extern const Metric LocalThreadActive; - extern const Metric LocalThreadScheduled; -} - -namespace DB -{ - -namespace ErrorCodes -{ - extern const int NOT_IMPLEMENTED; - extern const int LOGICAL_ERROR; - extern const int UNFINISHED; - extern const int BAD_ARGUMENTS; -} - - -void ClusterCopier::init() -{ - auto zookeeper = getContext()->getZooKeeper(); - - task_description_watch_callback = [this] (const Coordination::WatchResponse & response) - { - if (response.error != Coordination::Error::ZOK) - return; - UInt64 version = ++task_description_version; - LOG_INFO(log, "Task description should be updated, local version {}", version); - }; - - task_description_path = task_zookeeper_path + "/description"; - task_cluster = std::make_unique(task_zookeeper_path, working_database_name); - - reloadTaskDescription(); - - task_cluster->loadTasks(*task_cluster_current_config); - getContext()->setClustersConfig(task_cluster_current_config, false, task_cluster->clusters_prefix); - - /// Set up shards and their priority - task_cluster->random_engine.seed(randomSeed()); - for (auto & task_table : task_cluster->table_tasks) - { - task_table.cluster_pull = getContext()->getCluster(task_table.cluster_pull_name); - task_table.cluster_push = getContext()->getCluster(task_table.cluster_push_name); - task_table.initShards(task_cluster->random_engine); - } - - LOG_INFO(log, "Will process {} table tasks", task_cluster->table_tasks.size()); - - /// Do not initialize tables, will make deferred initialization in process() - - zookeeper->createAncestors(getWorkersPathVersion() + "/"); - zookeeper->createAncestors(getWorkersPath() + "/"); - /// Init status node - zookeeper->createIfNotExists(task_zookeeper_path + "/status", "{}"); -} - -template -decltype(auto) ClusterCopier::retry(T && func, UInt64 max_tries) -{ - std::exception_ptr exception; - - if (max_tries == 0) - throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot perform zero retries"); - - for (UInt64 try_number = 1; try_number <= max_tries; ++try_number) - { - try - { - return func(); - } - catch (...) - { - exception = std::current_exception(); - if (try_number < max_tries) - { - tryLogCurrentException(log, "Will retry"); - std::this_thread::sleep_for(retry_delay_ms); - } - } - } - - std::rethrow_exception(exception); -} - - -void ClusterCopier::discoverShardPartitions(const ConnectionTimeouts & timeouts, const TaskShardPtr & task_shard) -{ - TaskTable & task_table = task_shard->task_table; - - LOG_INFO(log, "Discover partitions of shard {}", task_shard->getDescription()); - - auto get_partitions = [&] () { return getShardPartitions(timeouts, *task_shard); }; - auto existing_partitions_names = retry(get_partitions, 60); - Strings filtered_partitions_names; - Strings missing_partitions; - - /// Check that user specified correct partition names - auto check_partition_format = [] (const DataTypePtr & type, const String & partition_text_quoted) - { - MutableColumnPtr column_dummy = type->createColumn(); - ReadBufferFromString rb(partition_text_quoted); - - try - { - type->getDefaultSerialization()->deserializeTextQuoted(*column_dummy, rb, FormatSettings()); - } - catch (Exception & e) - { - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Partition {} has incorrect format. {}", partition_text_quoted, e.displayText()); - } - }; - - if (task_table.has_enabled_partitions) - { - /// Process partition in order specified by - for (const String & partition_name : task_table.enabled_partitions) - { - /// Check that user specified correct partition names - check_partition_format(task_shard->partition_key_column.type, partition_name); - - auto it = existing_partitions_names.find(partition_name); - - /// Do not process partition if it is not in enabled_partitions list - if (it == existing_partitions_names.end()) - { - missing_partitions.emplace_back(partition_name); - continue; - } - - filtered_partitions_names.emplace_back(*it); - } - - for (const String & partition_name : existing_partitions_names) - { - if (!task_table.enabled_partitions_set.contains(partition_name)) - { - LOG_INFO(log, "Partition {} will not be processed, since it is not in enabled_partitions of {}", partition_name, task_table.table_id); - } - } - } - else - { - for (const String & partition_name : existing_partitions_names) - filtered_partitions_names.emplace_back(partition_name); - } - - for (const String & partition_name : filtered_partitions_names) - { - const size_t number_of_splits = task_table.number_of_splits; - task_shard->partition_tasks.emplace(partition_name, ShardPartition(*task_shard, partition_name, number_of_splits)); - task_shard->checked_partitions.emplace(partition_name, true); - - auto shard_partition_it = task_shard->partition_tasks.find(partition_name); - PartitionPieces & shard_partition_pieces = shard_partition_it->second.pieces; - - for (size_t piece_number = 0; piece_number < number_of_splits; ++piece_number) - { - bool res = checkPresentPartitionPiecesOnCurrentShard(timeouts, *task_shard, partition_name, piece_number); - shard_partition_pieces.emplace_back(shard_partition_it->second, piece_number, res); - } - } - - if (!missing_partitions.empty()) - { - WriteBufferFromOwnString ss; - for (const String & missing_partition : missing_partitions) - ss << " " << missing_partition; - - LOG_WARNING(log, "There are no {} partitions from enabled_partitions in shard {} :{}", missing_partitions.size(), task_shard->getDescription(), ss.str()); - } - - LOG_INFO(log, "Will copy {} partitions from shard {}", task_shard->partition_tasks.size(), task_shard->getDescription()); -} - -void ClusterCopier::discoverTablePartitions(const ConnectionTimeouts & timeouts, TaskTable & task_table, UInt64 num_threads) -{ - /// Fetch partitions list from a shard - { - ThreadPool thread_pool(CurrentMetrics::LocalThread, CurrentMetrics::LocalThreadActive, CurrentMetrics::LocalThreadScheduled, num_threads ? num_threads : 2 * getNumberOfPhysicalCPUCores()); - - for (const TaskShardPtr & task_shard : task_table.all_shards) - thread_pool.scheduleOrThrowOnError([this, timeouts, task_shard]() - { - setThreadName("DiscoverPartns"); - discoverShardPartitions(timeouts, task_shard); - }); - - LOG_INFO(log, "Waiting for {} setup jobs", thread_pool.active()); - thread_pool.wait(); - } -} - -void ClusterCopier::uploadTaskDescription(const std::string & task_path, const std::string & task_file, const bool force) -{ - auto local_task_description_path = task_path + "/description"; - - String task_config_str; - { - ReadBufferFromFile in(task_file); - readStringUntilEOF(task_config_str, in); - } - if (task_config_str.empty()) - return; - - auto zookeeper = getContext()->getZooKeeper(); - - zookeeper->createAncestors(local_task_description_path); - auto code = zookeeper->tryCreate(local_task_description_path, task_config_str, zkutil::CreateMode::Persistent); - if (code != Coordination::Error::ZOK && force) - zookeeper->createOrUpdate(local_task_description_path, task_config_str, zkutil::CreateMode::Persistent); - - LOG_INFO(log, "Task description {} uploaded to {} with result {} ({})", - ((code != Coordination::Error::ZOK && !force) ? "not " : ""), local_task_description_path, code, Coordination::errorMessage(code)); -} - -void ClusterCopier::reloadTaskDescription() -{ - auto zookeeper = getContext()->getZooKeeper(); - task_description_watch_zookeeper = zookeeper; - - Coordination::Stat stat{}; - - /// It will throw exception if such a node doesn't exist. - auto task_config_str = zookeeper->get(task_description_path, &stat); - - LOG_INFO(log, "Loading task description"); - task_cluster_current_config = getConfigurationFromXMLString(task_config_str); - - /// Setup settings - task_cluster->reloadSettings(*task_cluster_current_config); - getContext()->setSettings(task_cluster->settings_common); -} - -void ClusterCopier::updateConfigIfNeeded() -{ - UInt64 version_to_update = task_description_version; - bool is_outdated_version = task_description_current_version != version_to_update; - bool is_expired_session = !task_description_watch_zookeeper || task_description_watch_zookeeper->expired(); - - if (!is_outdated_version && !is_expired_session) - return; - - LOG_INFO(log, "Updating task description"); - reloadTaskDescription(); - - task_description_current_version = version_to_update; -} - -void ClusterCopier::process(const ConnectionTimeouts & timeouts) -{ - for (TaskTable & task_table : task_cluster->table_tasks) - { - LOG_INFO(log, "Process table task {} with {} shards, {} of them are local ones", task_table.table_id, task_table.all_shards.size(), task_table.local_shards.size()); - - if (task_table.all_shards.empty()) - continue; - - /// Discover partitions of each shard and total set of partitions - if (!task_table.has_enabled_partitions) - { - /// If there are no specified enabled_partitions, we must discover them manually - discoverTablePartitions(timeouts, task_table); - - /// After partitions of each shard are initialized, initialize cluster partitions - for (const TaskShardPtr & task_shard : task_table.all_shards) - { - for (const auto & partition_elem : task_shard->partition_tasks) - { - const String & partition_name = partition_elem.first; - task_table.cluster_partitions.emplace(partition_name, ClusterPartition{}); - } - } - - for (auto & partition_elem : task_table.cluster_partitions) - { - const String & partition_name = partition_elem.first; - - for (const TaskShardPtr & task_shard : task_table.all_shards) - task_shard->checked_partitions.emplace(partition_name); - - task_table.ordered_partition_names.emplace_back(partition_name); - } - } - else - { - /// If enabled_partitions are specified, assume that each shard has all partitions - /// We will refine partition set of each shard in future - - for (const String & partition_name : task_table.enabled_partitions) - { - task_table.cluster_partitions.emplace(partition_name, ClusterPartition{}); - task_table.ordered_partition_names.emplace_back(partition_name); - } - } - - task_table.watch.restart(); - - /// Retry table processing - bool table_is_done = false; - for (UInt64 num_table_tries = 1; num_table_tries <= max_table_tries; ++num_table_tries) - { - if (tryProcessTable(timeouts, task_table)) - { - table_is_done = true; - break; - } - } - - if (!table_is_done) - { - throw Exception(ErrorCodes::UNFINISHED, "Too many tries to process table {}. Abort remaining execution", - task_table.table_id); - } - } -} - -/// Protected section - - -/* - * Creates task worker node and checks maximum number of workers not to exceed the limit. - * To achieve this we have to check version of workers_version_path node and create current_worker_path - * node atomically. - * */ - -zkutil::EphemeralNodeHolder::Ptr ClusterCopier::createTaskWorkerNodeAndWaitIfNeed( - const zkutil::ZooKeeperPtr & zookeeper, - const String & description, - bool unprioritized) -{ - std::chrono::milliseconds current_sleep_time = retry_delay_ms; - static constexpr std::chrono::milliseconds max_sleep_time(30000); // 30 sec - - if (unprioritized) - std::this_thread::sleep_for(current_sleep_time); - - String workers_version_path = getWorkersPathVersion(); - String workers_path = getWorkersPath(); - String current_worker_path = getCurrentWorkerNodePath(); - - UInt64 num_bad_version_errors = 0; - - while (true) - { - updateConfigIfNeeded(); - - Coordination::Stat stat; - zookeeper->get(workers_version_path, &stat); - auto version = stat.version; - zookeeper->get(workers_path, &stat); - - if (static_cast(stat.numChildren) >= task_cluster->max_workers) - { - LOG_INFO(log, "Too many workers ({}, maximum {}). Postpone processing {}", stat.numChildren, task_cluster->max_workers, description); - - if (unprioritized) - current_sleep_time = std::min(max_sleep_time, current_sleep_time + retry_delay_ms); - - std::this_thread::sleep_for(current_sleep_time); - num_bad_version_errors = 0; - } - else - { - Coordination::Requests ops; - ops.emplace_back(zkutil::makeSetRequest(workers_version_path, description, version)); - ops.emplace_back(zkutil::makeCreateRequest(current_worker_path, description, zkutil::CreateMode::Ephemeral)); - Coordination::Responses responses; - auto code = zookeeper->tryMulti(ops, responses); - - if (code == Coordination::Error::ZOK || code == Coordination::Error::ZNODEEXISTS) - return zkutil::EphemeralNodeHolder::existing(current_worker_path, *zookeeper); - - if (code == Coordination::Error::ZBADVERSION) - { - ++num_bad_version_errors; - - /// Try to make fast retries - if (num_bad_version_errors > 3) - { - LOG_INFO(log, "A concurrent worker has just been added, will check free worker slots again"); - std::chrono::milliseconds random_sleep_time(std::uniform_int_distribution(1, 1000)(task_cluster->random_engine)); - std::this_thread::sleep_for(random_sleep_time); - num_bad_version_errors = 0; - } - } - else - throw Coordination::Exception(code); - } - } -} - - -bool ClusterCopier::checkPartitionPieceIsClean( - const zkutil::ZooKeeperPtr & zookeeper, - const CleanStateClock & clean_state_clock, - const String & task_status_path) -{ - LogicalClock task_start_clock; - - Coordination::Stat stat{}; - if (zookeeper->exists(task_status_path, &stat)) - task_start_clock = LogicalClock(stat.mzxid); - - return clean_state_clock.is_clean() && (!task_start_clock.hasHappened() || clean_state_clock.discovery_zxid <= task_start_clock); -} - - -bool ClusterCopier::checkAllPiecesInPartitionAreDone(const TaskTable & task_table, const String & partition_name, const TasksShard & shards_with_partition) -{ - bool answer = true; - for (size_t piece_number = 0; piece_number < task_table.number_of_splits; ++piece_number) - { - bool piece_is_done = checkPartitionPieceIsDone(task_table, partition_name, piece_number, shards_with_partition); - if (!piece_is_done) - LOG_INFO(log, "Partition {} piece {} is not already done.", partition_name, piece_number); - answer &= piece_is_done; - } - - return answer; -} - - -/* The same as function above - * Assume that we don't know on which shards do we have partition certain piece. - * We'll check them all (I mean shards that contain the whole partition) - * And shards that don't have certain piece MUST mark that piece is_done true. - * */ -bool ClusterCopier::checkPartitionPieceIsDone(const TaskTable & task_table, const String & partition_name, - size_t piece_number, const TasksShard & shards_with_partition) -{ - LOG_INFO(log, "Check that all shards processed partition {} piece {} successfully", partition_name, piece_number); - - auto zookeeper = getContext()->getZooKeeper(); - - /// Collect all shards that contain partition piece number piece_number. - Strings piece_status_paths; - for (const auto & shard : shards_with_partition) - { - ShardPartition & task_shard_partition = shard->partition_tasks.find(partition_name)->second; - ShardPartitionPiece & shard_partition_piece = task_shard_partition.pieces[piece_number]; - piece_status_paths.emplace_back(shard_partition_piece.getShardStatusPath()); - } - - std::vector zxid1, zxid2; - - try - { - std::vector get_futures; - for (const String & path : piece_status_paths) - get_futures.emplace_back(zookeeper->asyncGet(path)); - - // Check that state is Finished and remember zxid - for (auto & future : get_futures) - { - auto res = future.get(); - - TaskStateWithOwner status = TaskStateWithOwner::fromString(res.data); - if (status.state != TaskState::Finished) - { - LOG_INFO(log, "The task {} is being rewritten by {}. Partition piece will be rechecked", res.data, status.owner); - return false; - } - - zxid1.push_back(res.stat.pzxid); - } - - const String piece_is_dirty_flag_path = task_table.getCertainPartitionPieceIsDirtyPath(partition_name, piece_number); - const String piece_is_dirty_cleaned_path = task_table.getCertainPartitionPieceIsCleanedPath(partition_name, piece_number); - const String piece_task_status_path = task_table.getCertainPartitionPieceTaskStatusPath(partition_name, piece_number); - - CleanStateClock clean_state_clock (zookeeper, piece_is_dirty_flag_path, piece_is_dirty_cleaned_path); - - const bool is_clean = checkPartitionPieceIsClean(zookeeper, clean_state_clock, piece_task_status_path); - - - if (!is_clean) - { - LOG_INFO(log, "Partition {} become dirty", partition_name); - return false; - } - - get_futures.clear(); - for (const String & path : piece_status_paths) - get_futures.emplace_back(zookeeper->asyncGet(path)); - - // Remember zxid of states again - for (auto & future : get_futures) - { - auto res = future.get(); - zxid2.push_back(res.stat.pzxid); - } - } - catch (const Coordination::Exception & e) - { - LOG_INFO(log, "A ZooKeeper error occurred while checking partition {} piece number {}. Will recheck the partition. Error: {}", partition_name, toString(piece_number), e.displayText()); - return false; - } - - // If all task is finished and zxid is not changed then partition could not become dirty again - for (UInt64 shard_num = 0; shard_num < piece_status_paths.size(); ++shard_num) - { - if (zxid1[shard_num] != zxid2[shard_num]) - { - LOG_INFO(log, "The task {} is being modified now. Partition piece will be rechecked", piece_status_paths[shard_num]); - return false; - } - } - - LOG_INFO(log, "Partition {} piece number {} is copied successfully", partition_name, toString(piece_number)); - return true; -} - - -TaskStatus ClusterCopier::tryMoveAllPiecesToDestinationTable(const TaskTable & task_table, const String & partition_name) -{ - bool inject_fault = false; - if (move_fault_probability > 0) - { - double value = std::uniform_real_distribution<>(0, 1)(task_table.task_cluster.random_engine); - inject_fault = value < move_fault_probability; - } - - LOG_INFO(log, "Try to move {} to destination table", partition_name); - - auto zookeeper = getContext()->getZooKeeper(); - - const auto current_partition_attach_is_active = task_table.getPartitionAttachIsActivePath(partition_name); - const auto current_partition_attach_is_done = task_table.getPartitionAttachIsDonePath(partition_name); - - /// Create ephemeral node to mark that we are active and process the partition - zookeeper->createAncestors(current_partition_attach_is_active); - zkutil::EphemeralNodeHolderPtr partition_attach_node_holder; - try - { - partition_attach_node_holder = zkutil::EphemeralNodeHolder::create(current_partition_attach_is_active, *zookeeper, host_id); - } - catch (const Coordination::Exception & e) - { - if (e.code == Coordination::Error::ZNODEEXISTS) - { - LOG_INFO(log, "Someone is already moving pieces {}", current_partition_attach_is_active); - return TaskStatus::Active; - } - - throw; - } - - - /// Exit if task has been already processed; - /// create blocking node to signal cleaning up if it is abandoned - { - String status_data; - if (zookeeper->tryGet(current_partition_attach_is_done, status_data)) - { - TaskStateWithOwner status = TaskStateWithOwner::fromString(status_data); - if (status.state == TaskState::Finished) - { - LOG_INFO(log, "All pieces for partition from this task {} has been successfully moved to destination table by {}", current_partition_attach_is_active, status.owner); - return TaskStatus::Finished; - } - - /// Task is abandoned, because previously we created ephemeral node, possibly in other copier's process. - /// Initialize DROP PARTITION - LOG_INFO(log, "Moving piece for partition {} has not been successfully finished by {}. Will try to move by myself.", current_partition_attach_is_active, status.owner); - - /// Remove is_done marker. - zookeeper->remove(current_partition_attach_is_done); - } - } - - - /// Try start processing, create node about it - { - String start_state = TaskStateWithOwner::getData(TaskState::Started, host_id); - zookeeper->create(current_partition_attach_is_done, start_state, zkutil::CreateMode::Persistent); - } - - - /// Try to drop destination partition in original table - if (task_table.allow_to_drop_target_partitions) - { - DatabaseAndTableName original_table = task_table.table_push; - - WriteBufferFromOwnString ss; - ss << "ALTER TABLE " << getQuotedTable(original_table) << ((partition_name == "'all'") ? " DROP PARTITION ID " : " DROP PARTITION ") << partition_name; - - UInt64 num_shards_drop_partition = executeQueryOnCluster(task_table.cluster_push, ss.str(), task_cluster->settings_push, ClusterExecutionMode::ON_EACH_SHARD); - if (num_shards_drop_partition != task_table.cluster_push->getShardCount()) - return TaskStatus::Error; - - LOG_INFO(log, "Drop partition {} in original table {} have been executed successfully on {} shards of {}", - partition_name, getQuotedTable(original_table), num_shards_drop_partition, task_table.cluster_push->getShardCount()); - } - - /// Move partition to original destination table. - for (size_t current_piece_number = 0; current_piece_number < task_table.number_of_splits; ++current_piece_number) - { - LOG_INFO(log, "Trying to move partition {} piece {} to original table", partition_name, toString(current_piece_number)); - - ASTPtr query_alter_ast; - String query_alter_ast_string; - - DatabaseAndTableName original_table = task_table.table_push; - DatabaseAndTableName helping_table = DatabaseAndTableName(original_table.first, - original_table.second + "_piece_" + - toString(current_piece_number)); - - Settings settings_push = task_cluster->settings_push; - ClusterExecutionMode execution_mode = ClusterExecutionMode::ON_EACH_NODE; - - if (settings_push.alter_sync == 1) - execution_mode = ClusterExecutionMode::ON_EACH_SHARD; - - query_alter_ast_string += " ALTER TABLE " + getQuotedTable(original_table) + - ((partition_name == "'all'") ? " ATTACH PARTITION ID " : " ATTACH PARTITION ") + partition_name + - " FROM " + getQuotedTable(helping_table); - - LOG_INFO(log, "Executing ALTER query: {}", query_alter_ast_string); - - try - { - /// Try attach partition on each shard - UInt64 num_nodes = executeQueryOnCluster( - task_table.cluster_push, - query_alter_ast_string, - task_cluster->settings_push, - execution_mode); - - if (settings_push.alter_sync == 1) - { - LOG_INFO( - log, - "Destination tables {} have been executed alter query successfully on {} shards of {}", - getQuotedTable(task_table.table_push), - num_nodes, - task_table.cluster_push->getShardCount()); - - if (num_nodes != task_table.cluster_push->getShardCount()) - return TaskStatus::Error; - } - else - { - LOG_INFO(log, "Number of nodes that executed ALTER query successfully : {}", toString(num_nodes)); - } - } - catch (...) - { - LOG_INFO(log, "Error while moving partition {} piece {} to original table", partition_name, toString(current_piece_number)); - LOG_WARNING(log, "In case of non-replicated tables it can cause duplicates."); - throw; - } - - if (inject_fault) - throw Exception(ErrorCodes::UNFINISHED, "Copy fault injection is activated"); - } - - /// Create node to signal that we finished moving - /// Also increment a counter of processed partitions - { - const auto state_finished = TaskStateWithOwner::getData(TaskState::Finished, host_id); - const auto task_status = task_zookeeper_path + "/status"; - - /// Try until success - while (true) - { - Coordination::Stat stat; - auto status_json = zookeeper->get(task_status, &stat); - auto statuses = StatusAccumulator::fromJSON(status_json); - - /// Increment status for table. - (*statuses)[task_table.name_in_config].processed_partitions_count += 1; - auto statuses_to_commit = StatusAccumulator::serializeToJSON(statuses); - - Coordination::Requests ops; - ops.emplace_back(zkutil::makeSetRequest(current_partition_attach_is_done, state_finished, 0)); - ops.emplace_back(zkutil::makeSetRequest(task_status, statuses_to_commit, stat.version)); - - Coordination::Responses responses; - Coordination::Error code = zookeeper->tryMulti(ops, responses); - - if (code == Coordination::Error::ZOK) - break; - } - } - - return TaskStatus::Finished; -} - -/// This is needed to create internal Distributed table -/// Removes column's TTL expression from `CREATE` query -/// Removes MATEREALIZED or ALIAS columns not to copy additional and useless data over the network. -/// Removes data skipping indices. -ASTPtr ClusterCopier::removeAliasMaterializedAndTTLColumnsFromCreateQuery(const ASTPtr & query_ast, bool allow_to_copy_alias_and_materialized_columns) -{ - const ASTs & column_asts = query_ast->as().columns_list->columns->children; - auto new_columns = std::make_shared(); - - for (const ASTPtr & column_ast : column_asts) - { - const auto & column = column_ast->as(); - - /// Skip this columns - if (!column.default_specifier.empty() && !allow_to_copy_alias_and_materialized_columns) - { - ColumnDefaultKind kind = columnDefaultKindFromString(column.default_specifier); - if (kind == ColumnDefaultKind::Materialized || kind == ColumnDefaultKind::Alias) - continue; - } - - /// Remove TTL on columns definition. - auto new_column_ast = column_ast->clone(); - auto & new_column = new_column_ast->as(); - if (new_column.ttl) - new_column.ttl.reset(); - - new_columns->children.emplace_back(new_column_ast); - } - - ASTPtr new_query_ast = query_ast->clone(); - auto & new_query = new_query_ast->as(); - - auto new_columns_list = std::make_shared(); - new_columns_list->set(new_columns_list->columns, new_columns); - - /// Skip indices and projections are not needed, because distributed table doesn't support it. - - new_query.replace(new_query.columns_list, new_columns_list); - - return new_query_ast; -} - -/// Replaces ENGINE and table name in a create query -std::shared_ptr rewriteCreateQueryStorage(const ASTPtr & create_query_ast, - const DatabaseAndTableName & new_table, - const ASTPtr & new_storage_ast) -{ - const auto & create = create_query_ast->as(); - auto res = std::make_shared(create); - - if (create.storage == nullptr || new_storage_ast == nullptr) - throw Exception(ErrorCodes::LOGICAL_ERROR, "Storage is not specified"); - - res->setDatabase(new_table.first); - res->setTable(new_table.second); - - res->children.clear(); - res->set(res->columns_list, create.columns_list->clone()); - res->set(res->storage, new_storage_ast->clone()); - /// Just to make it better and don't store additional flag like `is_table_created` somewhere else - res->if_not_exists = true; - - return res; -} - - -bool ClusterCopier::tryDropPartitionPiece( - ShardPartition & task_partition, - const size_t current_piece_number, - const zkutil::ZooKeeperPtr & zookeeper, - const CleanStateClock & clean_state_clock) -{ - if (is_safe_mode) - throw Exception(ErrorCodes::NOT_IMPLEMENTED, "DROP PARTITION is prohibited in safe mode"); - - TaskTable & task_table = task_partition.task_shard.task_table; - ShardPartitionPiece & partition_piece = task_partition.pieces[current_piece_number]; - - const String current_shards_path = partition_piece.getPartitionPieceShardsPath(); - const String current_partition_active_workers_dir = partition_piece.getPartitionPieceActiveWorkersPath(); - const String is_dirty_flag_path = partition_piece.getPartitionPieceIsDirtyPath(); - const String dirty_cleaner_path = partition_piece.getPartitionPieceCleanerPath(); - const String is_dirty_cleaned_path = partition_piece.getPartitionPieceIsCleanedPath(); - - zkutil::EphemeralNodeHolder::Ptr cleaner_holder; - try - { - cleaner_holder = zkutil::EphemeralNodeHolder::create(dirty_cleaner_path, *zookeeper, host_id); - } - catch (const Coordination::Exception & e) - { - if (e.code == Coordination::Error::ZNODEEXISTS) - { - LOG_INFO(log, "Partition {} piece {} is cleaning now by somebody, sleep", task_partition.name, toString(current_piece_number)); - std::this_thread::sleep_for(retry_delay_ms); - return false; - } - - throw; - } - - Coordination::Stat stat{}; - if (zookeeper->exists(current_partition_active_workers_dir, &stat)) - { - if (stat.numChildren != 0) - { - LOG_INFO(log, "Partition {} contains {} active workers while trying to drop it. Going to sleep.", task_partition.name, stat.numChildren); - std::this_thread::sleep_for(retry_delay_ms); - return false; - } - else - { - zookeeper->remove(current_partition_active_workers_dir); - } - } - - { - zkutil::EphemeralNodeHolder::Ptr active_workers_lock; - try - { - active_workers_lock = zkutil::EphemeralNodeHolder::create(current_partition_active_workers_dir, *zookeeper, host_id); - } - catch (const Coordination::Exception & e) - { - if (e.code == Coordination::Error::ZNODEEXISTS) - { - LOG_INFO(log, "Partition {} is being filled now by somebody, sleep", task_partition.name); - return false; - } - - throw; - } - - // Lock the dirty flag - zookeeper->set(is_dirty_flag_path, host_id, clean_state_clock.discovery_version.value()); - zookeeper->tryRemove(partition_piece.getPartitionPieceCleanStartPath()); - CleanStateClock my_clock(zookeeper, is_dirty_flag_path, is_dirty_cleaned_path); - - /// Remove all status nodes - { - Strings children; - if (zookeeper->tryGetChildren(current_shards_path, children) == Coordination::Error::ZOK) - for (const auto & child : children) - { - zookeeper->removeRecursive(current_shards_path + "/" + child); - } - } - - - DatabaseAndTableName original_table = task_table.table_push; - DatabaseAndTableName helping_table = DatabaseAndTableName(original_table.first, original_table.second + "_piece_" + toString(current_piece_number)); - - String query = "ALTER TABLE " + getQuotedTable(helping_table); - query += ((task_partition.name == "'all'") ? " DROP PARTITION ID " : " DROP PARTITION ") + task_partition.name + ""; - - /// TODO: use this statement after servers will be updated up to 1.1.54310 - // query += " DROP PARTITION ID '" + task_partition.name + "'"; - - ClusterPtr & cluster_push = task_table.cluster_push; - Settings settings_push = task_cluster->settings_push; - - /// It is important, DROP PARTITION must be done synchronously - settings_push.alter_sync = 2; - - LOG_INFO(log, "Execute distributed DROP PARTITION: {}", query); - /// We have to drop partition_piece on each replica - size_t num_shards = executeQueryOnCluster( - cluster_push, query, - settings_push, - ClusterExecutionMode::ON_EACH_NODE); - - LOG_INFO(log, "DROP PARTITION was successfully executed on {} nodes of a cluster.", num_shards); - - /// Update the locking node - if (!my_clock.is_stale()) - { - zookeeper->set(is_dirty_flag_path, host_id, my_clock.discovery_version.value()); - if (my_clock.clean_state_version) - zookeeper->set(is_dirty_cleaned_path, host_id, my_clock.clean_state_version.value()); - else - zookeeper->create(is_dirty_cleaned_path, host_id, zkutil::CreateMode::Persistent); - } - else - { - LOG_INFO(log, "Clean state is altered when dropping the partition, cowardly bailing"); - /// clean state is stale - return false; - } - - LOG_INFO(log, "Partition {} piece {} was dropped on cluster {}", task_partition.name, toString(current_piece_number), task_table.cluster_push_name); - if (zookeeper->tryCreate(current_shards_path, host_id, zkutil::CreateMode::Persistent) == Coordination::Error::ZNODEEXISTS) - zookeeper->set(current_shards_path, host_id); - } - - LOG_INFO(log, "Partition {} piece {} is safe for work now.", task_partition.name, toString(current_piece_number)); - return true; -} - -bool ClusterCopier::tryProcessTable(const ConnectionTimeouts & timeouts, TaskTable & task_table) -{ - /// Create destination table - TaskStatus task_status = TaskStatus::Error; - - task_status = tryCreateDestinationTable(timeouts, task_table); - /// Exit if success - if (task_status != TaskStatus::Finished) - { - LOG_WARNING(log, "Create destination table failed "); - return false; - } - - /// Set all_partitions_count for table in Zookeeper - auto zookeeper = getContext()->getZooKeeper(); - while (true) - { - Coordination::Stat stat; - auto status_json = zookeeper->get(task_zookeeper_path + "/status", &stat); - auto statuses = StatusAccumulator::fromJSON(status_json); - - /// Exit if someone already set the initial value for this table. - if (statuses->find(task_table.name_in_config) != statuses->end()) - break; - (*statuses)[task_table.name_in_config] = StatusAccumulator::TableStatus - { - /*all_partitions_count=*/task_table.ordered_partition_names.size(), - /*processed_partition_count=*/0 - }; - - auto statuses_to_commit = StatusAccumulator::serializeToJSON(statuses); - auto error = zookeeper->trySet(task_zookeeper_path + "/status", statuses_to_commit, stat.version); - if (error == Coordination::Error::ZOK) - break; - } - - - /// An heuristic: if previous shard is already done, then check next one without sleeps due to max_workers constraint - bool previous_shard_is_instantly_finished = false; - - /// Process each partition that is present in cluster - for (const String & partition_name : task_table.ordered_partition_names) - { - if (!task_table.cluster_partitions.contains(partition_name)) - throw Exception(ErrorCodes::LOGICAL_ERROR, "There are no expected partition {}. It is a bug", partition_name); - - ClusterPartition & cluster_partition = task_table.cluster_partitions[partition_name]; - - Stopwatch watch; - /// We will check all the shards of the table and check if they contain current partition. - TasksShard expected_shards; - UInt64 num_failed_shards = 0; - - ++cluster_partition.total_tries; - - LOG_INFO(log, "Processing partition {} for the whole cluster", partition_name); - - /// Process each source shard having current partition and copy current partition - /// NOTE: shards are sorted by "distance" to current host - bool has_shard_to_process = false; - for (const TaskShardPtr & shard : task_table.all_shards) - { - /// Does shard have a node with current partition? - if (!shard->partition_tasks.contains(partition_name)) - { - /// If not, did we check existence of that partition previously? - if (!shard->checked_partitions.contains(partition_name)) - { - auto check_shard_has_partition = [&] () { return checkShardHasPartition(timeouts, *shard, partition_name); }; - bool has_partition = retry(check_shard_has_partition); - - shard->checked_partitions.emplace(partition_name); - - if (has_partition) - { - const size_t number_of_splits = task_table.number_of_splits; - shard->partition_tasks.emplace(partition_name, ShardPartition(*shard, partition_name, number_of_splits)); - LOG_INFO(log, "Discovered partition {} in shard {}", partition_name, shard->getDescription()); - /// To save references in the future. - auto shard_partition_it = shard->partition_tasks.find(partition_name); - PartitionPieces & shard_partition_pieces = shard_partition_it->second.pieces; - - for (size_t piece_number = 0; piece_number < number_of_splits; ++piece_number) - { - auto res = checkPresentPartitionPiecesOnCurrentShard(timeouts, *shard, partition_name, piece_number); - shard_partition_pieces.emplace_back(shard_partition_it->second, piece_number, res); - } - } - else - { - LOG_INFO(log, "Found that shard {} does not contain current partition {}", shard->getDescription(), partition_name); - continue; - } - } - else - { - /// We have already checked that partition, but did not discover it - previous_shard_is_instantly_finished = true; - continue; - } - } - - auto it_shard_partition = shard->partition_tasks.find(partition_name); - /// Previously when we discovered that shard does not contain current partition, we skipped it. - /// At this moment partition have to be present. - if (it_shard_partition == shard->partition_tasks.end()) - throw Exception(ErrorCodes::LOGICAL_ERROR, "There are no such partition in a shard. This is a bug."); - auto & partition = it_shard_partition->second; - - expected_shards.emplace_back(shard); - - /// Do not sleep if there is a sequence of already processed shards to increase startup - bool is_unprioritized_task = !previous_shard_is_instantly_finished && shard->priority.is_remote; - task_status = TaskStatus::Error; - bool was_error = false; - has_shard_to_process = true; - for (UInt64 try_num = 1; try_num <= max_shard_partition_tries; ++try_num) - { - task_status = tryProcessPartitionTask(timeouts, partition, is_unprioritized_task); - - /// Exit if success - if (task_status == TaskStatus::Finished) - break; - - was_error = true; - - /// Skip if the task is being processed by someone - if (task_status == TaskStatus::Active) - break; - - /// Repeat on errors - std::this_thread::sleep_for(retry_delay_ms); - } - - if (task_status == TaskStatus::Error) - ++num_failed_shards; - - previous_shard_is_instantly_finished = !was_error; - } - - cluster_partition.elapsed_time_seconds += watch.elapsedSeconds(); - - /// Check that whole cluster partition is done - /// Firstly check the number of failed partition tasks, then look into ZooKeeper and ensure that each partition is done - bool partition_copying_is_done = num_failed_shards == 0; - try - { - partition_copying_is_done = - !has_shard_to_process - || (partition_copying_is_done && checkAllPiecesInPartitionAreDone(task_table, partition_name, expected_shards)); - } - catch (...) - { - tryLogCurrentException(log); - partition_copying_is_done = false; - } - - - bool partition_moving_is_done = false; - /// Try to move only if all pieces were copied. - if (partition_copying_is_done) - { - for (UInt64 try_num = 0; try_num < max_shard_partition_piece_tries_for_alter; ++try_num) - { - try - { - auto res = tryMoveAllPiecesToDestinationTable(task_table, partition_name); - /// Exit and mark current task is done. - if (res == TaskStatus::Finished) - { - partition_moving_is_done = true; - break; - } - - /// Exit if this task is active. - if (res == TaskStatus::Active) - break; - - /// Repeat on errors. - std::this_thread::sleep_for(retry_delay_ms); - } - catch (...) - { - tryLogCurrentException(log, "Some error occurred while moving pieces to destination table for partition " + partition_name); - } - } - } - - if (partition_copying_is_done && partition_moving_is_done) - { - task_table.finished_cluster_partitions.emplace(partition_name); - - task_table.bytes_copied += cluster_partition.bytes_copied; - task_table.rows_copied += cluster_partition.rows_copied; - double elapsed = cluster_partition.elapsed_time_seconds; - - LOG_INFO(log, "It took {} seconds to copy partition {}: {} uncompressed bytes, {} rows and {} source blocks are copied", - elapsed, partition_name, - formatReadableSizeWithDecimalSuffix(cluster_partition.bytes_copied), - formatReadableQuantity(cluster_partition.rows_copied), - cluster_partition.blocks_copied); - - if (cluster_partition.rows_copied) - { - LOG_INFO(log, "Average partition speed: {} per second.", formatReadableSizeWithDecimalSuffix(cluster_partition.bytes_copied / elapsed)); - } - - if (task_table.rows_copied) - { - LOG_INFO(log, "Average table {} speed: {} per second.", task_table.table_id, formatReadableSizeWithDecimalSuffix(task_table.bytes_copied / elapsed)); - } - } - } - - UInt64 required_partitions = task_table.cluster_partitions.size(); - UInt64 finished_partitions = task_table.finished_cluster_partitions.size(); - bool table_is_done = finished_partitions >= required_partitions; - - if (!table_is_done) - { - LOG_INFO(log, "Table {} is not processed yet. Copied {} of {}, will retry", task_table.table_id, finished_partitions, required_partitions); - } - else - { - /// Delete helping tables in case that whole table is done - dropHelpingTables(task_table); - } - - return table_is_done; -} - -TaskStatus ClusterCopier::tryCreateDestinationTable(const ConnectionTimeouts & timeouts, TaskTable & task_table) -{ - /// Try create original table (if not exists) on each shard - - //TaskTable & task_table = task_shard.task_table; - const TaskShardPtr task_shard = task_table.all_shards.at(0); - /// We need to update table definitions for each part, it could be changed after ALTER - task_shard->current_pull_table_create_query = getCreateTableForPullShard(timeouts, *task_shard); - try - { - auto create_query_push_ast - = rewriteCreateQueryStorage(task_shard->current_pull_table_create_query, task_table.table_push, task_table.engine_push_ast); - auto & create = create_query_push_ast->as(); - create.if_not_exists = true; - InterpreterCreateQuery::prepareOnClusterQuery(create, getContext(), task_table.cluster_push_name); - String query = queryToString(create_query_push_ast); - - LOG_INFO(log, "Create destination tables. Query: {}", query); - UInt64 shards = executeQueryOnCluster(task_table.cluster_push, query, task_cluster->settings_push, ClusterExecutionMode::ON_EACH_NODE); - LOG_INFO( - log, - "Destination tables {} have been created on {} shards of {}", - getQuotedTable(task_table.table_push), - shards, - task_table.cluster_push->getShardCount()); - } - catch (...) - { - tryLogCurrentException(log, "Error while creating original table. Maybe we are not first."); - } - - return TaskStatus::Finished; -} - -/// Job for copying partition from particular shard. -TaskStatus ClusterCopier::tryProcessPartitionTask(const ConnectionTimeouts & timeouts, ShardPartition & task_partition, bool is_unprioritized_task) -{ - TaskStatus res; - - try - { - res = iterateThroughAllPiecesInPartition(timeouts, task_partition, is_unprioritized_task); - } - catch (...) - { - tryLogCurrentException(log, "An error occurred while processing partition " + task_partition.name); - res = TaskStatus::Error; - } - - /// At the end of each task check if the config is updated - try - { - updateConfigIfNeeded(); - } - catch (...) - { - tryLogCurrentException(log, "An error occurred while updating the config"); - } - - return res; -} - -TaskStatus ClusterCopier::iterateThroughAllPiecesInPartition(const ConnectionTimeouts & timeouts, ShardPartition & task_partition, - bool is_unprioritized_task) -{ - const size_t total_number_of_pieces = task_partition.task_shard.task_table.number_of_splits; - - TaskStatus res{TaskStatus::Finished}; - - bool was_failed_pieces = false; - bool was_active_pieces = false; - - for (size_t piece_number = 0; piece_number < total_number_of_pieces; piece_number++) - { - for (UInt64 try_num = 0; try_num < max_shard_partition_tries; ++try_num) - { - LOG_INFO(log, "Attempt number {} to process partition {} piece number {} on shard number {} with index {}.", - try_num, task_partition.name, piece_number, - task_partition.task_shard.numberInCluster(), - task_partition.task_shard.indexInCluster()); - - res = processPartitionPieceTaskImpl(timeouts, task_partition, piece_number, is_unprioritized_task); - - /// Exit if success - if (res == TaskStatus::Finished) - break; - - /// Skip if the task is being processed by someone - if (res == TaskStatus::Active) - break; - - /// Repeat on errors - std::this_thread::sleep_for(retry_delay_ms); - } - - was_active_pieces |= (res == TaskStatus::Active); - was_failed_pieces |= (res == TaskStatus::Error); - } - - if (was_failed_pieces) - return TaskStatus::Error; - - if (was_active_pieces) - return TaskStatus::Active; - - return TaskStatus::Finished; -} - - -TaskStatus ClusterCopier::processPartitionPieceTaskImpl( - const ConnectionTimeouts & timeouts, ShardPartition & task_partition, - const size_t current_piece_number, bool is_unprioritized_task) -{ - TaskShard & task_shard = task_partition.task_shard; - TaskTable & task_table = task_shard.task_table; - ClusterPartition & cluster_partition = task_table.getClusterPartition(task_partition.name); - ShardPartitionPiece & partition_piece = task_partition.pieces[current_piece_number]; - - const size_t number_of_splits = task_table.number_of_splits; - const String primary_key_comma_separated = task_table.primary_key_comma_separated; - - /// We need to update table definitions for each partition, it could be changed after ALTER - createShardInternalTables(timeouts, task_shard, true); - - auto split_table_for_current_piece = task_shard.list_of_split_tables_on_shard[current_piece_number]; - - auto zookeeper = getContext()->getZooKeeper(); - - const String piece_is_dirty_flag_path = partition_piece.getPartitionPieceIsDirtyPath(); - const String piece_is_dirty_cleaned_path = partition_piece.getPartitionPieceIsCleanedPath(); - const String current_task_piece_is_active_path = partition_piece.getActiveWorkerPath(); - const String current_task_piece_status_path = partition_piece.getShardStatusPath(); - - /// Auxiliary functions: - - /// Creates is_dirty node to initialize DROP PARTITION - auto create_is_dirty_node = [&] (const CleanStateClock & clock) - { - if (clock.is_stale()) - LOG_INFO(log, "Clean state clock is stale while setting dirty flag, cowardly bailing"); - else if (!clock.is_clean()) - LOG_INFO(log, "Thank you, Captain Obvious"); - else if (clock.discovery_version) - { - LOG_INFO(log, "Updating clean state clock"); - zookeeper->set(piece_is_dirty_flag_path, host_id, clock.discovery_version.value()); - } - else - { - LOG_INFO(log, "Creating clean state clock"); - zookeeper->create(piece_is_dirty_flag_path, host_id, zkutil::CreateMode::Persistent); - } - }; - - /// Returns SELECT query filtering current partition and applying user filter - auto get_select_query = [&] (const DatabaseAndTableName & from_table, const String & fields, bool enable_splitting, String limit = "") - { - String query; - query += "WITH " + task_partition.name + " AS partition_key "; - query += "SELECT " + fields + " FROM " + getQuotedTable(from_table); - - if (enable_splitting && experimental_use_sample_offset) - query += " SAMPLE 1/" + toString(number_of_splits) + " OFFSET " + toString(current_piece_number) + "/" + toString(number_of_splits); - - /// TODO: Bad, it is better to rewrite with ASTLiteral(partition_key_field) - query += " WHERE (" + queryToString(task_table.engine_push_partition_key_ast) + " = partition_key)"; - - if (enable_splitting && !experimental_use_sample_offset) - query += " AND ( cityHash64(" + primary_key_comma_separated + ") %" + toString(number_of_splits) + " = " + toString(current_piece_number) + " )"; - - if (!task_table.where_condition_str.empty()) - query += " AND (" + task_table.where_condition_str + ")"; - - if (!limit.empty()) - query += " LIMIT " + limit; - - query += " FORMAT Native"; - - ParserQuery p_query(query.data() + query.size()); - - const auto & settings = getContext()->getSettingsRef(); - return parseQuery(p_query, query, settings.max_query_size, settings.max_parser_depth); - }; - - /// Load balancing - auto worker_node_holder = createTaskWorkerNodeAndWaitIfNeed(zookeeper, current_task_piece_status_path, is_unprioritized_task); - - LOG_INFO(log, "Processing {}", current_task_piece_status_path); - - const String piece_status_path = partition_piece.getPartitionPieceShardsPath(); - - CleanStateClock clean_state_clock(zookeeper, piece_is_dirty_flag_path, piece_is_dirty_cleaned_path); - - const bool is_clean = checkPartitionPieceIsClean(zookeeper, clean_state_clock, piece_status_path); - - /// Do not start if partition piece is dirty, try to clean it - if (is_clean) - { - LOG_INFO(log, "Partition {} piece {} appears to be clean", task_partition.name, current_piece_number); - zookeeper->createAncestors(current_task_piece_status_path); - } - else - { - LOG_INFO(log, "Partition {} piece {} is dirty, try to drop it", task_partition.name, current_piece_number); - - try - { - tryDropPartitionPiece(task_partition, current_piece_number, zookeeper, clean_state_clock); - } - catch (...) - { - tryLogCurrentException(log, "An error occurred when clean partition"); - } - - return TaskStatus::Error; - } - - /// Create ephemeral node to mark that we are active and process the partition - zookeeper->createAncestors(current_task_piece_is_active_path); - zkutil::EphemeralNodeHolderPtr partition_task_node_holder; - try - { - partition_task_node_holder = zkutil::EphemeralNodeHolder::create(current_task_piece_is_active_path, *zookeeper, host_id); - } - catch (const Coordination::Exception & e) - { - if (e.code == Coordination::Error::ZNODEEXISTS) - { - LOG_INFO(log, "Someone is already processing {}", current_task_piece_is_active_path); - return TaskStatus::Active; - } - - throw; - } - - /// Exit if task has been already processed; - /// create blocking node to signal cleaning up if it is abandoned - { - String status_data; - if (zookeeper->tryGet(current_task_piece_status_path, status_data)) - { - TaskStateWithOwner status = TaskStateWithOwner::fromString(status_data); - if (status.state == TaskState::Finished) - { - LOG_INFO(log, "Task {} has been successfully executed by {}", current_task_piece_status_path, status.owner); - return TaskStatus::Finished; - } - - /// Task is abandoned, because previously we created ephemeral node, possibly in other copier's process. - /// Initialize DROP PARTITION - LOG_INFO(log, "Task {} has not been successfully finished by {}. Partition will be dropped and refilled.", current_task_piece_status_path, status.owner); - - create_is_dirty_node(clean_state_clock); - return TaskStatus::Error; - } - } - - - /// Try create table (if not exists) on each shard - /// We have to create this table even in case that partition piece is empty - /// This is significant, because we will have simpler code - { - /// 1) Get columns description from any replica of destination cluster - /// 2) Change ENGINE, database and table name - /// 3) Create helping table on the whole destination cluster - auto & settings_push = task_cluster->settings_push; - - auto connection = task_table.cluster_push->getAnyShardInfo().pool->get(timeouts, settings_push, true); - String create_query = getRemoteCreateTable(task_shard.task_table.table_push, *connection, settings_push); - - ParserCreateQuery parser_create_query; - auto create_query_ast = parseQuery(parser_create_query, create_query, settings_push.max_query_size, settings_push.max_parser_depth); - /// Define helping table database and name for current partition piece - DatabaseAndTableName database_and_table_for_current_piece - { - task_table.table_push.first, - task_table.table_push.second + "_piece_" + toString(current_piece_number) - }; - - - auto new_engine_push_ast = task_table.engine_push_ast; - if (task_table.isReplicatedTable()) - new_engine_push_ast = task_table.rewriteReplicatedCreateQueryToPlain(); - - /// Take columns definition from destination table, new database and table name, and new engine (non replicated variant of MergeTree) - auto create_query_push_ast = rewriteCreateQueryStorage(create_query_ast, database_and_table_for_current_piece, new_engine_push_ast); - String query = queryToString(create_query_push_ast); - - LOG_INFO(log, "Create destination tables. Query: {}", query); - UInt64 shards = executeQueryOnCluster(task_table.cluster_push, query, task_cluster->settings_push, ClusterExecutionMode::ON_EACH_NODE); - LOG_INFO( - log, - "Destination tables {} have been created on {} shards of {}", - getQuotedTable(task_table.table_push), - shards, - task_table.cluster_push->getShardCount()); - } - - - /// Exit if current piece is absent on this shard. Also mark it as finished, because we will check - /// whether each shard have processed each partitition (and its pieces). - if (partition_piece.is_absent_piece) - { - String state_finished = TaskStateWithOwner::getData(TaskState::Finished, host_id); - auto res = zookeeper->tryCreate(current_task_piece_status_path, state_finished, zkutil::CreateMode::Persistent); - if (res == Coordination::Error::ZNODEEXISTS) - LOG_INFO(log, "Partition {} piece {} is absent on current replica of a shard. But other replicas have already marked it as done.", task_partition.name, current_piece_number); - if (res == Coordination::Error::ZOK) - LOG_INFO(log, "Partition {} piece {} is absent on current replica of a shard. Will mark it as done. Other replicas will do the same.", task_partition.name, current_piece_number); - return TaskStatus::Finished; - } - - /// Check that destination partition is empty if we are first worker - /// NOTE: this check is incorrect if pull and push tables have different partition key! - String clean_start_status; - if (!zookeeper->tryGet(partition_piece.getPartitionPieceCleanStartPath(), clean_start_status) || clean_start_status != "ok") - { - zookeeper->createIfNotExists(partition_piece.getPartitionPieceCleanStartPath(), ""); - auto checker = zkutil::EphemeralNodeHolder::create(partition_piece.getPartitionPieceCleanStartPath() + "/checker", - *zookeeper, host_id); - // Maybe we are the first worker - - ASTPtr query_select_ast = get_select_query(split_table_for_current_piece, "count()", /* enable_splitting= */ true); - UInt64 count; - { - auto local_context = Context::createCopy(context); - // Use pull (i.e. readonly) settings, but fetch data from destination servers - local_context->setSettings(task_cluster->settings_pull); - local_context->setSetting("skip_unavailable_shards", true); - - InterpreterSelectWithUnionQuery select(query_select_ast, local_context, SelectQueryOptions{}); - QueryPlan plan; - select.buildQueryPlan(plan); - auto builder = std::move(*plan.buildQueryPipeline( - QueryPlanOptimizationSettings::fromContext(local_context), - BuildQueryPipelineSettings::fromContext(local_context))); - - Block block = getBlockWithAllStreamData(std::move(builder)); - count = (block) ? block.safeGetByPosition(0).column->getUInt(0) : 0; - } - - if (count != 0) - { - LOG_INFO(log, "Partition {} piece {} is not empty. In contains {} rows.", task_partition.name, current_piece_number, count); - Coordination::Stat stat_shards{}; - zookeeper->get(partition_piece.getPartitionPieceShardsPath(), &stat_shards); - - /// NOTE: partition is still fresh if dirt discovery happens before cleaning - if (stat_shards.numChildren == 0) - { - LOG_WARNING(log, "There are no workers for partition {} piece {}, but destination table contains {} rows. Partition will be dropped and refilled.", task_partition.name, toString(current_piece_number), count); - - create_is_dirty_node(clean_state_clock); - return TaskStatus::Error; - } - } - zookeeper->set(partition_piece.getPartitionPieceCleanStartPath(), "ok"); - } - /// At this point, we need to sync that the destination table is clean - /// before any actual work - - /// Try start processing, create node about it - { - String start_state = TaskStateWithOwner::getData(TaskState::Started, host_id); - CleanStateClock new_clean_state_clock(zookeeper, piece_is_dirty_flag_path, piece_is_dirty_cleaned_path); - if (clean_state_clock != new_clean_state_clock) - { - LOG_INFO(log, "Partition {} piece {} clean state changed, cowardly bailing", task_partition.name, toString(current_piece_number)); - return TaskStatus::Error; - } - else if (!new_clean_state_clock.is_clean()) - { - LOG_INFO(log, "Partition {} piece {} is dirty and will be dropped and refilled", task_partition.name, toString(current_piece_number)); - create_is_dirty_node(new_clean_state_clock); - return TaskStatus::Error; - } - zookeeper->create(current_task_piece_status_path, start_state, zkutil::CreateMode::Persistent); - } - - - /// Do the copying - { - bool inject_fault = false; - if (copy_fault_probability > 0) - { - double value = std::uniform_real_distribution<>(0, 1)(task_table.task_cluster.random_engine); - inject_fault = value < copy_fault_probability; - } - - // Select all fields - ASTPtr query_select_ast = get_select_query(task_shard.table_read_shard, "*", /* enable_splitting= */ true, inject_fault ? "1" : ""); - - LOG_INFO(log, "Executing SELECT query and pull from {}: {}", task_shard.getDescription(), queryToString(query_select_ast)); - - ASTPtr query_insert_ast; - { - String query; - query += "INSERT INTO " + getQuotedTable(split_table_for_current_piece) + " FORMAT Native "; - - ParserQuery p_query(query.data() + query.size()); - const auto & settings = getContext()->getSettingsRef(); - query_insert_ast = parseQuery(p_query, query, settings.max_query_size, settings.max_parser_depth); - - LOG_INFO(log, "Executing INSERT query: {}", query); - } - - try - { - auto context_select = Context::createCopy(context); - context_select->setSettings(task_cluster->settings_pull); - - auto context_insert = Context::createCopy(context); - context_insert->setSettings(task_cluster->settings_push); - - /// Custom INSERT SELECT implementation - QueryPipeline input; - QueryPipeline output; - { - BlockIO io_insert = InterpreterFactory::instance().get(query_insert_ast, context_insert)->execute(); - - InterpreterSelectWithUnionQuery select(query_select_ast, context_select, SelectQueryOptions{}); - QueryPlan plan; - select.buildQueryPlan(plan); - auto builder = std::move(*plan.buildQueryPipeline( - QueryPlanOptimizationSettings::fromContext(context_select), - BuildQueryPipelineSettings::fromContext(context_select))); - - output = std::move(io_insert.pipeline); - - /// Add converting actions to make it possible to copy blocks with slightly different schema - const auto & select_block = builder.getHeader(); - const auto & insert_block = output.getHeader(); - auto actions_dag = ActionsDAG::makeConvertingActions( - select_block.getColumnsWithTypeAndName(), - insert_block.getColumnsWithTypeAndName(), - ActionsDAG::MatchColumnsMode::Position); - - auto actions = std::make_shared(actions_dag, ExpressionActionsSettings::fromContext(getContext())); - - builder.addSimpleTransform([&](const Block & header) - { - return std::make_shared(header, actions); - }); - input = QueryPipelineBuilder::getPipeline(std::move(builder)); - } - - /// Fail-fast optimization to abort copying when the current clean state expires - std::future future_is_dirty_checker; - - Stopwatch watch(CLOCK_MONOTONIC_COARSE); - constexpr UInt64 check_period_milliseconds = 500; - - /// Will asynchronously check that ZooKeeper connection and is_dirty flag appearing while copying data - auto cancel_check = [&] () - { - if (zookeeper->expired()) - throw Exception(ErrorCodes::UNFINISHED, "ZooKeeper session is expired, cancel INSERT SELECT"); - - if (!future_is_dirty_checker.valid()) - future_is_dirty_checker = zookeeper->asyncExists(piece_is_dirty_flag_path); - - /// check_period_milliseconds should less than average insert time of single block - /// Otherwise, the insertion will slow a little bit - if (watch.elapsedMilliseconds() >= check_period_milliseconds) - { - Coordination::ExistsResponse status = future_is_dirty_checker.get(); - - if (status.error != Coordination::Error::ZNONODE) - { - LogicalClock dirt_discovery_epoch (status.stat.mzxid); - if (dirt_discovery_epoch == clean_state_clock.discovery_zxid) - return false; - throw Exception(ErrorCodes::UNFINISHED, "Partition is dirty, cancel INSERT SELECT"); - } - } - - return false; - }; - - /// Update statistics - /// It is quite rough: bytes_copied don't take into account DROP PARTITION. - auto update_stats = [&cluster_partition] (const Block & block) - { - cluster_partition.bytes_copied += block.bytes(); - cluster_partition.rows_copied += block.rows(); - cluster_partition.blocks_copied += 1; - }; - - /// Main work is here - PullingPipelineExecutor pulling_executor(input); - PushingPipelineExecutor pushing_executor(output); - - Block data; - bool is_cancelled = false; - while (pulling_executor.pull(data)) - { - if (cancel_check()) - { - is_cancelled = true; - pushing_executor.cancel(); - pushing_executor.cancel(); - break; - } - pushing_executor.push(data); - update_stats(data); - } - - if (!is_cancelled) - pushing_executor.finish(); - - // Just in case - if (future_is_dirty_checker.valid()) - future_is_dirty_checker.get(); - - if (inject_fault) - throw Exception(ErrorCodes::UNFINISHED, "Copy fault injection is activated"); - } - catch (...) - { - tryLogCurrentException(log, "An error occurred during copying, partition will be marked as dirty"); - create_is_dirty_node(clean_state_clock); - return TaskStatus::Error; - } - } - - LOG_INFO(log, "Partition {} piece {} copied. But not moved to original destination table.", task_partition.name, toString(current_piece_number)); - - /// Finalize the processing, change state of current partition task (and also check is_dirty flag) - { - String state_finished = TaskStateWithOwner::getData(TaskState::Finished, host_id); - CleanStateClock new_clean_state_clock (zookeeper, piece_is_dirty_flag_path, piece_is_dirty_cleaned_path); - if (clean_state_clock != new_clean_state_clock) - { - LOG_INFO(log, "Partition {} piece {} clean state changed, cowardly bailing", task_partition.name, toString(current_piece_number)); - return TaskStatus::Error; - } - else if (!new_clean_state_clock.is_clean()) - { - LOG_INFO(log, "Partition {} piece {} became dirty and will be dropped and refilled", task_partition.name, toString(current_piece_number)); - create_is_dirty_node(new_clean_state_clock); - return TaskStatus::Error; - } - zookeeper->set(current_task_piece_status_path, state_finished, 0); - } - - return TaskStatus::Finished; -} - -void ClusterCopier::dropAndCreateLocalTable(const ASTPtr & create_ast) -{ - const auto & create = create_ast->as(); - dropLocalTableIfExists({create.getDatabase(), create.getTable()}); - - auto create_context = Context::createCopy(getContext()); - - InterpreterCreateQuery interpreter(create_ast, create_context); - interpreter.execute(); -} - -void ClusterCopier::dropLocalTableIfExists(const DatabaseAndTableName & table_name) const -{ - auto drop_ast = std::make_shared(); - drop_ast->if_exists = true; - drop_ast->setDatabase(table_name.first); - drop_ast->setTable(table_name.second); - - auto drop_context = Context::createCopy(getContext()); - - InterpreterDropQuery interpreter(drop_ast, drop_context); - interpreter.execute(); -} - -void ClusterCopier::dropHelpingTablesByPieceNumber(const TaskTable & task_table, size_t current_piece_number) -{ - LOG_INFO(log, "Removing helping tables piece {}", current_piece_number); - - DatabaseAndTableName original_table = task_table.table_push; - DatabaseAndTableName helping_table - = DatabaseAndTableName(original_table.first, original_table.second + "_piece_" + toString(current_piece_number)); - - String query = "DROP TABLE IF EXISTS " + getQuotedTable(helping_table); - - const ClusterPtr & cluster_push = task_table.cluster_push; - Settings settings_push = task_cluster->settings_push; - - LOG_INFO(log, "Execute distributed DROP TABLE: {}", query); - - /// We have to drop partition_piece on each replica - UInt64 num_nodes = executeQueryOnCluster(cluster_push, query, settings_push, ClusterExecutionMode::ON_EACH_NODE); - - LOG_INFO(log, "DROP TABLE query was successfully executed on {} nodes.", toString(num_nodes)); -} - -void ClusterCopier::dropHelpingTables(const TaskTable & task_table) -{ - LOG_INFO(log, "Removing helping tables"); - for (size_t current_piece_number = 0; current_piece_number < task_table.number_of_splits; ++current_piece_number) - { - dropHelpingTablesByPieceNumber(task_table, current_piece_number); - } -} - -void ClusterCopier::dropParticularPartitionPieceFromAllHelpingTables(const TaskTable & task_table, const String & partition_name) -{ - LOG_INFO(log, "Try drop partition partition from all helping tables."); - for (size_t current_piece_number = 0; current_piece_number < task_table.number_of_splits; ++current_piece_number) - { - DatabaseAndTableName original_table = task_table.table_push; - DatabaseAndTableName helping_table = DatabaseAndTableName(original_table.first, original_table.second + "_piece_" + toString(current_piece_number)); - - String query = "ALTER TABLE " + getQuotedTable(helping_table) + ((partition_name == "'all'") ? " DROP PARTITION ID " : " DROP PARTITION ") + partition_name; - - const ClusterPtr & cluster_push = task_table.cluster_push; - Settings settings_push = task_cluster->settings_push; - - LOG_INFO(log, "Execute distributed DROP PARTITION: {}", query); - /// We have to drop partition_piece on each replica - UInt64 num_nodes = executeQueryOnCluster( - cluster_push, query, - settings_push, - ClusterExecutionMode::ON_EACH_NODE); - - LOG_INFO(log, "DROP PARTITION query was successfully executed on {} nodes.", toString(num_nodes)); - } - LOG_INFO(log, "All helping tables dropped partition {}", partition_name); -} - -String ClusterCopier::getRemoteCreateTable(const DatabaseAndTableName & table, Connection & connection, const Settings & settings) -{ - auto remote_context = Context::createCopy(context); - remote_context->setSettings(settings); - - String query = "SHOW CREATE TABLE " + getQuotedTable(table); - - QueryPipelineBuilder builder; - builder.init(Pipe(std::make_shared( - std::make_shared(connection, query, InterpreterShowCreateQuery::getSampleBlock(), remote_context), false, false, /* async_query_sending= */ false))); - Block block = getBlockWithAllStreamData(std::move(builder)); - return typeid_cast(*block.safeGetByPosition(0).column).getDataAt(0).toString(); -} - - -ASTPtr ClusterCopier::getCreateTableForPullShard(const ConnectionTimeouts & timeouts, TaskShard & task_shard) -{ - /// Fetch and parse (possibly) new definition - auto connection_entry = task_shard.info.pool->get(timeouts, task_cluster->settings_pull, true); - String create_query_pull_str = getRemoteCreateTable( - task_shard.task_table.table_pull, - *connection_entry, - task_cluster->settings_pull); - - ParserCreateQuery parser_create_query; - const auto & settings = getContext()->getSettingsRef(); - return parseQuery(parser_create_query, create_query_pull_str, settings.max_query_size, settings.max_parser_depth); -} - - -/// If it is implicitly asked to create split Distributed table for certain piece on current shard, we will do it. -void ClusterCopier::createShardInternalTables(const ConnectionTimeouts & timeouts, - TaskShard & task_shard, bool create_split) -{ - TaskTable & task_table = task_shard.task_table; - - /// We need to update table definitions for each part, it could be changed after ALTER - task_shard.current_pull_table_create_query = getCreateTableForPullShard(timeouts, task_shard); - - /// Create local Distributed tables: - /// a table fetching data from current shard and a table inserting data to the whole destination cluster - String read_shard_prefix = ".read_shard_" + toString(task_shard.indexInCluster()) + "."; - String split_shard_prefix = ".split."; - task_shard.table_read_shard = DatabaseAndTableName(working_database_name, read_shard_prefix + task_table.table_id); - task_shard.main_table_split_shard = DatabaseAndTableName(working_database_name, split_shard_prefix + task_table.table_id); - - for (const auto & piece_number : collections::range(0, task_table.number_of_splits)) - { - task_shard.list_of_split_tables_on_shard[piece_number] = - DatabaseAndTableName(working_database_name, split_shard_prefix + task_table.table_id + "_piece_" + toString(piece_number)); - } - - /// Create special cluster with single shard - String shard_read_cluster_name = read_shard_prefix + task_table.cluster_pull_name; - ClusterPtr cluster_pull_current_shard = task_table.cluster_pull->getClusterWithSingleShard(task_shard.indexInCluster()); - getContext()->setCluster(shard_read_cluster_name, cluster_pull_current_shard); - - auto storage_shard_ast = createASTStorageDistributed(shard_read_cluster_name, task_table.table_pull.first, task_table.table_pull.second); - - auto create_query_ast = removeAliasMaterializedAndTTLColumnsFromCreateQuery( - task_shard.current_pull_table_create_query, - task_table.allow_to_copy_alias_and_materialized_columns); - - auto create_table_pull_ast = rewriteCreateQueryStorage(create_query_ast, task_shard.table_read_shard, storage_shard_ast); - dropAndCreateLocalTable(create_table_pull_ast); - - if (create_split) - { - auto create_table_split_piece_ast = rewriteCreateQueryStorage( - create_query_ast, - task_shard.main_table_split_shard, - task_table.main_engine_split_ast); - - dropAndCreateLocalTable(create_table_split_piece_ast); - - /// Create auxiliary split tables for each piece - for (const auto & piece_number : collections::range(0, task_table.number_of_splits)) - { - const auto & storage_piece_split_ast = task_table.auxiliary_engine_split_asts[piece_number]; - - create_table_split_piece_ast = rewriteCreateQueryStorage( - create_query_ast, - task_shard.list_of_split_tables_on_shard[piece_number], - storage_piece_split_ast); - - dropAndCreateLocalTable(create_table_split_piece_ast); - } - } - -} - - -std::set ClusterCopier::getShardPartitions(const ConnectionTimeouts & timeouts, TaskShard & task_shard) -{ - std::set res; - - createShardInternalTables(timeouts, task_shard, false); - - TaskTable & task_table = task_shard.task_table; - - const String & partition_name = queryToString(task_table.engine_push_partition_key_ast); - - if (partition_name == "'all'") - { - res.emplace("'all'"); - return res; - } - - String query; - { - WriteBufferFromOwnString wb; - wb << "SELECT " << partition_name << " AS partition FROM " - << getQuotedTable(task_shard.table_read_shard) << " GROUP BY partition ORDER BY partition DESC"; - query = wb.str(); - } - - ParserQuery parser_query(query.data() + query.size()); - const auto & settings = getContext()->getSettingsRef(); - ASTPtr query_ast = parseQuery(parser_query, query, settings.max_query_size, settings.max_parser_depth); - - LOG_INFO(log, "Computing destination partition set, executing query: {}", query); - - auto local_context = Context::createCopy(context); - local_context->setSettings(task_cluster->settings_pull); - InterpreterSelectWithUnionQuery select(query_ast, local_context, SelectQueryOptions{}); - QueryPlan plan; - select.buildQueryPlan(plan); - auto builder = std::move(*plan.buildQueryPipeline( - QueryPlanOptimizationSettings::fromContext(local_context), - BuildQueryPipelineSettings::fromContext(local_context))); - - Block block = getBlockWithAllStreamData(std::move(builder)); - - if (block) - { - ColumnWithTypeAndName & column = block.getByPosition(0); - task_shard.partition_key_column = column; - - for (size_t i = 0; i < column.column->size(); ++i) - { - WriteBufferFromOwnString wb; - column.type->getDefaultSerialization()->serializeTextQuoted(*column.column, i, wb, FormatSettings()); - res.emplace(wb.str()); - } - } - - LOG_INFO(log, "There are {} destination partitions in shard {}", res.size(), task_shard.getDescription()); - - return res; -} - -bool ClusterCopier::checkShardHasPartition(const ConnectionTimeouts & timeouts, - TaskShard & task_shard, const String & partition_quoted_name) -{ - createShardInternalTables(timeouts, task_shard, false); - - TaskTable & task_table = task_shard.task_table; - - WriteBufferFromOwnString ss; - ss << "WITH " + partition_quoted_name + " AS partition_key "; - ss << "SELECT 1 FROM " << getQuotedTable(task_shard.table_read_shard); - ss << " WHERE (" << queryToString(task_table.engine_push_partition_key_ast) << " = partition_key)"; - if (!task_table.where_condition_str.empty()) - ss << " AND (" << task_table.where_condition_str << ")"; - ss << " LIMIT 1"; - auto query = ss.str(); - - ParserQuery parser_query(query.data() + query.size()); - const auto & settings = getContext()->getSettingsRef(); - ASTPtr query_ast = parseQuery(parser_query, query, settings.max_query_size, settings.max_parser_depth); - - LOG_INFO(log, "Checking shard {} for partition {} existence, executing query: {}", - task_shard.getDescription(), partition_quoted_name, query_ast->formatForErrorMessage()); - - auto local_context = Context::createCopy(context); - local_context->setSettings(task_cluster->settings_pull); - auto pipeline = InterpreterFactory::instance().get(query_ast, local_context)->execute().pipeline; - PullingPipelineExecutor executor(pipeline); - Block block; - executor.pull(block); - return block.rows() != 0; -} - -bool ClusterCopier::checkPresentPartitionPiecesOnCurrentShard(const ConnectionTimeouts & timeouts, - TaskShard & task_shard, const String & partition_quoted_name, size_t current_piece_number) -{ - createShardInternalTables(timeouts, task_shard, false); - - TaskTable & task_table = task_shard.task_table; - const size_t number_of_splits = task_table.number_of_splits; - const String & primary_key_comma_separated = task_table.primary_key_comma_separated; - - UNUSED(primary_key_comma_separated); - - std::string query; - - query += "WITH " + partition_quoted_name + " AS partition_key "; - query += "SELECT 1 FROM " + getQuotedTable(task_shard.table_read_shard); - - if (experimental_use_sample_offset) - query += " SAMPLE 1/" + toString(number_of_splits) + " OFFSET " + toString(current_piece_number) + "/" + toString(number_of_splits); - - query += " WHERE (" + queryToString(task_table.engine_push_partition_key_ast) + " = partition_key)"; - - if (!experimental_use_sample_offset) - query += " AND (cityHash64(" + primary_key_comma_separated + ") % " - + std::to_string(number_of_splits) + " = " + std::to_string(current_piece_number) + " )"; - - if (!task_table.where_condition_str.empty()) - query += " AND (" + task_table.where_condition_str + ")"; - - query += " LIMIT 1"; - - LOG_INFO(log, "Checking shard {} for partition {} piece {} existence, executing query: {}", task_shard.getDescription(), partition_quoted_name, std::to_string(current_piece_number), query); - - ParserQuery parser_query(query.data() + query.size()); - const auto & settings = getContext()->getSettingsRef(); - ASTPtr query_ast = parseQuery(parser_query, query, settings.max_query_size, settings.max_parser_depth); - - auto local_context = Context::createCopy(context); - local_context->setSettings(task_cluster->settings_pull); - auto pipeline = InterpreterFactory::instance().get(query_ast, local_context)->execute().pipeline; - PullingPipelineExecutor executor(pipeline); - Block result; - executor.pull(result); - if (result.rows() != 0) - LOG_INFO(log, "Partition {} piece number {} is PRESENT on shard {}", partition_quoted_name, std::to_string(current_piece_number), task_shard.getDescription()); - else - LOG_INFO(log, "Partition {} piece number {} is ABSENT on shard {}", partition_quoted_name, std::to_string(current_piece_number), task_shard.getDescription()); - return result.rows() != 0; -} - - -/** Executes simple query (without output streams, for example DDL queries) on each shard of the cluster - * Returns number of shards for which at least one replica executed query successfully - */ -UInt64 ClusterCopier::executeQueryOnCluster( - const ClusterPtr & cluster, - const String & query, - const Settings & current_settings, - ClusterExecutionMode execution_mode) const -{ - ClusterPtr cluster_for_query = cluster; - if (execution_mode == ClusterExecutionMode::ON_EACH_NODE) - cluster_for_query = cluster->getClusterWithReplicasAsShards(current_settings); - - std::vector> connections; - connections.reserve(cluster->getShardCount()); - - std::atomic successfully_executed = 0; - - for (const auto & replicas : cluster_for_query->getShardsAddresses()) - { - for (const auto & node : replicas) - { - try - { - connections.emplace_back(std::make_shared( - node.host_name, node.port, node.default_database, - node.user, node.password, ssh::SSHKey(), node.quota_key, node.cluster, node.cluster_secret, - "ClusterCopier", node.compression, node.secure - )); - - /// We execute only Alter, Create and Drop queries. - const auto header = Block{}; - - /// For unknown reason global context is passed to IStorage::read() method - /// So, task_identifier is passed as constructor argument. It is more obvious. - auto remote_query_executor = std::make_shared( - *connections.back(), query, header, getContext(), - /*throttler=*/nullptr, Scalars(), Tables(), QueryProcessingStage::Complete); - - try - { - remote_query_executor->sendQuery(); - } - catch (...) - { - LOG_WARNING(log, "Node with address {} seems to be unreachable.", node.host_name); - continue; - } - - while (true) - { - auto block = remote_query_executor->readBlock(); - if (!block) - break; - } - - remote_query_executor->finish(); - ++successfully_executed; - break; - } - catch (...) - { - LOG_WARNING(log, "An error occurred while processing query: {}", query); - tryLogCurrentException(log); - continue; - } - } - } - - return successfully_executed.load(); -} - -} diff --git a/programs/copier/ClusterCopier.h b/programs/copier/ClusterCopier.h deleted file mode 100644 index 01f8b30f546..00000000000 --- a/programs/copier/ClusterCopier.h +++ /dev/null @@ -1,240 +0,0 @@ -#pragma once - -#include "Aliases.h" -#include "Internals.h" -#include "TaskCluster.h" -#include "TaskShard.h" -#include "TaskTable.h" -#include "ShardPartition.h" -#include "ShardPartitionPiece.h" -#include "ZooKeeperStaff.h" - - -namespace DB -{ - -class ClusterCopier : WithMutableContext -{ -public: - ClusterCopier(const String & task_path_, - const String & host_id_, - const String & proxy_database_name_, - ContextMutablePtr context_, - LoggerRawPtr log_) - : WithMutableContext(context_), - task_zookeeper_path(task_path_), - host_id(host_id_), - working_database_name(proxy_database_name_), - log(log_) {} - - void init(); - - template - decltype(auto) retry(T && func, UInt64 max_tries = 100); - - void discoverShardPartitions(const ConnectionTimeouts & timeouts, const TaskShardPtr & task_shard); - - /// Compute set of partitions, assume set of partitions aren't changed during the processing - void discoverTablePartitions(const ConnectionTimeouts & timeouts, TaskTable & task_table, UInt64 num_threads = 0); - - void uploadTaskDescription(const std::string & task_path, const std::string & task_file, bool force); - - void reloadTaskDescription(); - - void updateConfigIfNeeded(); - - void process(const ConnectionTimeouts & timeouts); - - /// Disables DROP PARTITION commands that used to clear data after errors - void setSafeMode(bool is_safe_mode_ = true) - { - is_safe_mode = is_safe_mode_; - } - - void setCopyFaultProbability(double copy_fault_probability_) - { - copy_fault_probability = copy_fault_probability_; - } - - void setMoveFaultProbability(double move_fault_probability_) - { - move_fault_probability = move_fault_probability_; - } - - void setExperimentalUseSampleOffset(bool value) - { - experimental_use_sample_offset = value; - } - - void setMaxTableTries(UInt64 tries) - { - max_table_tries = tries; - } - void setMaxShardPartitionTries(UInt64 tries) - { - max_shard_partition_tries = tries; - } - void setMaxShardPartitionPieceTriesForAlter(UInt64 tries) - { - max_shard_partition_piece_tries_for_alter = tries; - } - void setRetryDelayMs(std::chrono::milliseconds ms) - { - retry_delay_ms = ms; - } - -protected: - - String getWorkersPath() const - { - return task_cluster->task_zookeeper_path + "/task_active_workers"; - } - - String getWorkersPathVersion() const - { - return getWorkersPath() + "_version"; - } - - String getCurrentWorkerNodePath() const - { - return getWorkersPath() + "/" + host_id; - } - - zkutil::EphemeralNodeHolder::Ptr createTaskWorkerNodeAndWaitIfNeed( - const zkutil::ZooKeeperPtr & zookeeper, - const String & description, - bool unprioritized); - - /* - * Checks that partition piece or some other entity is clean. - * The only requirement is that you have to pass is_dirty_flag_path and is_dirty_cleaned_path to the function. - * And is_dirty_flag_path is a parent of is_dirty_cleaned_path. - * */ - static bool checkPartitionPieceIsClean( - const zkutil::ZooKeeperPtr & zookeeper, - const CleanStateClock & clean_state_clock, - const String & task_status_path); - - bool checkAllPiecesInPartitionAreDone(const TaskTable & task_table, const String & partition_name, const TasksShard & shards_with_partition); - - /** Checks that the whole partition of a table was copied. We should do it carefully due to dirty lock. - * State of some task could change during the processing. - * We have to ensure that all shards have the finished state and there is no dirty flag. - * Moreover, we have to check status twice and check zxid, because state can change during the checking. - */ - - /* The same as function above - * Assume that we don't know on which shards do we have partition certain piece. - * We'll check them all (I mean shards that contain the whole partition) - * And shards that don't have certain piece MUST mark that piece is_done true. - * */ - bool checkPartitionPieceIsDone(const TaskTable & task_table, const String & partition_name, - size_t piece_number, const TasksShard & shards_with_partition); - - - /*Alter successful insertion to helping tables it will move all pieces to destination table*/ - TaskStatus tryMoveAllPiecesToDestinationTable(const TaskTable & task_table, const String & partition_name); - - /// Removes MATERIALIZED and ALIAS columns from create table query - static ASTPtr removeAliasMaterializedAndTTLColumnsFromCreateQuery(const ASTPtr & query_ast, bool allow_to_copy_alias_and_materialized_columns); - - bool tryDropPartitionPiece(ShardPartition & task_partition, size_t current_piece_number, - const zkutil::ZooKeeperPtr & zookeeper, const CleanStateClock & clean_state_clock); - - bool tryProcessTable(const ConnectionTimeouts & timeouts, TaskTable & task_table); - - TaskStatus tryCreateDestinationTable(const ConnectionTimeouts & timeouts, TaskTable & task_table); - /// Job for copying partition from particular shard. - TaskStatus tryProcessPartitionTask(const ConnectionTimeouts & timeouts, - ShardPartition & task_partition, - bool is_unprioritized_task); - - TaskStatus iterateThroughAllPiecesInPartition(const ConnectionTimeouts & timeouts, - ShardPartition & task_partition, - bool is_unprioritized_task); - - TaskStatus processPartitionPieceTaskImpl(const ConnectionTimeouts & timeouts, - ShardPartition & task_partition, - size_t current_piece_number, - bool is_unprioritized_task); - - void dropAndCreateLocalTable(const ASTPtr & create_ast); - - void dropLocalTableIfExists(const DatabaseAndTableName & table_name) const; - - void dropHelpingTables(const TaskTable & task_table); - - void dropHelpingTablesByPieceNumber(const TaskTable & task_table, size_t current_piece_number); - - /// Is used for usage less disk space. - /// After all pieces were successfully moved to original destination - /// table we can get rid of partition pieces (partitions in helping tables). - void dropParticularPartitionPieceFromAllHelpingTables(const TaskTable & task_table, const String & partition_name); - - String getRemoteCreateTable(const DatabaseAndTableName & table, Connection & connection, const Settings & settings); - - ASTPtr getCreateTableForPullShard(const ConnectionTimeouts & timeouts, TaskShard & task_shard); - - /// If it is implicitly asked to create split Distributed table for certain piece on current shard, we will do it. - void createShardInternalTables(const ConnectionTimeouts & timeouts, TaskShard & task_shard, bool create_split = true); - - std::set getShardPartitions(const ConnectionTimeouts & timeouts, TaskShard & task_shard); - - bool checkShardHasPartition(const ConnectionTimeouts & timeouts, TaskShard & task_shard, const String & partition_quoted_name); - - bool checkPresentPartitionPiecesOnCurrentShard(const ConnectionTimeouts & timeouts, - TaskShard & task_shard, const String & partition_quoted_name, size_t current_piece_number); - - /* - * This class is used in executeQueryOnCluster function - * You can execute query on each shard (no sense it is executed on each replica of a shard or not) - * or you can execute query on each replica on each shard. - * First mode is useful for INSERTS queries. - * */ - enum ClusterExecutionMode - { - ON_EACH_SHARD, - ON_EACH_NODE - }; - - /** Executes simple query (without output streams, for example DDL queries) on each shard of the cluster - * Returns number of shards for which at least one replica executed query successfully - */ - UInt64 executeQueryOnCluster( - const ClusterPtr & cluster, - const String & query, - const Settings & current_settings, - ClusterExecutionMode execution_mode = ClusterExecutionMode::ON_EACH_SHARD) const; - -private: - String task_zookeeper_path; - String task_description_path; - String host_id; - String working_database_name; - - /// Auto update config stuff - UInt64 task_description_current_version = 1; - std::atomic task_description_version{1}; - Coordination::WatchCallback task_description_watch_callback; - /// ZooKeeper session used to set the callback - zkutil::ZooKeeperPtr task_description_watch_zookeeper; - - ConfigurationPtr task_cluster_initial_config; - ConfigurationPtr task_cluster_current_config; - - std::unique_ptr task_cluster; - - bool is_safe_mode = false; - double copy_fault_probability = 0.0; - double move_fault_probability = 0.0; - - bool experimental_use_sample_offset{false}; - - LoggerRawPtr log; - - UInt64 max_table_tries = 3; - UInt64 max_shard_partition_tries = 3; - UInt64 max_shard_partition_piece_tries_for_alter = 10; - std::chrono::milliseconds retry_delay_ms{1000}; -}; -} diff --git a/programs/copier/ClusterCopierApp.cpp b/programs/copier/ClusterCopierApp.cpp deleted file mode 100644 index fdf07dec61a..00000000000 --- a/programs/copier/ClusterCopierApp.cpp +++ /dev/null @@ -1,252 +0,0 @@ -#include "ClusterCopierApp.h" -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -namespace fs = std::filesystem; - -namespace DB -{ - -/// ClusterCopierApp - -void ClusterCopierApp::initialize(Poco::Util::Application & self) -{ - is_help = config().has("help"); - if (is_help) - return; - - config_xml_path = config().getString("config-file"); - task_path = config().getString("task-path"); - log_level = config().getString("log-level", "info"); - is_safe_mode = config().has("safe-mode"); - is_status_mode = config().has("status"); - if (config().has("copy-fault-probability")) - copy_fault_probability = std::max(std::min(config().getDouble("copy-fault-probability"), 1.0), 0.0); - if (config().has("move-fault-probability")) - move_fault_probability = std::max(std::min(config().getDouble("move-fault-probability"), 1.0), 0.0); - base_dir = (config().has("base-dir")) ? config().getString("base-dir") : fs::current_path().string(); - - max_table_tries = std::max(config().getUInt("max-table-tries", 3), 1); - max_shard_partition_tries = std::max(config().getUInt("max-shard-partition-tries", 3), 1); - max_shard_partition_piece_tries_for_alter = std::max(config().getUInt("max-shard-partition-piece-tries-for-alter", 10), 1); - retry_delay_ms = std::chrono::milliseconds(std::max(config().getUInt("retry-delay-ms", 1000), 100)); - - if (config().has("experimental-use-sample-offset")) - experimental_use_sample_offset = config().getBool("experimental-use-sample-offset"); - - // process_id is '#_' - time_t timestamp = Poco::Timestamp().epochTime(); - auto curr_pid = Poco::Process::id(); - - process_id = std::to_string(DateLUT::serverTimezoneInstance().toNumYYYYMMDDhhmmss(timestamp)) + "_" + std::to_string(curr_pid); - host_id = escapeForFileName(getFQDNOrHostName()) + '#' + process_id; - process_path = fs::weakly_canonical(fs::path(base_dir) / ("clickhouse-copier_" + process_id)); - fs::create_directories(process_path); - - /// Override variables for BaseDaemon - if (config().has("log-level")) - config().setString("logger.level", config().getString("log-level")); - - if (config().has("base-dir") || !config().has("logger.log")) - config().setString("logger.log", fs::path(process_path) / "log.log"); - - if (config().has("base-dir") || !config().has("logger.errorlog")) - config().setString("logger.errorlog", fs::path(process_path) / "log.err.log"); - - Base::initialize(self); -} - - -void ClusterCopierApp::handleHelp(const std::string &, const std::string &) -{ - uint16_t terminal_width = 0; - if (isatty(STDIN_FILENO)) - terminal_width = getTerminalWidth(); - - Poco::Util::HelpFormatter help_formatter(options()); - if (terminal_width) - help_formatter.setWidth(terminal_width); - help_formatter.setCommand(commandName()); - help_formatter.setHeader("Copies tables from one cluster to another"); - help_formatter.setUsage("--config-file --task-path "); - help_formatter.format(std::cerr); - help_formatter.setFooter("See also: https://clickhouse.com/docs/en/operations/utilities/clickhouse-copier/"); - - stopOptionsProcessing(); -} - - -void ClusterCopierApp::defineOptions(Poco::Util::OptionSet & options) -{ - Base::defineOptions(options); - - options.addOption(Poco::Util::Option("task-path", "", "path to task in ZooKeeper") - .argument("task-path").binding("task-path")); - options.addOption(Poco::Util::Option("task-file", "", "path to task file for uploading in ZooKeeper to task-path") - .argument("task-file").binding("task-file")); - options.addOption(Poco::Util::Option("task-upload-force", "", "Force upload task-file even node already exists. Default is false.") - .argument("task-upload-force").binding("task-upload-force")); - options.addOption(Poco::Util::Option("safe-mode", "", "disables ALTER DROP PARTITION in case of errors") - .binding("safe-mode")); - options.addOption(Poco::Util::Option("copy-fault-probability", "", "the copying fails with specified probability (used to test partition state recovering)") - .argument("copy-fault-probability").binding("copy-fault-probability")); - options.addOption(Poco::Util::Option("move-fault-probability", "", "the moving fails with specified probability (used to test partition state recovering)") - .argument("move-fault-probability").binding("move-fault-probability")); - options.addOption(Poco::Util::Option("log-level", "", "sets log level") - .argument("log-level").binding("log-level")); - options.addOption(Poco::Util::Option("base-dir", "", "base directory for copiers, consecutive copier launches will populate /base-dir/launch_id/* directories") - .argument("base-dir").binding("base-dir")); - options.addOption(Poco::Util::Option("experimental-use-sample-offset", "", "Use SAMPLE OFFSET query instead of cityHash64(PRIMARY KEY) % n == k") - .argument("experimental-use-sample-offset").binding("experimental-use-sample-offset")); - options.addOption(Poco::Util::Option("status", "", "Get for status for current execution").binding("status")); - - options.addOption(Poco::Util::Option("max-table-tries", "", "Number of tries for the copy table task") - .argument("max-table-tries").binding("max-table-tries")); - options.addOption(Poco::Util::Option("max-shard-partition-tries", "", "Number of tries for the copy one partition task") - .argument("max-shard-partition-tries").binding("max-shard-partition-tries")); - options.addOption(Poco::Util::Option("max-shard-partition-piece-tries-for-alter", "", "Number of tries for final ALTER ATTACH to destination table") - .argument("max-shard-partition-piece-tries-for-alter").binding("max-shard-partition-piece-tries-for-alter")); - options.addOption(Poco::Util::Option("retry-delay-ms", "", "Delay between task retries") - .argument("retry-delay-ms").binding("retry-delay-ms")); - - using Me = std::decay_t; - options.addOption(Poco::Util::Option("help", "", "produce this help message").binding("help") - .callback(Poco::Util::OptionCallback(this, &Me::handleHelp))); -} - - -void ClusterCopierApp::mainImpl() -{ - /// Status command - { - if (is_status_mode) - { - SharedContextHolder shared_context = Context::createShared(); - auto context = Context::createGlobal(shared_context.get()); - context->makeGlobalContext(); - SCOPE_EXIT_SAFE(context->shutdown()); - - auto zookeeper = context->getZooKeeper(); - auto status_json = zookeeper->get(task_path + "/status"); - - LOG_INFO(&logger(), "{}", status_json); - std::cout << status_json << std::endl; - - context->resetZooKeeper(); - return; - } - } - StatusFile status_file(process_path + "/status", StatusFile::write_full_info); - ThreadStatus thread_status; - - auto * log = &logger(); - LOG_INFO(log, "Starting clickhouse-copier (id {}, host_id {}, path {}, revision {})", process_id, host_id, process_path, ClickHouseRevision::getVersionRevision()); - - SharedContextHolder shared_context = Context::createShared(); - auto context = Context::createGlobal(shared_context.get()); - context->makeGlobalContext(); - SCOPE_EXIT_SAFE(context->shutdown()); - - context->setConfig(loaded_config.configuration); - context->setApplicationType(Context::ApplicationType::LOCAL); - context->setPath(process_path + "/"); - - registerInterpreters(); - registerFunctions(); - registerAggregateFunctions(); - registerTableFunctions(); - registerDatabases(); - registerStorages(); - registerDictionaries(); - registerDisks(/* global_skip_access_check= */ true); - registerFormats(); - - static const std::string default_database = "_local"; - DatabaseCatalog::instance().attachDatabase(default_database, std::make_shared(default_database, context)); - context->setCurrentDatabase(default_database); - - /// Disable queries logging, since: - /// - There are bits that is not allowed for global context, like adding factories info (for the query_log) - /// - And anyway it is useless for copier. - context->setSetting("log_queries", false); - - auto local_context = Context::createCopy(context); - - /// Initialize query scope just in case. - CurrentThread::QueryScope query_scope(local_context); - - auto copier = std::make_unique( - task_path, host_id, default_database, local_context, log); - copier->setSafeMode(is_safe_mode); - copier->setCopyFaultProbability(copy_fault_probability); - copier->setMoveFaultProbability(move_fault_probability); - copier->setMaxTableTries(max_table_tries); - copier->setMaxShardPartitionTries(max_shard_partition_tries); - copier->setMaxShardPartitionPieceTriesForAlter(max_shard_partition_piece_tries_for_alter); - copier->setRetryDelayMs(retry_delay_ms); - copier->setExperimentalUseSampleOffset(experimental_use_sample_offset); - - auto task_file = config().getString("task-file", ""); - if (!task_file.empty()) - copier->uploadTaskDescription(task_path, task_file, config().getBool("task-upload-force", false)); - - zkutil::validateZooKeeperConfig(config()); - - copier->init(); - copier->process(ConnectionTimeouts::getTCPTimeoutsWithoutFailover(context->getSettingsRef())); - - /// Reset ZooKeeper before removing ClusterCopier. - /// Otherwise zookeeper watch can call callback which use already removed ClusterCopier object. - context->resetZooKeeper(); -} - - -int ClusterCopierApp::main(const std::vector &) -{ - if (is_help) - return 0; - - try - { - mainImpl(); - } - catch (...) - { - tryLogCurrentException(&Poco::Logger::root(), __PRETTY_FUNCTION__); - auto code = getCurrentExceptionCode(); - - return (code) ? code : -1; - } - - return 0; -} - - -} - -#pragma GCC diagnostic ignored "-Wunused-function" -#pragma GCC diagnostic ignored "-Wmissing-declarations" - -int mainEntryClickHouseClusterCopier(int argc, char ** argv) -{ - try - { - DB::ClusterCopierApp app; - return app.run(argc, argv); - } - catch (...) - { - std::cerr << DB::getCurrentExceptionMessage(true) << "\n"; - auto code = DB::getCurrentExceptionCode(); - - return (code) ? code : -1; - } -} diff --git a/programs/copier/ClusterCopierApp.h b/programs/copier/ClusterCopierApp.h deleted file mode 100644 index 0ddc232381e..00000000000 --- a/programs/copier/ClusterCopierApp.h +++ /dev/null @@ -1,99 +0,0 @@ -#pragma once - -#include -#include - -#include "ClusterCopier.h" - -/* clickhouse cluster copier util - * Copies tables data from one cluster to new tables of other (possibly the same) cluster in distributed fault-tolerant manner. - * - * See overview in the docs: docs/en/utils/clickhouse-copier.md - * - * Implementation details: - * - * cluster-copier workers pull each partition of each shard of the source cluster and push it to the destination cluster through - * Distributed table (to perform data resharding). So, worker job is a partition of a source shard. - * A job has three states: Active, Finished and Abandoned. Abandoned means that worker died and did not finish the job. - * - * If an error occurred during the copying (a worker failed or a worker did not finish the INSERT), then the whole partition (on - * all destination servers) should be dropped and refilled. So, copying entity is a partition of all destination shards. - * If a failure is detected a special /is_dirty node is created in ZooKeeper signalling that other workers copying the same partition - * should stop, after a refilling procedure should start. - * - * ZooKeeper task node has the following structure: - * /task/path_root - path passed in --task-path parameter - * /description - contains user-defined XML config of the task - * /task_active_workers - contains ephemeral nodes of all currently active workers, used to implement max_workers limitation - * /server_fqdn#PID_timestamp - cluster-copier worker ID - * ... - * /tables - directory with table tasks - * /cluster.db.table1 - directory of table_hits task - * /partition1 - directory for partition1 - * /shards - directory for source cluster shards - * /1 - worker job for the first shard of partition1 of table test.hits - * Contains info about current status (Active or Finished) and worker ID. - * /2 - * ... - * /partition_active_workers - * /1 - for each job in /shards a corresponding ephemeral node created in /partition_active_workers - * It is used to detect Abandoned jobs (if there is Active node in /shards and there is no node in - * /partition_active_workers). - * Also, it is used to track active workers in the partition (when we need to refill the partition we do - * not DROP PARTITION while there are active workers) - * /2 - * ... - * /is_dirty - the node is set if some worker detected that an error occurred (the INSERT is failed or an Abandoned node is - * detected). If the node appeared workers in this partition should stop and start cleaning and refilling - * partition procedure. - * During this procedure a single 'cleaner' worker is selected. The worker waits for stopping all partition - * workers, removes /shards node, executes DROP PARTITION on each destination node and removes /is_dirty node. - * /cleaner- An ephemeral node used to select 'cleaner' worker. Contains ID of the worker. - * /cluster.db.table2 - * ... - */ - -namespace DB -{ - -class ClusterCopierApp : public BaseDaemon -{ -public: - - void initialize(Poco::Util::Application & self) override; - - void handleHelp(const std::string &, const std::string &); - - void defineOptions(Poco::Util::OptionSet & options) override; - - int main(const std::vector &) override; - -private: - - using Base = BaseDaemon; - - void mainImpl(); - - std::string config_xml_path; - std::string task_path; - std::string log_level = "info"; - bool is_safe_mode = false; - bool is_status_mode = false; - double copy_fault_probability = 0.0; - double move_fault_probability = 0.0; - bool is_help = false; - - UInt64 max_table_tries = 3; - UInt64 max_shard_partition_tries = 3; - UInt64 max_shard_partition_piece_tries_for_alter = 10; - std::chrono::milliseconds retry_delay_ms{1000}; - - bool experimental_use_sample_offset{false}; - - std::string base_dir; - std::string process_path; - std::string process_id; - std::string host_id; -}; - -} diff --git a/programs/copier/ClusterPartition.h b/programs/copier/ClusterPartition.h deleted file mode 100644 index 22063989e22..00000000000 --- a/programs/copier/ClusterPartition.h +++ /dev/null @@ -1,22 +0,0 @@ -#pragma once - -#include -#include - -namespace DB -{ - -/// Contains info about all shards that contain a partition -struct ClusterPartition -{ - double elapsed_time_seconds = 0; - UInt64 bytes_copied = 0; - UInt64 rows_copied = 0; - UInt64 blocks_copied = 0; - - UInt64 total_tries = 0; -}; - -using ClusterPartitions = std::map>; - -} diff --git a/programs/copier/Internals.cpp b/programs/copier/Internals.cpp deleted file mode 100644 index dcd199c6b38..00000000000 --- a/programs/copier/Internals.cpp +++ /dev/null @@ -1,280 +0,0 @@ -#include "Internals.h" -#include -#include -#include -#include -#include -#include -#include - -namespace DB -{ -namespace ErrorCodes -{ - extern const int BAD_ARGUMENTS; -} - -using ConfigurationPtr = Poco::AutoPtr; - -ConfigurationPtr getConfigurationFromXMLString(const std::string & xml_data) -{ - std::stringstream ss(xml_data); // STYLE_CHECK_ALLOW_STD_STRING_STREAM - Poco::XML::InputSource input_source{ss}; - return {new Poco::Util::XMLConfiguration{&input_source}}; -} - -String getQuotedTable(const String & database, const String & table) -{ - if (database.empty()) - return backQuoteIfNeed(table); - - return backQuoteIfNeed(database) + "." + backQuoteIfNeed(table); -} - -String getQuotedTable(const DatabaseAndTableName & db_and_table) -{ - return getQuotedTable(db_and_table.first, db_and_table.second); -} - - -// Creates AST representing 'ENGINE = Distributed(cluster, db, table, [sharding_key]) -std::shared_ptr createASTStorageDistributed( - const String & cluster_name, const String & database, const String & table, - const ASTPtr & sharding_key_ast) -{ - auto args = std::make_shared(); - args->children.emplace_back(std::make_shared(cluster_name)); - args->children.emplace_back(std::make_shared(database)); - args->children.emplace_back(std::make_shared(table)); - if (sharding_key_ast) - args->children.emplace_back(sharding_key_ast); - - auto engine = std::make_shared(); - engine->name = "Distributed"; - engine->arguments = args; - - auto storage = std::make_shared(); - storage->set(storage->engine, engine); - - return storage; -} - - -Block getBlockWithAllStreamData(QueryPipelineBuilder builder) -{ - builder.addTransform(std::make_shared( - builder.getHeader(), - std::numeric_limits::max(), - std::numeric_limits::max())); - - auto cur_pipeline = QueryPipelineBuilder::getPipeline(std::move(builder)); - Block block; - PullingPipelineExecutor executor(cur_pipeline); - executor.pull(block); - - return block; -} - -bool isExtendedDefinitionStorage(const ASTPtr & storage_ast) -{ - const auto & storage = storage_ast->as(); - return storage.partition_by || storage.order_by || storage.sample_by; -} - -ASTPtr extractPartitionKey(const ASTPtr & storage_ast) -{ - String storage_str = queryToString(storage_ast); - - const auto & storage = storage_ast->as(); - const auto & engine = storage.engine->as(); - - if (!endsWith(engine.name, "MergeTree")) - { - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unsupported engine was specified in {}, only *MergeTree engines are supported", storage_str); - } - - if (isExtendedDefinitionStorage(storage_ast)) - { - if (storage.partition_by) - return storage.partition_by->clone(); - - static const char * all = "all"; - return std::make_shared(Field(all, strlen(all))); - } - else - { - bool is_replicated = startsWith(engine.name, "Replicated"); - size_t min_args = is_replicated ? 3 : 1; - - if (!engine.arguments) - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Expected arguments in {}", storage_str); - - ASTPtr arguments_ast = engine.arguments->clone(); - ASTs & arguments = arguments_ast->children; - - if (arguments.size() < min_args) - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Expected at least {} arguments in {}", min_args, storage_str); - - ASTPtr & month_arg = is_replicated ? arguments[2] : arguments[1]; - return makeASTFunction("toYYYYMM", month_arg->clone()); - } -} - -ASTPtr extractPrimaryKey(const ASTPtr & storage_ast) -{ - String storage_str = queryToString(storage_ast); - - const auto & storage = storage_ast->as(); - const auto & engine = storage.engine->as(); - - if (!endsWith(engine.name, "MergeTree")) - { - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unsupported engine was specified in {}, only *MergeTree engines are supported", storage_str); - } - - if (!isExtendedDefinitionStorage(storage_ast)) - { - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Is not extended deginition storage {} Will be fixed later.", storage_str); - } - - if (storage.primary_key) - return storage.primary_key->clone(); - - return nullptr; -} - - -ASTPtr extractOrderBy(const ASTPtr & storage_ast) -{ - String storage_str = queryToString(storage_ast); - - const auto & storage = storage_ast->as(); - const auto & engine = storage.engine->as(); - - if (!endsWith(engine.name, "MergeTree")) - { - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unsupported engine was specified in {}, only *MergeTree engines are supported", storage_str); - } - - if (!isExtendedDefinitionStorage(storage_ast)) - { - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Is not extended deginition storage {} Will be fixed later.", storage_str); - } - - if (storage.order_by) - return storage.order_by->clone(); - - throw Exception(ErrorCodes::BAD_ARGUMENTS, "ORDER BY cannot be empty"); -} - -/// Wraps only identifiers with backticks. -std::string wrapIdentifiersWithBackticks(const ASTPtr & root) -{ - if (auto identifier = std::dynamic_pointer_cast(root)) - return backQuote(identifier->name()); - - if (auto function = std::dynamic_pointer_cast(root)) - return function->name + '(' + wrapIdentifiersWithBackticks(function->arguments) + ')'; - - if (auto expression_list = std::dynamic_pointer_cast(root)) - { - Names function_arguments(expression_list->children.size()); - for (size_t i = 0; i < expression_list->children.size(); ++i) - function_arguments[i] = wrapIdentifiersWithBackticks(expression_list->children[0]); - return boost::algorithm::join(function_arguments, ", "); - } - - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Primary key could be represented only as columns or functions from columns."); -} - - -Names extractPrimaryKeyColumnNames(const ASTPtr & storage_ast) -{ - const auto sorting_key_ast = extractOrderBy(storage_ast); - const auto primary_key_ast = extractPrimaryKey(storage_ast); - - const auto sorting_key_expr_list = extractKeyExpressionList(sorting_key_ast); - const auto primary_key_expr_list = primary_key_ast - ? extractKeyExpressionList(primary_key_ast) : sorting_key_expr_list->clone(); - - /// Maybe we have to handle VersionedCollapsing engine separately. But in our case in looks pointless. - - size_t primary_key_size = primary_key_expr_list->children.size(); - size_t sorting_key_size = sorting_key_expr_list->children.size(); - - if (primary_key_size > sorting_key_size) - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Primary key must be a prefix of the sorting key, but its length: " - "{} is greater than the sorting key length: {}", - primary_key_size, sorting_key_size); - - Names primary_key_columns; - NameSet primary_key_columns_set; - - for (size_t i = 0; i < sorting_key_size; ++i) - { - /// Column name could be represented as a f_1(f_2(...f_n(column_name))). - /// Each f_i could take one or more parameters. - /// We will wrap identifiers with backticks to allow non-standard identifier names. - String sorting_key_column = sorting_key_expr_list->children[i]->getColumnName(); - - if (i < primary_key_size) - { - String pk_column = primary_key_expr_list->children[i]->getColumnName(); - if (pk_column != sorting_key_column) - throw Exception(ErrorCodes::BAD_ARGUMENTS, - "Primary key must be a prefix of the sorting key, " - "but the column in the position {} is {}, not {}", i, sorting_key_column, pk_column); - - if (!primary_key_columns_set.emplace(pk_column).second) - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Primary key contains duplicate columns"); - - primary_key_columns.push_back(wrapIdentifiersWithBackticks(primary_key_expr_list->children[i])); - } - } - - return primary_key_columns; -} - -bool isReplicatedTableEngine(const ASTPtr & storage_ast) -{ - const auto & storage = storage_ast->as(); - const auto & engine = storage.engine->as(); - - if (!endsWith(engine.name, "MergeTree")) - { - String storage_str = queryToString(storage_ast); - throw Exception(ErrorCodes::BAD_ARGUMENTS, "Unsupported engine was specified in {}, only *MergeTree engines are supported", storage_str); - } - - return startsWith(engine.name, "Replicated"); -} - -ShardPriority getReplicasPriority(const Cluster::Addresses & replicas, const std::string & local_hostname, UInt8 random) -{ - ShardPriority res; - - if (replicas.empty()) - return res; - - res.is_remote = 1; - for (const auto & replica : replicas) - { - if (isLocalAddress(DNSResolver::instance().resolveHostAllInOriginOrder(replica.host_name).front())) - { - res.is_remote = 0; - break; - } - } - - res.hostname_difference = std::numeric_limits::max(); - for (const auto & replica : replicas) - { - size_t difference = getHostNamePrefixDistance(local_hostname, replica.host_name); - res.hostname_difference = std::min(difference, res.hostname_difference); - } - - res.random = random; - return res; -} - -} diff --git a/programs/copier/Internals.h b/programs/copier/Internals.h deleted file mode 100644 index 27fedd5d9e8..00000000000 --- a/programs/copier/Internals.h +++ /dev/null @@ -1,198 +0,0 @@ -#pragma once - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "Aliases.h" - -namespace DB -{ - -namespace ErrorCodes -{ - extern const int LOGICAL_ERROR; -} - - -ConfigurationPtr getConfigurationFromXMLString(const std::string & xml_data); - -String getQuotedTable(const String & database, const String & table); - -String getQuotedTable(const DatabaseAndTableName & db_and_table); - - -enum class TaskState -{ - Started = 0, - Finished, - Unknown -}; - -/// Used to mark status of shard partition tasks -struct TaskStateWithOwner -{ - TaskStateWithOwner() = default; - - TaskStateWithOwner(TaskState state_, const String & owner_) : state(state_), owner(owner_) {} - - TaskState state{TaskState::Unknown}; - String owner; - - static String getData(TaskState state, const String &owner) - { - return TaskStateWithOwner(state, owner).toString(); - } - - String toString() const - { - WriteBufferFromOwnString wb; - wb << static_cast(state) << "\n" << escape << owner; - return wb.str(); - } - - static TaskStateWithOwner fromString(const String & data) - { - ReadBufferFromString rb(data); - TaskStateWithOwner res; - UInt32 state; - - rb >> state >> "\n" >> escape >> res.owner; - - if (state >= static_cast(TaskState::Unknown)) - throw Exception(ErrorCodes::LOGICAL_ERROR, "Unknown state {}", data); - - res.state = static_cast(state); - return res; - } -}; - - -struct ShardPriority -{ - UInt8 is_remote = 1; - size_t hostname_difference = 0; - UInt8 random = 0; - - static bool greaterPriority(const ShardPriority & current, const ShardPriority & other) - { - return std::forward_as_tuple(current.is_remote, current.hostname_difference, current.random) - < std::forward_as_tuple(other.is_remote, other.hostname_difference, other.random); - } -}; - -/// Execution status of a task. -/// Is used for: partition copying task status, partition piece copying task status, partition moving task status. -enum class TaskStatus -{ - Active, - Finished, - Error, -}; - -struct MultiTransactionInfo -{ - int32_t code; - Coordination::Requests requests; - Coordination::Responses responses; -}; - -// Creates AST representing 'ENGINE = Distributed(cluster, db, table, [sharding_key]) -std::shared_ptr createASTStorageDistributed( - const String & cluster_name, const String & database, const String & table, - const ASTPtr & sharding_key_ast = nullptr); - -Block getBlockWithAllStreamData(QueryPipelineBuilder builder); - -bool isExtendedDefinitionStorage(const ASTPtr & storage_ast); - -ASTPtr extractPartitionKey(const ASTPtr & storage_ast); - -/* -* Choosing a Primary Key that Differs from the Sorting Key -* It is possible to specify a primary key (an expression with values that are written in the index file for each mark) -* that is different from the sorting key (an expression for sorting the rows in data parts). -* In this case the primary key expression tuple must be a prefix of the sorting key expression tuple. -* This feature is helpful when using the SummingMergeTree and AggregatingMergeTree table engines. -* In a common case when using these engines, the table has two types of columns: dimensions and measures. -* Typical queries aggregate values of measure columns with arbitrary GROUP BY and filtering by dimensions. -* Because SummingMergeTree and AggregatingMergeTree aggregate rows with the same value of the sorting key, -* it is natural to add all dimensions to it. As a result, the key expression consists of a long list of columns -* and this list must be frequently updated with newly added dimensions. -* In this case it makes sense to leave only a few columns in the primary key that will provide efficient -* range scans and add the remaining dimension columns to the sorting key tuple. -* ALTER of the sorting key is a lightweight operation because when a new column is simultaneously added t -* o the table and to the sorting key, existing data parts don't need to be changed. -* Since the old sorting key is a prefix of the new sorting key and there is no data in the newly added column, -* the data is sorted by both the old and new sorting keys at the moment of table modification. -* -* */ -ASTPtr extractPrimaryKey(const ASTPtr & storage_ast); - -ASTPtr extractOrderBy(const ASTPtr & storage_ast); - -Names extractPrimaryKeyColumnNames(const ASTPtr & storage_ast); - -bool isReplicatedTableEngine(const ASTPtr & storage_ast); - -ShardPriority getReplicasPriority(const Cluster::Addresses & replicas, const std::string & local_hostname, UInt8 random); - -} diff --git a/programs/copier/ShardPartition.cpp b/programs/copier/ShardPartition.cpp deleted file mode 100644 index 4c962fc807d..00000000000 --- a/programs/copier/ShardPartition.cpp +++ /dev/null @@ -1,70 +0,0 @@ -#include "ShardPartition.h" - -#include "TaskShard.h" -#include "TaskTable.h" - -namespace DB -{ - -ShardPartition::ShardPartition(TaskShard & parent, String name_quoted_, size_t number_of_splits) - : task_shard(parent) - , name(std::move(name_quoted_)) -{ - pieces.reserve(number_of_splits); -} - -String ShardPartition::getPartitionCleanStartPath() const -{ - return getPartitionPath() + "/clean_start"; -} - -String ShardPartition::getPartitionPieceCleanStartPath(size_t current_piece_number) const -{ - assert(current_piece_number < task_shard.task_table.number_of_splits); - return getPartitionPiecePath(current_piece_number) + "/clean_start"; -} - -String ShardPartition::getPartitionPath() const -{ - return task_shard.task_table.getPartitionPath(name); -} - -String ShardPartition::getPartitionPiecePath(size_t current_piece_number) const -{ - assert(current_piece_number < task_shard.task_table.number_of_splits); - return task_shard.task_table.getPartitionPiecePath(name, current_piece_number); -} - -String ShardPartition::getShardStatusPath() const -{ - // schema: //tables///shards/ - // e.g. /root/table_test.hits/201701/shards/1 - return getPartitionShardsPath() + "/" + toString(task_shard.numberInCluster()); -} - -String ShardPartition::getPartitionShardsPath() const -{ - return getPartitionPath() + "/shards"; -} - -String ShardPartition::getPartitionActiveWorkersPath() const -{ - return getPartitionPath() + "/partition_active_workers"; -} - -String ShardPartition::getActiveWorkerPath() const -{ - return getPartitionActiveWorkersPath() + "/" + toString(task_shard.numberInCluster()); -} - -String ShardPartition::getCommonPartitionIsDirtyPath() const -{ - return getPartitionPath() + "/is_dirty"; -} - -String ShardPartition::getCommonPartitionIsCleanedPath() const -{ - return getCommonPartitionIsDirtyPath() + "/cleaned"; -} - -} diff --git a/programs/copier/ShardPartition.h b/programs/copier/ShardPartition.h deleted file mode 100644 index 2457213733c..00000000000 --- a/programs/copier/ShardPartition.h +++ /dev/null @@ -1,54 +0,0 @@ -#pragma once - -#include "ShardPartitionPiece.h" - -#include - -#include - -namespace DB -{ - -struct TaskShard; - -/// Just destination partition of a shard -/// I don't know what this comment means. -/// In short, when we discovered what shards contain currently processing partition, -/// This class describes a partition (name) that is stored on the shard (parent). -struct ShardPartition -{ - ShardPartition(TaskShard &parent, String name_quoted_, size_t number_of_splits = 10); - - String getPartitionPath() const; - - String getPartitionPiecePath(size_t current_piece_number) const; - - String getPartitionCleanStartPath() const; - - String getPartitionPieceCleanStartPath(size_t current_piece_number) const; - - String getCommonPartitionIsDirtyPath() const; - - String getCommonPartitionIsCleanedPath() const; - - String getPartitionActiveWorkersPath() const; - - String getActiveWorkerPath() const; - - String getPartitionShardsPath() const; - - String getShardStatusPath() const; - - /// What partition pieces are present in current shard. - /// FYI: Piece is a part of partition which has modulo equals to concrete constant (less than number_of_splits obliously) - /// For example SELECT ... from ... WHERE partition=current_partition AND cityHash64(*) == const; - /// Absent pieces have field is_absent_piece equals to true. - PartitionPieces pieces; - - TaskShard & task_shard; - String name; -}; - -using TasksPartition = std::map>; - -} diff --git a/programs/copier/ShardPartitionPiece.cpp b/programs/copier/ShardPartitionPiece.cpp deleted file mode 100644 index 36d1621e012..00000000000 --- a/programs/copier/ShardPartitionPiece.cpp +++ /dev/null @@ -1,64 +0,0 @@ -#include "ShardPartitionPiece.h" - -#include "ShardPartition.h" -#include "TaskShard.h" - -#include - -namespace DB -{ - -ShardPartitionPiece::ShardPartitionPiece(ShardPartition & parent, size_t current_piece_number_, bool is_present_piece_) - : is_absent_piece(!is_present_piece_) - , current_piece_number(current_piece_number_) - , shard_partition(parent) -{ -} - -String ShardPartitionPiece::getPartitionPiecePath() const -{ - return shard_partition.getPartitionPath() + "/piece_" + toString(current_piece_number); -} - -String ShardPartitionPiece::getPartitionPieceCleanStartPath() const -{ - return getPartitionPiecePath() + "/clean_start"; -} - -String ShardPartitionPiece::getPartitionPieceIsDirtyPath() const -{ - return getPartitionPiecePath() + "/is_dirty"; -} - -String ShardPartitionPiece::getPartitionPieceIsCleanedPath() const -{ - return getPartitionPieceIsDirtyPath() + "/cleaned"; -} - -String ShardPartitionPiece::getPartitionPieceActiveWorkersPath() const -{ - return getPartitionPiecePath() + "/partition_piece_active_workers"; -} - -String ShardPartitionPiece::getActiveWorkerPath() const -{ - return getPartitionPieceActiveWorkersPath() + "/" + toString(shard_partition.task_shard.numberInCluster()); -} - -/// On what shards do we have current partition. -String ShardPartitionPiece::getPartitionPieceShardsPath() const -{ - return getPartitionPiecePath() + "/shards"; -} - -String ShardPartitionPiece::getShardStatusPath() const -{ - return getPartitionPieceShardsPath() + "/" + toString(shard_partition.task_shard.numberInCluster()); -} - -String ShardPartitionPiece::getPartitionPieceCleanerPath() const -{ - return getPartitionPieceIsDirtyPath() + "/cleaner"; -} - -} diff --git a/programs/copier/ShardPartitionPiece.h b/programs/copier/ShardPartitionPiece.h deleted file mode 100644 index 453364c0fc8..00000000000 --- a/programs/copier/ShardPartitionPiece.h +++ /dev/null @@ -1,43 +0,0 @@ -#pragma once - -#include - -#include - -namespace DB -{ - -struct ShardPartition; - -struct ShardPartitionPiece -{ - ShardPartitionPiece(ShardPartition & parent, size_t current_piece_number_, bool is_present_piece_); - - String getPartitionPiecePath() const; - - String getPartitionPieceCleanStartPath() const; - - String getPartitionPieceIsDirtyPath() const; - - String getPartitionPieceIsCleanedPath() const; - - String getPartitionPieceActiveWorkersPath() const; - - String getActiveWorkerPath() const ; - - /// On what shards do we have current partition. - String getPartitionPieceShardsPath() const; - - String getShardStatusPath() const; - - String getPartitionPieceCleanerPath() const; - - bool is_absent_piece; - const size_t current_piece_number; - - ShardPartition & shard_partition; -}; - -using PartitionPieces = std::vector; - -} diff --git a/programs/copier/StatusAccumulator.cpp b/programs/copier/StatusAccumulator.cpp deleted file mode 100644 index 77adeac708c..00000000000 --- a/programs/copier/StatusAccumulator.cpp +++ /dev/null @@ -1,48 +0,0 @@ -#include "StatusAccumulator.h" - -#include -#include -#include -#include - -#include - -namespace DB -{ - -StatusAccumulator::MapPtr StatusAccumulator::fromJSON(String state_json) -{ - Poco::JSON::Parser parser; - auto state = parser.parse(state_json).extract(); - MapPtr result_ptr = std::make_shared(); - for (const auto & table_name : state->getNames()) - { - auto table_status_json = state->getValue(table_name); - auto table_status = parser.parse(table_status_json).extract(); - /// Map entry will be created if it is absent - auto & map_table_status = (*result_ptr)[table_name]; - map_table_status.all_partitions_count += table_status->getValue("all_partitions_count"); - map_table_status.processed_partitions_count += table_status->getValue("processed_partitions_count"); - } - return result_ptr; -} - -String StatusAccumulator::serializeToJSON(MapPtr statuses) -{ - Poco::JSON::Object result_json; - for (const auto & [table_name, table_status] : *statuses) - { - Poco::JSON::Object status_json; - status_json.set("all_partitions_count", table_status.all_partitions_count); - status_json.set("processed_partitions_count", table_status.processed_partitions_count); - - result_json.set(table_name, status_json); - } - std::ostringstream oss; // STYLE_CHECK_ALLOW_STD_STRING_STREAM - oss.exceptions(std::ios::failbit); - Poco::JSON::Stringifier::stringify(result_json, oss); - auto result = oss.str(); - return result; -} - -} diff --git a/programs/copier/StatusAccumulator.h b/programs/copier/StatusAccumulator.h deleted file mode 100644 index d420b611602..00000000000 --- a/programs/copier/StatusAccumulator.h +++ /dev/null @@ -1,27 +0,0 @@ -#pragma once - -#include - -#include -#include - -namespace DB -{ - -class StatusAccumulator -{ -public: - struct TableStatus - { - size_t all_partitions_count; - size_t processed_partitions_count; - }; - - using Map = std::unordered_map; - using MapPtr = std::shared_ptr; - - static MapPtr fromJSON(String state_json); - static String serializeToJSON(MapPtr statuses); -}; - -} diff --git a/programs/copier/TaskCluster.cpp b/programs/copier/TaskCluster.cpp deleted file mode 100644 index 0fb06616e50..00000000000 --- a/programs/copier/TaskCluster.cpp +++ /dev/null @@ -1,74 +0,0 @@ -#include "TaskCluster.h" - -namespace DB -{ - -namespace ErrorCodes -{ - extern const int BAD_ARGUMENTS; -} - -TaskCluster::TaskCluster(const String & task_zookeeper_path_, const String & default_local_database_) - : task_zookeeper_path(task_zookeeper_path_) - , default_local_database(default_local_database_) -{} - -void DB::TaskCluster::loadTasks(const Poco::Util::AbstractConfiguration & config, const String & base_key) -{ - String prefix = base_key.empty() ? "" : base_key + "."; - - clusters_prefix = prefix + "remote_servers"; - if (!config.has(clusters_prefix)) - throw Exception(ErrorCodes::BAD_ARGUMENTS, "You should specify list of clusters in {}", clusters_prefix); - - Poco::Util::AbstractConfiguration::Keys tables_keys; - config.keys(prefix + "tables", tables_keys); - - for (const auto & table_key : tables_keys) - { - table_tasks.emplace_back(*this, config, prefix + "tables", table_key); - } -} - -void DB::TaskCluster::reloadSettings(const Poco::Util::AbstractConfiguration & config, const String & base_key) -{ - String prefix = base_key.empty() ? "" : base_key + "."; - - max_workers = config.getUInt64(prefix + "max_workers"); - - settings_common = Settings(); - if (config.has(prefix + "settings")) - settings_common.loadSettingsFromConfig(prefix + "settings", config); - - settings_common.prefer_localhost_replica = false; - - settings_pull = settings_common; - if (config.has(prefix + "settings_pull")) - settings_pull.loadSettingsFromConfig(prefix + "settings_pull", config); - - settings_push = settings_common; - if (config.has(prefix + "settings_push")) - settings_push.loadSettingsFromConfig(prefix + "settings_push", config); - - auto set_default_value = [] (auto && setting, auto && default_value) - { - setting = setting.changed ? setting.value : default_value; - }; - - /// Override important settings - settings_pull.readonly = 1; - settings_pull.prefer_localhost_replica = false; - settings_push.distributed_foreground_insert = true; - settings_push.prefer_localhost_replica = false; - - set_default_value(settings_pull.load_balancing, LoadBalancing::NEAREST_HOSTNAME); - set_default_value(settings_pull.max_threads, 1); - set_default_value(settings_pull.max_block_size, 8192UL); - set_default_value(settings_pull.preferred_block_size_bytes, 0); - - set_default_value(settings_push.distributed_background_insert_timeout, 0); - set_default_value(settings_push.alter_sync, 2); -} - -} - diff --git a/programs/copier/TaskCluster.h b/programs/copier/TaskCluster.h deleted file mode 100644 index a7f8bc3baca..00000000000 --- a/programs/copier/TaskCluster.h +++ /dev/null @@ -1,51 +0,0 @@ -#pragma once - -#include "TaskTable.h" - -#include -#include - -#include - -#include - -namespace DB -{ - -struct TaskCluster -{ - TaskCluster(const String & task_zookeeper_path_, const String & default_local_database_); - - void loadTasks(const Poco::Util::AbstractConfiguration & config, const String & base_key = ""); - - /// Set (or update) settings and max_workers param - void reloadSettings(const Poco::Util::AbstractConfiguration & config, const String & base_key = ""); - - /// Base node for all tasks. Its structure: - /// workers/ - directory with active workers (amount of them is less or equal max_workers) - /// description - node with task configuration - /// table_table1/ - directories with per-partition copying status - String task_zookeeper_path; - - /// Database used to create temporary Distributed tables - String default_local_database; - - /// Limits number of simultaneous workers - UInt64 max_workers = 0; - - /// Base settings for pull and push - Settings settings_common; - /// Settings used to fetch data - Settings settings_pull; - /// Settings used to insert data - Settings settings_push; - - String clusters_prefix; - - /// Subtasks - TasksTable table_tasks; - - pcg64 random_engine; -}; - -} diff --git a/programs/copier/TaskShard.cpp b/programs/copier/TaskShard.cpp deleted file mode 100644 index d156f451a84..00000000000 --- a/programs/copier/TaskShard.cpp +++ /dev/null @@ -1,37 +0,0 @@ -#include "TaskShard.h" - -#include "TaskTable.h" - -namespace DB -{ - -TaskShard::TaskShard(TaskTable & parent, const Cluster::ShardInfo & info_) - : task_table(parent) - , info(info_) -{ - list_of_split_tables_on_shard.assign(task_table.number_of_splits, DatabaseAndTableName()); -} - -UInt32 TaskShard::numberInCluster() const -{ - return info.shard_num; -} - -UInt32 TaskShard::indexInCluster() const -{ - return info.shard_num - 1; -} - -String DB::TaskShard::getDescription() const -{ - return fmt::format("N{} (having a replica {}, pull table {} of cluster {}", - numberInCluster(), getHostNameExample(), getQuotedTable(task_table.table_pull), task_table.cluster_pull_name); -} - -String DB::TaskShard::getHostNameExample() const -{ - const auto & replicas = task_table.cluster_pull->getShardsAddresses().at(indexInCluster()); - return replicas.at(0).readableString(); -} - -} diff --git a/programs/copier/TaskShard.h b/programs/copier/TaskShard.h deleted file mode 100644 index 05d652077ea..00000000000 --- a/programs/copier/TaskShard.h +++ /dev/null @@ -1,56 +0,0 @@ -#pragma once - -#include "Aliases.h" -#include "Internals.h" -#include "ClusterPartition.h" -#include "ShardPartition.h" - - -namespace DB -{ - -struct TaskTable; - -struct TaskShard -{ - TaskShard(TaskTable & parent, const Cluster::ShardInfo & info_); - - TaskTable & task_table; - - Cluster::ShardInfo info; - - UInt32 numberInCluster() const; - - UInt32 indexInCluster() const; - - String getDescription() const; - - String getHostNameExample() const; - - /// Used to sort clusters by their proximity - ShardPriority priority; - - /// Column with unique destination partitions (computed from engine_push_partition_key expr.) in the shard - ColumnWithTypeAndName partition_key_column; - - /// There is a task for each destination partition - TasksPartition partition_tasks; - - /// Which partitions have been checked for existence - /// If some partition from this lists is exists, it is in partition_tasks - std::set checked_partitions; - - /// Last CREATE TABLE query of the table of the shard - ASTPtr current_pull_table_create_query; - ASTPtr current_push_table_create_query; - - /// Internal distributed tables - DatabaseAndTableName table_read_shard; - DatabaseAndTableName main_table_split_shard; - ListOfDatabasesAndTableNames list_of_split_tables_on_shard; -}; - -using TaskShardPtr = std::shared_ptr; -using TasksShard = std::vector; - -} diff --git a/programs/copier/TaskTable.cpp b/programs/copier/TaskTable.cpp deleted file mode 100644 index d055ceb4c7b..00000000000 --- a/programs/copier/TaskTable.cpp +++ /dev/null @@ -1,222 +0,0 @@ -#include "TaskTable.h" - -#include "ClusterPartition.h" -#include "TaskCluster.h" - -#include -#include - -#include - - -namespace DB -{ -namespace ErrorCodes -{ - extern const int UNKNOWN_ELEMENT_IN_CONFIG; - extern const int LOGICAL_ERROR; -} - -TaskTable::TaskTable(TaskCluster & parent, const Poco::Util::AbstractConfiguration & config, - const String & prefix_, const String & table_key) - : task_cluster(parent) -{ - String table_prefix = prefix_ + "." + table_key + "."; - - name_in_config = table_key; - - number_of_splits = config.getUInt64(table_prefix + "number_of_splits", 3); - - allow_to_copy_alias_and_materialized_columns = config.getBool(table_prefix + "allow_to_copy_alias_and_materialized_columns", false); - allow_to_drop_target_partitions = config.getBool(table_prefix + "allow_to_drop_target_partitions", false); - - cluster_pull_name = config.getString(table_prefix + "cluster_pull"); - cluster_push_name = config.getString(table_prefix + "cluster_push"); - - table_pull.first = config.getString(table_prefix + "database_pull"); - table_pull.second = config.getString(table_prefix + "table_pull"); - - table_push.first = config.getString(table_prefix + "database_push"); - table_push.second = config.getString(table_prefix + "table_push"); - - /// Used as node name in ZooKeeper - table_id = escapeForFileName(cluster_push_name) - + "." + escapeForFileName(table_push.first) - + "." + escapeForFileName(table_push.second); - - engine_push_str = config.getString(table_prefix + "engine", "rand()"); - - { - ParserStorage parser_storage{ParserStorage::TABLE_ENGINE}; - engine_push_ast = parseQuery(parser_storage, engine_push_str, 0, DBMS_DEFAULT_MAX_PARSER_DEPTH); - engine_push_partition_key_ast = extractPartitionKey(engine_push_ast); - primary_key_comma_separated = boost::algorithm::join(extractPrimaryKeyColumnNames(engine_push_ast), ", "); - is_replicated_table = isReplicatedTableEngine(engine_push_ast); - } - - sharding_key_str = config.getString(table_prefix + "sharding_key"); - - auxiliary_engine_split_asts.reserve(number_of_splits); - { - ParserExpressionWithOptionalAlias parser_expression(false); - sharding_key_ast = parseQuery(parser_expression, sharding_key_str, 0, DBMS_DEFAULT_MAX_PARSER_DEPTH); - main_engine_split_ast = createASTStorageDistributed(cluster_push_name, table_push.first, table_push.second, - sharding_key_ast); - - for (const auto piece_number : collections::range(0, number_of_splits)) - { - auxiliary_engine_split_asts.emplace_back - ( - createASTStorageDistributed(cluster_push_name, table_push.first, - table_push.second + "_piece_" + toString(piece_number), sharding_key_ast) - ); - } - } - - where_condition_str = config.getString(table_prefix + "where_condition", ""); - if (!where_condition_str.empty()) - { - ParserExpressionWithOptionalAlias parser_expression(false); - where_condition_ast = parseQuery(parser_expression, where_condition_str, 0, DBMS_DEFAULT_MAX_PARSER_DEPTH); - - // Will use canonical expression form - where_condition_str = queryToString(where_condition_ast); - } - - String enabled_partitions_prefix = table_prefix + "enabled_partitions"; - has_enabled_partitions = config.has(enabled_partitions_prefix); - - if (has_enabled_partitions) - { - Strings keys; - config.keys(enabled_partitions_prefix, keys); - - if (keys.empty()) - { - /// Parse list of partition from space-separated string - String partitions_str = config.getString(table_prefix + "enabled_partitions"); - boost::trim_if(partitions_str, isWhitespaceASCII); - boost::split(enabled_partitions, partitions_str, isWhitespaceASCII, boost::token_compress_on); - } - else - { - /// Parse sequence of ... - for (const String &key : keys) - { - if (!startsWith(key, "partition")) - throw Exception(ErrorCodes::UNKNOWN_ELEMENT_IN_CONFIG, "Unknown key {} in {}", key, enabled_partitions_prefix); - - enabled_partitions.emplace_back(config.getString(enabled_partitions_prefix + "." + key)); - } - } - - std::copy(enabled_partitions.begin(), enabled_partitions.end(), std::inserter(enabled_partitions_set, enabled_partitions_set.begin())); - } -} - - -String TaskTable::getPartitionPath(const String & partition_name) const -{ - return task_cluster.task_zookeeper_path // root - + "/tables/" + table_id // tables/dst_cluster.merge.hits - + "/" + escapeForFileName(partition_name); // 201701 -} - -String TaskTable::getPartitionAttachIsActivePath(const String & partition_name) const -{ - return getPartitionPath(partition_name) + "/attach_active"; -} - -String TaskTable::getPartitionAttachIsDonePath(const String & partition_name) const -{ - return getPartitionPath(partition_name) + "/attach_is_done"; -} - -String TaskTable::getPartitionPiecePath(const String & partition_name, size_t piece_number) const -{ - assert(piece_number < number_of_splits); - return getPartitionPath(partition_name) + "/piece_" + toString(piece_number); // 1...number_of_splits -} - -String TaskTable::getCertainPartitionIsDirtyPath(const String &partition_name) const -{ - return getPartitionPath(partition_name) + "/is_dirty"; -} - -String TaskTable::getCertainPartitionPieceIsDirtyPath(const String & partition_name, const size_t piece_number) const -{ - return getPartitionPiecePath(partition_name, piece_number) + "/is_dirty"; -} - -String TaskTable::getCertainPartitionIsCleanedPath(const String & partition_name) const -{ - return getCertainPartitionIsDirtyPath(partition_name) + "/cleaned"; -} - -String TaskTable::getCertainPartitionPieceIsCleanedPath(const String & partition_name, const size_t piece_number) const -{ - return getCertainPartitionPieceIsDirtyPath(partition_name, piece_number) + "/cleaned"; -} - -String TaskTable::getCertainPartitionTaskStatusPath(const String & partition_name) const -{ - return getPartitionPath(partition_name) + "/shards"; -} - -String TaskTable::getCertainPartitionPieceTaskStatusPath(const String & partition_name, const size_t piece_number) const -{ - return getPartitionPiecePath(partition_name, piece_number) + "/shards"; -} - -bool TaskTable::isReplicatedTable() const -{ - return is_replicated_table; -} - -String TaskTable::getStatusAllPartitionCount() const -{ - return task_cluster.task_zookeeper_path + "/status/all_partitions_count"; -} - -String TaskTable::getStatusProcessedPartitionsCount() const -{ - return task_cluster.task_zookeeper_path + "/status/processed_partitions_count"; -} - -ASTPtr TaskTable::rewriteReplicatedCreateQueryToPlain() const -{ - ASTPtr prev_engine_push_ast = engine_push_ast->clone(); - - auto & new_storage_ast = prev_engine_push_ast->as(); - auto & new_engine_ast = new_storage_ast.engine->as(); - - /// Remove "Replicated" from name - new_engine_ast.name = new_engine_ast.name.substr(10); - - if (new_engine_ast.arguments) - { - auto & replicated_table_arguments = new_engine_ast.arguments->children; - - - /// In some cases of Atomic database engine usage ReplicatedMergeTree tables - /// could be created without arguments. - if (!replicated_table_arguments.empty()) - { - /// Delete first two arguments of Replicated...MergeTree() table. - replicated_table_arguments.erase(replicated_table_arguments.begin()); - replicated_table_arguments.erase(replicated_table_arguments.begin()); - } - } - - return new_storage_ast.clone(); -} - -ClusterPartition & TaskTable::getClusterPartition(const String & partition_name) -{ - auto it = cluster_partitions.find(partition_name); - if (it == cluster_partitions.end()) - throw Exception(ErrorCodes::LOGICAL_ERROR, "There are no cluster partition {} in {}", partition_name, table_id); - return it->second; -} - -} diff --git a/programs/copier/TaskTable.h b/programs/copier/TaskTable.h deleted file mode 100644 index 2bb7f078bc6..00000000000 --- a/programs/copier/TaskTable.h +++ /dev/null @@ -1,173 +0,0 @@ -#pragma once - -#include "Aliases.h" -#include "TaskShard.h" - - -namespace DB -{ - -struct ClusterPartition; -struct TaskCluster; - -struct TaskTable -{ - TaskTable(TaskCluster & parent, const Poco::Util::AbstractConfiguration & config, const String & prefix, const String & table_key); - - TaskCluster & task_cluster; - - /// These functions used in checkPartitionIsDone() or checkPartitionPieceIsDone() - /// They are implemented here not to call task_table.tasks_shard[partition_name].second.pieces[current_piece_number] etc. - - String getPartitionPath(const String & partition_name) const; - - String getPartitionAttachIsActivePath(const String & partition_name) const; - - String getPartitionAttachIsDonePath(const String & partition_name) const; - - String getPartitionPiecePath(const String & partition_name, size_t piece_number) const; - - String getCertainPartitionIsDirtyPath(const String & partition_name) const; - - String getCertainPartitionPieceIsDirtyPath(const String & partition_name, size_t piece_number) const; - - String getCertainPartitionIsCleanedPath(const String & partition_name) const; - - String getCertainPartitionPieceIsCleanedPath(const String & partition_name, size_t piece_number) const; - - String getCertainPartitionTaskStatusPath(const String & partition_name) const; - - String getCertainPartitionPieceTaskStatusPath(const String & partition_name, size_t piece_number) const; - - bool isReplicatedTable() const; - - /// These nodes are used for check-status option - String getStatusAllPartitionCount() const; - String getStatusProcessedPartitionsCount() const; - - /// Partitions will be split into number-of-splits pieces. - /// Each piece will be copied independently. (10 by default) - size_t number_of_splits; - - bool allow_to_copy_alias_and_materialized_columns{false}; - bool allow_to_drop_target_partitions{false}; - - String name_in_config; - - /// Used as task ID - String table_id; - - /// Column names in primary key - String primary_key_comma_separated; - - /// Source cluster and table - String cluster_pull_name; - DatabaseAndTableName table_pull; - - /// Destination cluster and table - String cluster_push_name; - DatabaseAndTableName table_push; - - /// Storage of destination table - /// (tables that are stored on each shard of target cluster) - String engine_push_str; - ASTPtr engine_push_ast; - ASTPtr engine_push_partition_key_ast; - - /// First argument of Replicated...MergeTree() - String engine_push_zk_path; - bool is_replicated_table; - - ASTPtr rewriteReplicatedCreateQueryToPlain() const; - - /* - * A Distributed table definition used to split data - * Distributed table will be created on each shard of default - * cluster to perform data copying and resharding - * */ - String sharding_key_str; - ASTPtr sharding_key_ast; - ASTPtr main_engine_split_ast; - - /* - * To copy partition piece form one cluster to another we have to use Distributed table. - * In case of usage separate table (engine_push) for each partition piece, - * we have to use many Distributed tables. - * */ - ASTs auxiliary_engine_split_asts; - - /// Additional WHERE expression to filter input data - String where_condition_str; - ASTPtr where_condition_ast; - - /// Resolved clusters - ClusterPtr cluster_pull; - ClusterPtr cluster_push; - - /// Filter partitions that should be copied - bool has_enabled_partitions = false; - Strings enabled_partitions; - NameSet enabled_partitions_set; - - /** - * Prioritized list of shards - * all_shards contains information about all shards in the table. - * So we have to check whether particular shard have current partition or not while processing. - */ - TasksShard all_shards; - TasksShard local_shards; - - /// All partitions of the current table. - ClusterPartitions cluster_partitions; - NameSet finished_cluster_partitions; - - /// Partition names to process in user-specified order - Strings ordered_partition_names; - - ClusterPartition & getClusterPartition(const String & partition_name); - - Stopwatch watch; - UInt64 bytes_copied = 0; - UInt64 rows_copied = 0; - - template - void initShards(RandomEngine &&random_engine); -}; - -using TasksTable = std::list; - - -template -inline void TaskTable::initShards(RandomEngine && random_engine) -{ - const String & fqdn_name = getFQDNOrHostName(); - std::uniform_int_distribution get_urand(0, std::numeric_limits::max()); - - // Compute the priority - for (const auto & shard_info : cluster_pull->getShardsInfo()) - { - TaskShardPtr task_shard = std::make_shared(*this, shard_info); - const auto & replicas = cluster_pull->getShardsAddresses().at(task_shard->indexInCluster()); - task_shard->priority = getReplicasPriority(replicas, fqdn_name, get_urand(random_engine)); - - all_shards.emplace_back(task_shard); - } - - // Sort by priority - std::sort(all_shards.begin(), all_shards.end(), - [](const TaskShardPtr & lhs, const TaskShardPtr & rhs) - { - return ShardPriority::greaterPriority(lhs->priority, rhs->priority); - }); - - // Cut local shards - auto it_first_remote = std::lower_bound(all_shards.begin(), all_shards.end(), 1, - [](const TaskShardPtr & lhs, UInt8 is_remote) - { - return lhs->priority.is_remote < is_remote; - }); - - local_shards.assign(all_shards.begin(), it_first_remote); -} - -} diff --git a/programs/copier/ZooKeeperStaff.h b/programs/copier/ZooKeeperStaff.h deleted file mode 100644 index c15db73f060..00000000000 --- a/programs/copier/ZooKeeperStaff.h +++ /dev/null @@ -1,221 +0,0 @@ -#pragma once - -/** Allows to compare two incremental counters of type UInt32 in presence of possible overflow. - * We assume that we compare values that are not too far away. - * For example, when we increment 0xFFFFFFFF, we get 0. So, 0xFFFFFFFF is less than 0. - */ -class WrappingUInt32 -{ -public: - UInt32 value; - - explicit WrappingUInt32(UInt32 _value) - : value(_value) - {} - - bool operator<(const WrappingUInt32 & other) const - { - return value != other.value && *this <= other; - } - - bool operator<=(const WrappingUInt32 & other) const - { - const UInt32 HALF = static_cast(1) << 31; - return (value <= other.value && other.value - value < HALF) - || (value > other.value && value - other.value > HALF); - } - - bool operator==(const WrappingUInt32 & other) const - { - return value == other.value; - } -}; - -/** Conforming Zxid definition. - * cf. https://github.com/apache/zookeeper/blob/631d1b284f0edb1c4f6b0fb221bf2428aec71aaa/zookeeper-docs/src/main/resources/markdown/zookeeperInternals.md#guarantees-properties-and-definitions - * - * But it is better to read this: https://zookeeper.apache.org/doc/r3.1.2/zookeeperProgrammers.html - * - * Actually here is the definition of Zxid. - * Every change to the ZooKeeper state receives a stamp in the form of a zxid (ZooKeeper Transaction Id). - * This exposes the total ordering of all changes to ZooKeeper. Each change will have a unique zxid - * and if zxid1 is smaller than zxid2 then zxid1 happened before zxid2. - */ -class Zxid -{ -public: - WrappingUInt32 epoch; - WrappingUInt32 counter; - explicit Zxid(UInt64 _zxid) - : epoch(static_cast(_zxid >> 32)) - , counter(static_cast(_zxid)) - {} - - bool operator<=(const Zxid & other) const - { - return (epoch < other.epoch) - || (epoch == other.epoch && counter <= other.counter); - } - - bool operator==(const Zxid & other) const - { - return epoch == other.epoch && counter == other.counter; - } -}; - -/* When multiple ClusterCopiers discover that the target partition is not empty, - * they will attempt to clean up this partition before proceeding to copying. - * - * Instead of purging is_dirty, the history of cleaning work is preserved and partition hygiene is established - * based on a happens-before relation between the events. - * This relation is encoded by LogicalClock based on the mzxid of the is_dirty ZNode and is_dirty/cleaned. - * The fact of the partition hygiene is encoded by CleanStateClock. - * - * For you to know what mzxid means: - * - * ZooKeeper Stat Structure: - * The Stat structure for each znode in ZooKeeper is made up of the following fields: - * - * -- czxid - * The zxid of the change that caused this znode to be created. - * - * -- mzxid - * The zxid of the change that last modified this znode. - * - * -- ctime - * The time in milliseconds from epoch when this znode was created. - * - * -- mtime - * The time in milliseconds from epoch when this znode was last modified. - * - * -- version - * The number of changes to the data of this znode. - * - * -- cversion - * The number of changes to the children of this znode. - * - * -- aversion - * The number of changes to the ACL of this znode. - * - * -- ephemeralOwner - * The session id of the owner of this znode if the znode is an ephemeral node. - * If it is not an ephemeral node, it will be zero. - * - * -- dataLength - * The length of the data field of this znode. - * - * -- numChildren - * The number of children of this znode. - * */ - -class LogicalClock -{ -public: - std::optional zxid; - - LogicalClock() = default; - - explicit LogicalClock(UInt64 _zxid) - : zxid(_zxid) - {} - - bool hasHappened() const - { - return bool(zxid); - } - - /// happens-before relation with a reasonable time bound - bool happensBefore(const LogicalClock & other) const - { - return !zxid - || (other.zxid && *zxid <= *other.zxid); - } - - bool operator<=(const LogicalClock & other) const - { - return happensBefore(other); - } - - /// strict equality check - bool operator==(const LogicalClock & other) const - { - return zxid == other.zxid; - } -}; - - -class CleanStateClock -{ -public: - LogicalClock discovery_zxid; - std::optional discovery_version; - - LogicalClock clean_state_zxid; - std::optional clean_state_version; - - std::shared_ptr stale; - - bool is_clean() const - { - return !is_stale() - && (!discovery_zxid.hasHappened() || (clean_state_zxid.hasHappened() && discovery_zxid <= clean_state_zxid)); - } - - bool is_stale() const - { - return stale->load(); - } - - CleanStateClock( - const zkutil::ZooKeeperPtr & zookeeper, - const String & discovery_path, - const String & clean_state_path) - : stale(std::make_shared(false)) - { - Coordination::Stat stat{}; - String _some_data; - auto watch_callback = - [my_stale = stale] (const Coordination::WatchResponse & rsp) - { - auto logger = getLogger("ClusterCopier"); - if (rsp.error == Coordination::Error::ZOK) - { - switch (rsp.type) /// NOLINT(bugprone-switch-missing-default-case) - { - case Coordination::CREATED: - LOG_DEBUG(logger, "CleanStateClock change: CREATED, at {}", rsp.path); - my_stale->store(true); - break; - case Coordination::CHANGED: - LOG_DEBUG(logger, "CleanStateClock change: CHANGED, at {}", rsp.path); - my_stale->store(true); - } - } - }; - if (zookeeper->tryGetWatch(discovery_path, _some_data, &stat, watch_callback)) - { - discovery_zxid = LogicalClock(stat.mzxid); - discovery_version = stat.version; - } - if (zookeeper->tryGetWatch(clean_state_path, _some_data, &stat, watch_callback)) - { - clean_state_zxid = LogicalClock(stat.mzxid); - clean_state_version = stat.version; - } - } - - bool operator==(const CleanStateClock & other) const - { - return !is_stale() - && !other.is_stale() - && discovery_zxid == other.discovery_zxid - && discovery_version == other.discovery_version - && clean_state_zxid == other.clean_state_zxid - && clean_state_version == other.clean_state_version; - } - - bool operator!=(const CleanStateClock & other) const - { - return !(*this == other); - } -}; diff --git a/programs/copier/clickhouse-copier.cpp b/programs/copier/clickhouse-copier.cpp deleted file mode 100644 index 4dabb01775b..00000000000 --- a/programs/copier/clickhouse-copier.cpp +++ /dev/null @@ -1 +0,0 @@ -int mainEntryClickHouseClusterCopier(int argc, char ** argv); diff --git a/programs/diagnostics/testdata/configs/xml/config.xml b/programs/diagnostics/testdata/configs/xml/config.xml index ae09d207091..eb7c70cf498 100644 --- a/programs/diagnostics/testdata/configs/xml/config.xml +++ b/programs/diagnostics/testdata/configs/xml/config.xml @@ -94,7 +94,7 @@ 8123 - - - system -
query_log
- - - 1000 - - \ No newline at end of file diff --git a/tests/integration/test_cluster_copier/configs/config-copier.xml b/tests/integration/test_cluster_copier/configs/config-copier.xml deleted file mode 100644 index 590b1892f8d..00000000000 --- a/tests/integration/test_cluster_copier/configs/config-copier.xml +++ /dev/null @@ -1,11 +0,0 @@ - - - information - /var/log/clickhouse-server/copier/log.log - /var/log/clickhouse-server/copier/log.err.log - 1000M - 10 - /var/log/clickhouse-server/copier/stderr.log - /var/log/clickhouse-server/copier/stdout.log - - diff --git a/tests/integration/test_cluster_copier/configs/users.xml b/tests/integration/test_cluster_copier/configs/users.xml deleted file mode 100644 index b463dfc81e7..00000000000 --- a/tests/integration/test_cluster_copier/configs/users.xml +++ /dev/null @@ -1,34 +0,0 @@ - - - - 1 - - 5 - 1 - - - - - - - - ::/0 - - default - default - - - 12345678 - - ::/0 - - default - default - - - - - - - - diff --git a/tests/integration/test_cluster_copier/configs_three_nodes/conf.d/clusters.xml b/tests/integration/test_cluster_copier/configs_three_nodes/conf.d/clusters.xml deleted file mode 100644 index 9de7b57de27..00000000000 --- a/tests/integration/test_cluster_copier/configs_three_nodes/conf.d/clusters.xml +++ /dev/null @@ -1,27 +0,0 @@ - - - - - false - - first - 9000 - - - - false - - second - 9000 - - - - false - - third - 9000 - - - - - diff --git a/tests/integration/test_cluster_copier/configs_three_nodes/conf.d/ddl.xml b/tests/integration/test_cluster_copier/configs_three_nodes/conf.d/ddl.xml deleted file mode 100644 index 64fa32335ab..00000000000 --- a/tests/integration/test_cluster_copier/configs_three_nodes/conf.d/ddl.xml +++ /dev/null @@ -1,5 +0,0 @@ - - - /clickhouse/task_queue/ddl - - \ No newline at end of file diff --git a/tests/integration/test_cluster_copier/configs_three_nodes/config-copier.xml b/tests/integration/test_cluster_copier/configs_three_nodes/config-copier.xml deleted file mode 100644 index d0cab0fafb7..00000000000 --- a/tests/integration/test_cluster_copier/configs_three_nodes/config-copier.xml +++ /dev/null @@ -1,27 +0,0 @@ - - - information - /var/log/clickhouse-server/copier/log.log - /var/log/clickhouse-server/copier/log.err.log - 1000M - 10 - /var/log/clickhouse-server/copier/stderr.log - /var/log/clickhouse-server/copier/stdout.log - - - - - zoo1 - 2181 - - - zoo2 - 2181 - - - zoo3 - 2181 - - 2000 - - diff --git a/tests/integration/test_cluster_copier/configs_three_nodes/users.xml b/tests/integration/test_cluster_copier/configs_three_nodes/users.xml deleted file mode 100644 index badaf46a5ca..00000000000 --- a/tests/integration/test_cluster_copier/configs_three_nodes/users.xml +++ /dev/null @@ -1,32 +0,0 @@ - - - - 1 - 1 - - - - - - - - ::/0 - - default - default - - - 12345678 - - ::/0 - - default - default - - - - - - - - diff --git a/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/clusters.xml b/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/clusters.xml deleted file mode 100644 index 38d88308631..00000000000 --- a/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/clusters.xml +++ /dev/null @@ -1,22 +0,0 @@ - - - - - false - - first_of_two - 9000 - - - - - - false - - second_of_two - 9000 - - - - - diff --git a/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/ddl.xml b/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/ddl.xml deleted file mode 100644 index 64fa32335ab..00000000000 --- a/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/ddl.xml +++ /dev/null @@ -1,5 +0,0 @@ - - - /clickhouse/task_queue/ddl - - \ No newline at end of file diff --git a/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/storage_configuration.xml b/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/storage_configuration.xml deleted file mode 100644 index 8306f40ad6a..00000000000 --- a/tests/integration/test_cluster_copier/configs_two_nodes/conf.d/storage_configuration.xml +++ /dev/null @@ -1,34 +0,0 @@ - - - - - - - - /jbod1/ - - - /jbod2/ - - - /external/ - - - - - - - - external - -
- jbod1 - jbod2 -
- - - - - - - diff --git a/tests/integration/test_cluster_copier/configs_two_nodes/config-copier.xml b/tests/integration/test_cluster_copier/configs_two_nodes/config-copier.xml deleted file mode 100644 index 55bd24816ae..00000000000 --- a/tests/integration/test_cluster_copier/configs_two_nodes/config-copier.xml +++ /dev/null @@ -1,19 +0,0 @@ - - - information - /var/log/clickhouse-server/copier/log.log - /var/log/clickhouse-server/copier/log.err.log - 1000M - 10 - /var/log/clickhouse-server/copier/stderr.log - /var/log/clickhouse-server/copier/stdout.log - - - - - zoo1 - 2181 - - 2000 - - diff --git a/tests/integration/test_cluster_copier/configs_two_nodes/users.xml b/tests/integration/test_cluster_copier/configs_two_nodes/users.xml deleted file mode 100644 index badaf46a5ca..00000000000 --- a/tests/integration/test_cluster_copier/configs_two_nodes/users.xml +++ /dev/null @@ -1,32 +0,0 @@ - - - - 1 - 1 - - - - - - - - ::/0 - - default - default - - - 12345678 - - ::/0 - - default - default - - - - - - - - diff --git a/tests/integration/test_cluster_copier/task0_description.xml b/tests/integration/test_cluster_copier/task0_description.xml deleted file mode 100644 index 8d74d0bdde0..00000000000 --- a/tests/integration/test_cluster_copier/task0_description.xml +++ /dev/null @@ -1,95 +0,0 @@ - - - 3 - - - - 1 - - - - - 0 - - - - - - - - - - cluster0 - default - hits - - cluster1 - default - hits - - 2 - - 3 4 5 6 1 2 0 - - - ENGINE=ReplicatedMergeTree PARTITION BY d % 3 ORDER BY (d, sipHash64(d)) SAMPLE BY sipHash64(d) SETTINGS index_granularity = 16 - - - d + 1 - - - d - d = 0 - - - - - - - - true - - s0_0_0 - 9000 - - - s0_0_1 - 9000 - - - - true - - s0_1_0 - 9000 - - - - - - - true - - s1_0_0 - 9000 - - - s1_0_1 - 9000 - - - - true - - s1_1_0 - 9000 - - - - 255.255.255.255 - 9000 - - - - - - diff --git a/tests/integration/test_cluster_copier/task_drop_target_partition.xml b/tests/integration/test_cluster_copier/task_drop_target_partition.xml deleted file mode 100644 index dc8e6452243..00000000000 --- a/tests/integration/test_cluster_copier/task_drop_target_partition.xml +++ /dev/null @@ -1,41 +0,0 @@ - - - - - false - - first_of_two - 9000 - - - - - - false - - second_of_two - 9000 - - - - - - 2 - - - - source - db_drop_target_partition - source - - destination - db_drop_target_partition - destination - - true - - ENGINE = MergeTree() PARTITION BY toYYYYMMDD(Column3) ORDER BY (Column3, Column2, Column1) - rand() - - - diff --git a/tests/integration/test_cluster_copier/task_month_to_week_description.xml b/tests/integration/test_cluster_copier/task_month_to_week_description.xml deleted file mode 100644 index bc290ca397f..00000000000 --- a/tests/integration/test_cluster_copier/task_month_to_week_description.xml +++ /dev/null @@ -1,99 +0,0 @@ - - - 4 - - - - 1 - 2 - - - - 0 - - - - - - cluster0 - default - a - - cluster1 - default - b - - - - 2 - - - ENGINE= - ReplicatedMergeTree - PARTITION BY toMonday(date) - ORDER BY d - - - - jumpConsistentHash(intHash64(d), 2) - - - - - - - - - - - true - - s0_0_0 - 9000 - - - s0_0_1 - 9000 - - - - true - - s0_1_0 - 9000 - - - - - - - true - - s1_0_0 - 9000 - - - s1_0_1 - 9000 - - - - true - - s1_1_0 - 9000 - - - - 255.255.255.255 - 9000 - - - - - - diff --git a/tests/integration/test_cluster_copier/task_no_arg.xml b/tests/integration/test_cluster_copier/task_no_arg.xml deleted file mode 100644 index 262ff073537..00000000000 --- a/tests/integration/test_cluster_copier/task_no_arg.xml +++ /dev/null @@ -1,39 +0,0 @@ - - - - - 1 - - s0_0_0 - 9000 - - - - - - - 1 - - s1_1_0 - 9000 - - - - - - 1 - - - - source_cluster - default - copier_test1 - - default_cluster - default - copier_test1_1 - ENGINE = MergeTree PARTITION BY date ORDER BY (date, sipHash64(date)) SAMPLE BY sipHash64(date) - rand() - - - diff --git a/tests/integration/test_cluster_copier/task_no_index.xml b/tests/integration/test_cluster_copier/task_no_index.xml deleted file mode 100644 index 265f99e21a6..00000000000 --- a/tests/integration/test_cluster_copier/task_no_index.xml +++ /dev/null @@ -1,109 +0,0 @@ - - - - - false - - s0_0_0 - 9000 - - - - - - - false - - s1_1_0 - 9000 - - - - - - - 2 - - - - 1 - - - - - 0 - - - - - 3 - - 1 - - - - - - - - source_cluster - default - ontime - - - - destination_cluster - default - ontime22 - - - - - - - ENGINE = MergeTree() PARTITION BY Year ORDER BY (Year, FlightDate) SETTINGS index_granularity=8192 - - - - - jumpConsistentHash(intHash64(Year), 2) - - - - - - - 2017 - - - - - - - diff --git a/tests/integration/test_cluster_copier/task_non_partitioned_table.xml b/tests/integration/test_cluster_copier/task_non_partitioned_table.xml deleted file mode 100644 index d5424b95f45..00000000000 --- a/tests/integration/test_cluster_copier/task_non_partitioned_table.xml +++ /dev/null @@ -1,39 +0,0 @@ - - - - - 1 - - s0_0_0 - 9000 - - - - - - - 1 - - s1_1_0 - 9000 - - - - - - 1 - - - - source_cluster - default - copier_test1 - - default_cluster - default - copier_test1_1 - ENGINE = MergeTree ORDER BY date SETTINGS index_granularity = 8192 - rand() - - - diff --git a/tests/integration/test_cluster_copier/task_self_copy.xml b/tests/integration/test_cluster_copier/task_self_copy.xml deleted file mode 100644 index 21d577bc397..00000000000 --- a/tests/integration/test_cluster_copier/task_self_copy.xml +++ /dev/null @@ -1,63 +0,0 @@ - - 9440 - - - - false - - s0_0_0 - 9000 - dbuser - 12345678 - 0 - - - - - - - false - - s0_0_0 - 9000 - dbuser - 12345678 - 0 - - - - - - 2 - - - 1 - - - - 0 - - - - 3 - 1 - - - - - source_cluster - db1 - source_table - - destination_cluster - db2 - destination_table - - - ENGINE = MergeTree PARTITION BY a ORDER BY a SETTINGS index_granularity = 8192 - - - rand() - - - \ No newline at end of file diff --git a/tests/integration/test_cluster_copier/task_skip_index.xml b/tests/integration/test_cluster_copier/task_skip_index.xml deleted file mode 100644 index b04cec963d4..00000000000 --- a/tests/integration/test_cluster_copier/task_skip_index.xml +++ /dev/null @@ -1,39 +0,0 @@ - - - - - false - - first_of_two - 9000 - - - - - - false - - second_of_two - 9000 - - - - - - 2 - - - - source - db_skip_index - source - - destination - db_skip_index - destination - - ENGINE = MergeTree() PARTITION BY toYYYYMMDD(Column3) ORDER BY (Column3, Column2, Column1) - rand() - - - diff --git a/tests/integration/test_cluster_copier/task_taxi_data.xml b/tests/integration/test_cluster_copier/task_taxi_data.xml deleted file mode 100644 index 94fa5087338..00000000000 --- a/tests/integration/test_cluster_copier/task_taxi_data.xml +++ /dev/null @@ -1,42 +0,0 @@ - - - - - false - - first - 9000 - - - - false - - second - 9000 - - - - false - - third - 9000 - - - - - - 2 - - - - events - dailyhistory - yellow_tripdata_staging - events - monthlyhistory - yellow_tripdata_staging - Engine=ReplacingMergeTree() PRIMARY KEY (tpep_pickup_datetime, id) ORDER BY (tpep_pickup_datetime, id) PARTITION BY (pickup_location_id, toYYYYMM(tpep_pickup_datetime)) - sipHash64(id) % 3 - - - \ No newline at end of file diff --git a/tests/integration/test_cluster_copier/task_test_block_size.xml b/tests/integration/test_cluster_copier/task_test_block_size.xml deleted file mode 100644 index bf29c7e1832..00000000000 --- a/tests/integration/test_cluster_copier/task_test_block_size.xml +++ /dev/null @@ -1,101 +0,0 @@ - - - 1 - - - - 1 - - - - - - - - - shard_0_0 - default - test_block_size - - cluster1 - default - test_block_size - - - '1970-01-01' - - - - ENGINE= - ReplicatedMergeTree - ORDER BY d PARTITION BY partition - - - - jumpConsistentHash(intHash64(d), 2) - - - - - - - - - - - true - - s0_0_0 - 9000 - - - s0_0_1 - 9000 - - - - true - - s0_1_0 - 9000 - - - - - - - true - - s1_0_0 - 9000 - - - s1_0_1 - 9000 - - - - true - - s1_1_0 - 9000 - - - - - - - true - - s0_0_0 - 9000 - - - s0_0_1 - 9000 - - - - - - diff --git a/tests/integration/test_cluster_copier/task_trivial.xml b/tests/integration/test_cluster_copier/task_trivial.xml deleted file mode 100644 index a3b8bc03888..00000000000 --- a/tests/integration/test_cluster_copier/task_trivial.xml +++ /dev/null @@ -1,63 +0,0 @@ - - - 3 - - - - 1 - - - - - 0 - - - - - - - - - - source_trivial_cluster - default - trivial - - destination_trivial_cluster - default - trivial - - - ENGINE=ReplicatedMergeTree('/clickhouse/tables/cluster{cluster}/{shard}/hits', '{replica}') PARTITION BY d % 5 ORDER BY (d, sipHash64(d)) SAMPLE BY sipHash64(d) SETTINGS index_granularity = 16 - - - d + 1 - - - d - d = 0 - - - - - - - - - first_trivial - 9000 - - - - - - - - - second_trivial - 9000 - - - - - - diff --git a/tests/integration/test_cluster_copier/task_trivial_without_arguments.xml b/tests/integration/test_cluster_copier/task_trivial_without_arguments.xml deleted file mode 100644 index 0197dee0181..00000000000 --- a/tests/integration/test_cluster_copier/task_trivial_without_arguments.xml +++ /dev/null @@ -1,63 +0,0 @@ - - - 3 - - - - 1 - - - - - 0 - - - - - - - - - - source_trivial_cluster - default - trivial_without_arguments - - destination_trivial_cluster - default - trivial_without_arguments - - - ENGINE=ReplicatedMergeTree() PARTITION BY d % 5 ORDER BY (d, sipHash64(d)) SAMPLE BY sipHash64(d) SETTINGS index_granularity = 16 - - - d + 1 - - - d - d = 0 - - - - - - - - - first_trivial - 9000 - - - - - - - - - second_trivial - 9000 - - - - - - diff --git a/tests/integration/test_cluster_copier/task_ttl_columns.xml b/tests/integration/test_cluster_copier/task_ttl_columns.xml deleted file mode 100644 index 2069c509c87..00000000000 --- a/tests/integration/test_cluster_copier/task_ttl_columns.xml +++ /dev/null @@ -1,39 +0,0 @@ - - - - - false - - first_of_two - 9000 - - - - - - false - - second_of_two - 9000 - - - - - - 2 - - - - source - db_ttl_columns - source - - destination - db_ttl_columns - destination - - ENGINE = MergeTree() PARTITION BY toYYYYMMDD(Column3) ORDER BY (Column3, Column2, Column1) - rand() - - - diff --git a/tests/integration/test_cluster_copier/task_ttl_move_to_volume.xml b/tests/integration/test_cluster_copier/task_ttl_move_to_volume.xml deleted file mode 100644 index 2a51fa7a66d..00000000000 --- a/tests/integration/test_cluster_copier/task_ttl_move_to_volume.xml +++ /dev/null @@ -1,39 +0,0 @@ - - - - - false - - first_of_two - 9000 - - - - - - false - - second_of_two - 9000 - - - - - - 2 - - - - source - db_move_to_volume - source - - destination - db_move_to_volume - destination - - ENGINE = MergeTree() PARTITION BY toYYYYMMDD(Column3) ORDER BY (Column3, Column2, Column1) TTL Column3 + INTERVAL 1 MONTH TO VOLUME 'external' SETTINGS storage_policy = 'external_with_jbods' - rand() - - - diff --git a/tests/integration/test_cluster_copier/task_with_different_schema.xml b/tests/integration/test_cluster_copier/task_with_different_schema.xml deleted file mode 100644 index e1e6ee4dc42..00000000000 --- a/tests/integration/test_cluster_copier/task_with_different_schema.xml +++ /dev/null @@ -1,39 +0,0 @@ - - - - - false - - first_of_two - 9000 - - - - - - false - - second_of_two - 9000 - - - - - - 2 - - - - source - db_different_schema - source - - destination - db_different_schema - destination - - ENGINE = MergeTree() PARTITION BY toYYYYMMDD(Column3) ORDER BY (Column9, Column1, Column2, Column3, Column4) - rand() - - - diff --git a/tests/integration/test_cluster_copier/test.py b/tests/integration/test_cluster_copier/test.py deleted file mode 100644 index be71fc21e33..00000000000 --- a/tests/integration/test_cluster_copier/test.py +++ /dev/null @@ -1,653 +0,0 @@ -import os -import random -import sys -import time -import kazoo -import pytest -import string -import random -from contextlib import contextmanager -from helpers.cluster import ClickHouseCluster -from helpers.test_tools import TSV - -import docker - -CURRENT_TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -sys.path.insert(0, os.path.dirname(CURRENT_TEST_DIR)) - -COPYING_FAIL_PROBABILITY = 0.2 -MOVING_FAIL_PROBABILITY = 0.2 - -cluster = ClickHouseCluster(__file__) - - -def generateRandomString(count): - return "".join( - random.choice(string.ascii_uppercase + string.digits) for _ in range(count) - ) - - -def check_all_hosts_sucesfully_executed(tsv_content, num_hosts): - M = TSV.toMat(tsv_content) - hosts = [(l[0], l[1]) for l in M] # (host, port) - codes = [l[2] for l in M] - - assert len(hosts) == num_hosts and len(set(hosts)) == num_hosts, "\n" + tsv_content - assert len(set(codes)) == 1, "\n" + tsv_content - assert codes[0] == "0", "\n" + tsv_content - - -def ddl_check_query(instance, query, num_hosts=3): - contents = instance.query(query) - check_all_hosts_sucesfully_executed(contents, num_hosts) - return contents - - -@pytest.fixture(scope="module") -def started_cluster(): - global cluster - try: - clusters_schema = { - "0": {"0": ["0", "1"], "1": ["0"]}, - "1": {"0": ["0", "1"], "1": ["0"]}, - } - - for cluster_name, shards in clusters_schema.items(): - for shard_name, replicas in shards.items(): - for replica_name in replicas: - name = "s{}_{}_{}".format(cluster_name, shard_name, replica_name) - cluster.add_instance( - name, - main_configs=[ - "configs/conf.d/query_log.xml", - "configs/conf.d/ddl.xml", - "configs/conf.d/clusters.xml", - ], - user_configs=["configs/users.xml"], - macros={ - "cluster": cluster_name, - "shard": shard_name, - "replica": replica_name, - }, - with_zookeeper=True, - ) - - cluster.start() - yield cluster - - finally: - cluster.shutdown() - - -class Task1: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_simple_" + generateRandomString(10) - self.container_task_file = "/task0_description.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task0_description.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - instance = cluster.instances["s0_0_0"] - - for cluster_num in ["0", "1"]: - ddl_check_query( - instance, - "DROP DATABASE IF EXISTS default ON CLUSTER cluster{} SYNC".format( - cluster_num - ), - ) - ddl_check_query( - instance, - "CREATE DATABASE default ON CLUSTER cluster{} ".format(cluster_num), - ) - - ddl_check_query( - instance, - "CREATE TABLE hits ON CLUSTER cluster0 (d UInt64, d1 UInt64 MATERIALIZED d+1) " - + "ENGINE=ReplicatedMergeTree " - + "PARTITION BY d % 3 ORDER BY (d, sipHash64(d)) SAMPLE BY sipHash64(d) SETTINGS index_granularity = 16", - ) - ddl_check_query( - instance, - "CREATE TABLE hits_all ON CLUSTER cluster0 (d UInt64) ENGINE=Distributed(cluster0, default, hits, d)", - ) - ddl_check_query( - instance, - "CREATE TABLE hits_all ON CLUSTER cluster1 (d UInt64) ENGINE=Distributed(cluster1, default, hits, d + 1)", - ) - instance.query( - "INSERT INTO hits_all SELECT * FROM system.numbers LIMIT 1002", - settings={"distributed_foreground_insert": 1}, - ) - - def check(self): - assert ( - self.cluster.instances["s0_0_0"] - .query("SELECT count() FROM hits_all") - .strip() - == "1002" - ) - assert ( - self.cluster.instances["s1_0_0"] - .query("SELECT count() FROM hits_all") - .strip() - == "1002" - ) - - assert ( - self.cluster.instances["s1_0_0"] - .query("SELECT DISTINCT d % 2 FROM hits") - .strip() - == "1" - ) - assert ( - self.cluster.instances["s1_1_0"] - .query("SELECT DISTINCT d % 2 FROM hits") - .strip() - == "0" - ) - - instance = self.cluster.instances["s0_0_0"] - ddl_check_query(instance, "DROP TABLE hits_all ON CLUSTER cluster0") - ddl_check_query(instance, "DROP TABLE hits_all ON CLUSTER cluster1") - ddl_check_query(instance, "DROP TABLE hits ON CLUSTER cluster0") - ddl_check_query(instance, "DROP TABLE hits ON CLUSTER cluster1") - - -class Task2: - def __init__(self, cluster, unique_zk_path): - self.cluster = cluster - self.zk_task_path = ( - "/clickhouse-copier/task_month_to_week_partition_" + generateRandomString(5) - ) - self.unique_zk_path = generateRandomString(10) - self.container_task_file = "/task_month_to_week_description.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_month_to_week_description.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - instance = cluster.instances["s0_0_0"] - - for cluster_num in ["0", "1"]: - ddl_check_query( - instance, - "DROP DATABASE IF EXISTS default ON CLUSTER cluster{}".format( - cluster_num - ), - ) - ddl_check_query( - instance, - "CREATE DATABASE IF NOT EXISTS default ON CLUSTER cluster{}".format( - cluster_num - ), - ) - - ddl_check_query( - instance, - "CREATE TABLE a ON CLUSTER cluster0 (date Date, d UInt64, d1 UInt64 ALIAS d+1) " - "ENGINE=ReplicatedMergeTree('/clickhouse/tables/cluster_{cluster}/{shard}/" - + self.unique_zk_path - + "', " - "'{replica}', date, intHash64(d), (date, intHash64(d)), 8192)", - ) - ddl_check_query( - instance, - "CREATE TABLE a_all ON CLUSTER cluster0 (date Date, d UInt64) ENGINE=Distributed(cluster0, default, a, d)", - ) - - instance.query( - "INSERT INTO a_all SELECT toDate(17581 + number) AS date, number AS d FROM system.numbers LIMIT 85", - settings={"distributed_foreground_insert": 1}, - ) - - def check(self): - assert TSV( - self.cluster.instances["s0_0_0"].query( - "SELECT count() FROM cluster(cluster0, default, a)" - ) - ) == TSV("85\n") - assert TSV( - self.cluster.instances["s1_0_0"].query( - "SELECT count(), uniqExact(date) FROM cluster(cluster1, default, b)" - ) - ) == TSV("85\t85\n") - - assert TSV( - self.cluster.instances["s1_0_0"].query( - "SELECT DISTINCT jumpConsistentHash(intHash64(d), 2) FROM b" - ) - ) == TSV("0\n") - assert TSV( - self.cluster.instances["s1_1_0"].query( - "SELECT DISTINCT jumpConsistentHash(intHash64(d), 2) FROM b" - ) - ) == TSV("1\n") - - assert TSV( - self.cluster.instances["s1_0_0"].query( - "SELECT uniqExact(partition) IN (12, 13) FROM system.parts WHERE active AND database='default' AND table='b'" - ) - ) == TSV("1\n") - assert TSV( - self.cluster.instances["s1_1_0"].query( - "SELECT uniqExact(partition) IN (12, 13) FROM system.parts WHERE active AND database='default' AND table='b'" - ) - ) == TSV("1\n") - - instance = cluster.instances["s0_0_0"] - ddl_check_query(instance, "DROP TABLE a ON CLUSTER cluster0") - ddl_check_query(instance, "DROP TABLE b ON CLUSTER cluster1") - - -class Task_test_block_size: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = ( - "/clickhouse-copier/task_test_block_size_" + generateRandomString(5) - ) - self.rows = 1000000 - self.container_task_file = "/task_test_block_size.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_test_block_size.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - instance = cluster.instances["s0_0_0"] - - ddl_check_query( - instance, - """ - CREATE TABLE test_block_size ON CLUSTER shard_0_0 (partition Date, d UInt64) - ENGINE=ReplicatedMergeTree - ORDER BY (d, sipHash64(d)) SAMPLE BY sipHash64(d)""", - 2, - ) - - instance.query( - "INSERT INTO test_block_size SELECT toDate(0) AS partition, number as d FROM system.numbers LIMIT {}".format( - self.rows - ) - ) - - def check(self): - assert TSV( - self.cluster.instances["s1_0_0"].query( - "SELECT count() FROM cluster(cluster1, default, test_block_size)" - ) - ) == TSV("{}\n".format(self.rows)) - - instance = cluster.instances["s0_0_0"] - ddl_check_query(instance, "DROP TABLE test_block_size ON CLUSTER shard_0_0", 2) - ddl_check_query(instance, "DROP TABLE test_block_size ON CLUSTER cluster1") - - -class Task_no_index: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_no_index_" + generateRandomString( - 5 - ) - self.rows = 1000000 - self.container_task_file = "/task_no_index.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_no_index.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - instance = cluster.instances["s0_0_0"] - instance.query("DROP TABLE IF EXISTS ontime SYNC") - instance.query( - "create table IF NOT EXISTS ontime (Year UInt16, FlightDate String) ENGINE = Memory" - ) - instance.query( - "insert into ontime values (2016, 'test6'), (2017, 'test7'), (2018, 'test8')" - ) - - def check(self): - assert TSV( - self.cluster.instances["s1_1_0"].query("SELECT Year FROM ontime22") - ) == TSV("2017\n") - instance = cluster.instances["s0_0_0"] - instance.query("DROP TABLE ontime") - instance = cluster.instances["s1_1_0"] - instance.query("DROP TABLE ontime22") - - -class Task_no_arg: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_no_arg" - self.rows = 1000000 - self.container_task_file = "/task_no_arg.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_no_arg.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - instance = cluster.instances["s0_0_0"] - instance.query("DROP TABLE IF EXISTS copier_test1 SYNC") - instance.query( - "create table if not exists copier_test1 (date Date, id UInt32) engine = MergeTree PARTITION BY date ORDER BY date SETTINGS index_granularity = 8192" - ) - instance.query("insert into copier_test1 values ('2016-01-01', 10);") - - def check(self): - assert TSV( - self.cluster.instances["s1_1_0"].query("SELECT date FROM copier_test1_1") - ) == TSV("2016-01-01\n") - instance = cluster.instances["s0_0_0"] - instance.query("DROP TABLE copier_test1 SYNC") - instance = cluster.instances["s1_1_0"] - instance.query("DROP TABLE copier_test1_1 SYNC") - - -class Task_non_partitioned_table: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_non_partitoned_table" - self.rows = 1000000 - self.container_task_file = "/task_non_partitioned_table.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_non_partitioned_table.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - instance = cluster.instances["s0_0_0"] - instance.query("DROP TABLE IF EXISTS copier_test1 SYNC") - instance.query( - "create table copier_test1 (date Date, id UInt32) engine = MergeTree ORDER BY date SETTINGS index_granularity = 8192" - ) - instance.query("insert into copier_test1 values ('2016-01-01', 10);") - - def check(self): - assert TSV( - self.cluster.instances["s1_1_0"].query("SELECT date FROM copier_test1_1") - ) == TSV("2016-01-01\n") - instance = cluster.instances["s0_0_0"] - instance.query("DROP TABLE copier_test1") - instance = cluster.instances["s1_1_0"] - instance.query("DROP TABLE copier_test1_1") - - -class Task_self_copy: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_self_copy" - self.container_task_file = "/task_self_copy.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_self_copy.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - instance = cluster.instances["s0_0_0"] - instance.query("DROP DATABASE IF EXISTS db1 SYNC") - instance.query("DROP DATABASE IF EXISTS db2 SYNC") - instance.query("CREATE DATABASE IF NOT EXISTS db1;") - instance.query( - "CREATE TABLE IF NOT EXISTS db1.source_table (`a` Int8, `b` String, `c` Int8) ENGINE = MergeTree PARTITION BY a ORDER BY a SETTINGS index_granularity = 8192" - ) - instance.query("CREATE DATABASE IF NOT EXISTS db2;") - instance.query( - "CREATE TABLE IF NOT EXISTS db2.destination_table (`a` Int8, `b` String, `c` Int8) ENGINE = MergeTree PARTITION BY a ORDER BY a SETTINGS index_granularity = 8192" - ) - instance.query("INSERT INTO db1.source_table VALUES (1, 'ClickHouse', 1);") - instance.query("INSERT INTO db1.source_table VALUES (2, 'Copier', 2);") - - def check(self): - instance = cluster.instances["s0_0_0"] - assert TSV( - instance.query("SELECT * FROM db2.destination_table ORDER BY a") - ) == TSV(instance.query("SELECT * FROM db1.source_table ORDER BY a")) - instance = cluster.instances["s0_0_0"] - instance.query("DROP DATABASE IF EXISTS db1 SYNC") - instance.query("DROP DATABASE IF EXISTS db2 SYNC") - - -def execute_task(started_cluster, task, cmd_options): - task.start() - - zk = started_cluster.get_kazoo_client("zoo1") - print("Use ZooKeeper server: {}:{}".format(zk.hosts[0][0], zk.hosts[0][1])) - - try: - zk.delete("/clickhouse-copier", recursive=True) - except kazoo.exceptions.NoNodeError: - print("No node /clickhouse-copier. It is Ok in first test.") - - # Run cluster-copier processes on each node - docker_api = started_cluster.docker_client.api - copiers_exec_ids = [] - - cmd = [ - "/usr/bin/clickhouse", - "copier", - "--config", - "/etc/clickhouse-server/config-copier.xml", - "--task-path", - task.zk_task_path, - "--task-file", - task.container_task_file, - "--task-upload-force", - "true", - "--base-dir", - "/var/log/clickhouse-server/copier", - ] - cmd += cmd_options - - print(cmd) - - copiers = random.sample(list(started_cluster.instances.keys()), 3) - - for instance_name in copiers: - instance = started_cluster.instances[instance_name] - container = instance.get_docker_handle() - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "configs/config-copier.xml"), - "/etc/clickhouse-server/config-copier.xml", - ) - print("Copied copier config to {}".format(instance.name)) - exec_id = docker_api.exec_create(container.id, cmd, stderr=True) - output = docker_api.exec_start(exec_id).decode("utf8") - print(output) - copiers_exec_ids.append(exec_id) - print( - "Copier for {} ({}) has started".format(instance.name, instance.ip_address) - ) - - # Wait for copiers stopping and check their return codes - for exec_id, instance_name in zip(copiers_exec_ids, copiers): - instance = started_cluster.instances[instance_name] - while True: - res = docker_api.exec_inspect(exec_id) - if not res["Running"]: - break - time.sleep(0.5) - - assert res["ExitCode"] == 0, "Instance: {} ({}). Info: {}".format( - instance.name, instance.ip_address, repr(res) - ) - - try: - task.check() - finally: - zk.delete(task.zk_task_path, recursive=True) - - -# Tests - - -@pytest.mark.parametrize(("use_sample_offset"), [False, True]) -def test_copy_simple(started_cluster, use_sample_offset): - if use_sample_offset: - execute_task( - started_cluster, - Task1(started_cluster), - ["--experimental-use-sample-offset", "1"], - ) - else: - execute_task(started_cluster, Task1(started_cluster), []) - - -@pytest.mark.parametrize(("use_sample_offset"), [False, True]) -def test_copy_with_recovering(started_cluster, use_sample_offset): - if use_sample_offset: - execute_task( - started_cluster, - Task1(started_cluster), - [ - "--copy-fault-probability", - str(COPYING_FAIL_PROBABILITY), - "--experimental-use-sample-offset", - "1", - "--max-table-tries", - "10", - ], - ) - else: - execute_task( - started_cluster, - Task1(started_cluster), - [ - "--copy-fault-probability", - str(COPYING_FAIL_PROBABILITY), - "--max-table-tries", - "10", - ], - ) - - -@pytest.mark.parametrize(("use_sample_offset"), [False, True]) -def test_copy_with_recovering_after_move_faults(started_cluster, use_sample_offset): - if use_sample_offset: - execute_task( - started_cluster, - Task1(started_cluster), - [ - "--move-fault-probability", - str(MOVING_FAIL_PROBABILITY), - "--experimental-use-sample-offset", - "1", - ], - ) - else: - execute_task( - started_cluster, - Task1(started_cluster), - ["--move-fault-probability", str(MOVING_FAIL_PROBABILITY)], - ) - - -@pytest.mark.timeout(600) -def test_copy_month_to_week_partition(started_cluster): - execute_task(started_cluster, Task2(started_cluster, "test1"), []) - - -@pytest.mark.timeout(600) -def test_copy_month_to_week_partition_with_recovering(started_cluster): - execute_task( - started_cluster, - Task2(started_cluster, "test2"), - [ - "--copy-fault-probability", - str(COPYING_FAIL_PROBABILITY), - "--max-table-tries", - "10", - ], - ) - - -@pytest.mark.timeout(600) -def test_copy_month_to_week_partition_with_recovering_after_move_faults( - started_cluster, -): - execute_task( - started_cluster, - Task2(started_cluster, "test3"), - ["--move-fault-probability", str(MOVING_FAIL_PROBABILITY)], - ) - - -def test_block_size(started_cluster): - execute_task(started_cluster, Task_test_block_size(started_cluster), []) - - -def test_no_index(started_cluster): - execute_task(started_cluster, Task_no_index(started_cluster), []) - - -def test_no_arg(started_cluster): - execute_task(started_cluster, Task_no_arg(started_cluster), []) - - -def test_non_partitioned_table(started_cluster): - execute_task(started_cluster, Task_non_partitioned_table(started_cluster), []) - - -def test_self_copy(started_cluster): - execute_task(started_cluster, Task_self_copy(started_cluster), []) diff --git a/tests/integration/test_cluster_copier/test_three_nodes.py b/tests/integration/test_cluster_copier/test_three_nodes.py deleted file mode 100644 index e7d07757adb..00000000000 --- a/tests/integration/test_cluster_copier/test_three_nodes.py +++ /dev/null @@ -1,286 +0,0 @@ -import os -import sys -import time -import logging -import pytest - -from helpers.cluster import ClickHouseCluster -from helpers.test_tools import TSV - -import docker - -CURRENT_TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -sys.path.insert(0, os.path.dirname(CURRENT_TEST_DIR)) - -cluster = ClickHouseCluster(__file__) - - -@pytest.fixture(scope="module") -def started_cluster(): - global cluster - try: - for name in ["first", "second", "third"]: - cluster.add_instance( - name, - main_configs=[ - "configs_three_nodes/conf.d/clusters.xml", - "configs_three_nodes/conf.d/ddl.xml", - ], - user_configs=["configs_three_nodes/users.xml"], - with_zookeeper=True, - ) - - cluster.start() - yield cluster - - finally: - cluster.shutdown() - - -class Task: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task" - self.container_task_file = "/task_taxi_data.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_taxi_data.xml"), - self.container_task_file, - ) - logging.debug( - f"Copied task file to container of '{instance_name}' instance. Path {self.container_task_file}" - ) - - def start(self): - for name in ["first", "second", "third"]: - node = cluster.instances[name] - node.query("DROP DATABASE IF EXISTS dailyhistory SYNC;") - node.query("DROP DATABASE IF EXISTS monthlyhistory SYNC;") - - first = cluster.instances["first"] - - # daily partition database - first.query("CREATE DATABASE IF NOT EXISTS dailyhistory on cluster events;") - first.query( - """CREATE TABLE dailyhistory.yellow_tripdata_staging ON CLUSTER events - ( - id UUID DEFAULT generateUUIDv4(), - vendor_id String, - tpep_pickup_datetime DateTime('UTC'), - tpep_dropoff_datetime DateTime('UTC'), - passenger_count Nullable(Float64), - trip_distance String, - pickup_longitude Float64, - pickup_latitude Float64, - rate_code_id String, - store_and_fwd_flag String, - dropoff_longitude Float64, - dropoff_latitude Float64, - payment_type String, - fare_amount String, - extra String, - mta_tax String, - tip_amount String, - tolls_amount String, - improvement_surcharge String, - total_amount String, - pickup_location_id String, - dropoff_location_id String, - congestion_surcharge String, - junk1 String, junk2 String - ) - Engine = ReplacingMergeTree() - PRIMARY KEY (tpep_pickup_datetime, id) - ORDER BY (tpep_pickup_datetime, id) - PARTITION BY (toYYYYMMDD(tpep_pickup_datetime))""" - ) - - first.query( - """CREATE TABLE dailyhistory.yellow_tripdata - ON CLUSTER events - AS dailyhistory.yellow_tripdata_staging - ENGINE = Distributed('events', 'dailyhistory', yellow_tripdata_staging, sipHash64(id) % 3);""" - ) - - first.query( - """INSERT INTO dailyhistory.yellow_tripdata - SELECT * FROM generateRandom( - 'id UUID DEFAULT generateUUIDv4(), - vendor_id String, - tpep_pickup_datetime DateTime(\\'UTC\\'), - tpep_dropoff_datetime DateTime(\\'UTC\\'), - passenger_count Nullable(Float64), - trip_distance String, - pickup_longitude Float64, - pickup_latitude Float64, - rate_code_id String, - store_and_fwd_flag String, - dropoff_longitude Float64, - dropoff_latitude Float64, - payment_type String, - fare_amount String, - extra String, - mta_tax String, - tip_amount String, - tolls_amount String, - improvement_surcharge String, - total_amount String, - pickup_location_id String, - dropoff_location_id String, - congestion_surcharge String, - junk1 String, - junk2 String', - 1, 10, 2) LIMIT 50;""" - ) - - # monthly partition database - first.query("create database IF NOT EXISTS monthlyhistory on cluster events;") - first.query( - """CREATE TABLE monthlyhistory.yellow_tripdata_staging ON CLUSTER events - ( - id UUID DEFAULT generateUUIDv4(), - vendor_id String, - tpep_pickup_datetime DateTime('UTC'), - tpep_dropoff_datetime DateTime('UTC'), - passenger_count Nullable(Float64), - trip_distance String, - pickup_longitude Float64, - pickup_latitude Float64, - rate_code_id String, - store_and_fwd_flag String, - dropoff_longitude Float64, - dropoff_latitude Float64, - payment_type String, - fare_amount String, - extra String, - mta_tax String, - tip_amount String, - tolls_amount String, - improvement_surcharge String, - total_amount String, - pickup_location_id String, - dropoff_location_id String, - congestion_surcharge String, - junk1 String, - junk2 String - ) - Engine = ReplacingMergeTree() - PRIMARY KEY (tpep_pickup_datetime, id) - ORDER BY (tpep_pickup_datetime, id) - PARTITION BY (pickup_location_id, toYYYYMM(tpep_pickup_datetime))""" - ) - - first.query( - """CREATE TABLE monthlyhistory.yellow_tripdata - ON CLUSTER events - AS monthlyhistory.yellow_tripdata_staging - ENGINE = Distributed('events', 'monthlyhistory', yellow_tripdata_staging, sipHash64(id) % 3);""" - ) - - def check(self): - first = cluster.instances["first"] - a = TSV(first.query("SELECT count() from dailyhistory.yellow_tripdata")) - b = TSV(first.query("SELECT count() from monthlyhistory.yellow_tripdata")) - assert a == b, "Distributed tables" - - for instance_name, instance in cluster.instances.items(): - instance = cluster.instances[instance_name] - a = instance.query( - "SELECT count() from dailyhistory.yellow_tripdata_staging" - ) - b = instance.query( - "SELECT count() from monthlyhistory.yellow_tripdata_staging" - ) - assert a == b, "MergeTree tables on each shard" - - a = TSV( - instance.query( - "SELECT sipHash64(*) from dailyhistory.yellow_tripdata_staging ORDER BY id" - ) - ) - b = TSV( - instance.query( - "SELECT sipHash64(*) from monthlyhistory.yellow_tripdata_staging ORDER BY id" - ) - ) - - assert a == b, "Data on each shard" - - for name in ["first", "second", "third"]: - node = cluster.instances[name] - node.query("DROP DATABASE IF EXISTS dailyhistory SYNC;") - node.query("DROP DATABASE IF EXISTS monthlyhistory SYNC;") - - -def execute_task(started_cluster, task, cmd_options): - task.start() - - zk = started_cluster.get_kazoo_client("zoo1") - logging.debug("Use ZooKeeper server: {}:{}".format(zk.hosts[0][0], zk.hosts[0][1])) - - # Run cluster-copier processes on each node - docker_api = started_cluster.docker_client.api - copiers_exec_ids = [] - - cmd = [ - "/usr/bin/clickhouse", - "copier", - "--config", - "/etc/clickhouse-server/config-copier.xml", - "--task-path", - task.zk_task_path, - "--task-file", - task.container_task_file, - "--task-upload-force", - "true", - "--base-dir", - "/var/log/clickhouse-server/copier", - ] - cmd += cmd_options - - logging.debug(f"execute_task cmd: {cmd}") - - for instance_name in started_cluster.instances.keys(): - instance = started_cluster.instances[instance_name] - container = instance.get_docker_handle() - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "configs_three_nodes/config-copier.xml"), - "/etc/clickhouse-server/config-copier.xml", - ) - logging.info("Copied copier config to {}".format(instance.name)) - exec_id = docker_api.exec_create(container.id, cmd, stderr=True) - output = docker_api.exec_start(exec_id).decode("utf8") - logging.info(output) - copiers_exec_ids.append(exec_id) - logging.info( - "Copier for {} ({}) has started".format(instance.name, instance.ip_address) - ) - - # time.sleep(1000) - - # Wait for copiers stopping and check their return codes - for exec_id, instance in zip( - copiers_exec_ids, iter(started_cluster.instances.values()) - ): - while True: - res = docker_api.exec_inspect(exec_id) - if not res["Running"]: - break - time.sleep(1) - - assert res["ExitCode"] == 0, "Instance: {} ({}). Info: {}".format( - instance.name, instance.ip_address, repr(res) - ) - - try: - task.check() - finally: - zk.delete(task.zk_task_path, recursive=True) - - -# Tests -@pytest.mark.timeout(600) -def test(started_cluster): - execute_task(started_cluster, Task(started_cluster), []) diff --git a/tests/integration/test_cluster_copier/test_trivial.py b/tests/integration/test_cluster_copier/test_trivial.py deleted file mode 100644 index b8060583ef8..00000000000 --- a/tests/integration/test_cluster_copier/test_trivial.py +++ /dev/null @@ -1,227 +0,0 @@ -import os -import sys -import time -import random -import string - -from helpers.cluster import ClickHouseCluster -from helpers.test_tools import TSV - -import kazoo -import pytest -import docker - - -CURRENT_TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -sys.path.insert(0, os.path.dirname(CURRENT_TEST_DIR)) - - -COPYING_FAIL_PROBABILITY = 0.1 -MOVING_FAIL_PROBABILITY = 0.1 - -cluster = ClickHouseCluster(__file__) - - -def generateRandomString(count): - return "".join( - random.choice(string.ascii_uppercase + string.digits) for _ in range(count) - ) - - -@pytest.fixture(scope="module") -def started_cluster(): - global cluster - try: - for name in ["first_trivial", "second_trivial"]: - instance = cluster.add_instance( - name, - main_configs=["configs/conf.d/clusters_trivial.xml"], - user_configs=["configs_two_nodes/users.xml"], - macros={ - "cluster": name, - "shard": "the_only_shard", - "replica": "the_only_replica", - }, - with_zookeeper=True, - ) - - cluster.start() - yield cluster - - finally: - cluster.shutdown() - - -class TaskTrivial: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_trivial" - self.copier_task_config = open( - os.path.join(CURRENT_TEST_DIR, "task_trivial.xml"), "r" - ).read() - - def start(self): - source = cluster.instances["first_trivial"] - destination = cluster.instances["second_trivial"] - - for node in [source, destination]: - node.query("DROP DATABASE IF EXISTS default") - node.query("CREATE DATABASE IF NOT EXISTS default") - - source.query( - "CREATE TABLE trivial (d UInt64, d1 UInt64 MATERIALIZED d+1)" - "ENGINE=ReplicatedMergeTree('/clickhouse/tables/source_trivial_cluster/1/trivial/{}', '1') " - "PARTITION BY d % 5 ORDER BY (d, sipHash64(d)) SAMPLE BY sipHash64(d) SETTINGS index_granularity = 16".format( - generateRandomString(10) - ) - ) - - source.query( - "INSERT INTO trivial SELECT * FROM system.numbers LIMIT 1002", - settings={"distributed_foreground_insert": 1}, - ) - - def check(self): - zk = cluster.get_kazoo_client("zoo1") - status_data, _ = zk.get(self.zk_task_path + "/status") - assert ( - status_data - == b'{"hits":{"all_partitions_count":5,"processed_partitions_count":5}}' - ) - - source = cluster.instances["first_trivial"] - destination = cluster.instances["second_trivial"] - - assert TSV(source.query("SELECT count() FROM trivial")) == TSV("1002\n") - assert TSV(destination.query("SELECT count() FROM trivial")) == TSV("1002\n") - - for node in [source, destination]: - node.query("DROP TABLE trivial") - - -class TaskReplicatedWithoutArguments: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_trivial_without_arguments" - self.copier_task_config = open( - os.path.join(CURRENT_TEST_DIR, "task_trivial_without_arguments.xml"), "r" - ).read() - - def start(self): - source = cluster.instances["first_trivial"] - destination = cluster.instances["second_trivial"] - - for node in [source, destination]: - node.query("DROP DATABASE IF EXISTS default") - node.query("CREATE DATABASE IF NOT EXISTS default") - - source.query( - "CREATE TABLE trivial_without_arguments ON CLUSTER source_trivial_cluster (d UInt64, d1 UInt64 MATERIALIZED d+1) " - "ENGINE=ReplicatedMergeTree() " - "PARTITION BY d % 5 ORDER BY (d, sipHash64(d)) SAMPLE BY sipHash64(d) SETTINGS index_granularity = 16" - ) - - source.query( - "INSERT INTO trivial_without_arguments SELECT * FROM system.numbers LIMIT 1002", - settings={"distributed_foreground_insert": 1}, - ) - - def check(self): - zk = cluster.get_kazoo_client("zoo1") - status_data, _ = zk.get(self.zk_task_path + "/status") - assert ( - status_data - == b'{"hits":{"all_partitions_count":5,"processed_partitions_count":5}}' - ) - - source = cluster.instances["first_trivial"] - destination = cluster.instances["second_trivial"] - - assert TSV( - source.query("SELECT count() FROM trivial_without_arguments") - ) == TSV("1002\n") - assert TSV( - destination.query("SELECT count() FROM trivial_without_arguments") - ) == TSV("1002\n") - - for node in [source, destination]: - node.query("DROP TABLE trivial_without_arguments") - - -def execute_task(started_cluster, task, cmd_options): - task.start() - - zk = started_cluster.get_kazoo_client("zoo1") - print("Use ZooKeeper server: {}:{}".format(zk.hosts[0][0], zk.hosts[0][1])) - - try: - zk.delete("/clickhouse-copier", recursive=True) - except kazoo.exceptions.NoNodeError: - print("No node /clickhouse-copier. It is Ok in first test.") - - zk_task_path = task.zk_task_path - zk.ensure_path(zk_task_path) - zk.create(zk_task_path + "/description", task.copier_task_config.encode()) - - # Run cluster-copier processes on each node - docker_api = started_cluster.docker_client.api - copiers_exec_ids = [] - - cmd = [ - "/usr/bin/clickhouse", - "copier", - "--config", - "/etc/clickhouse-server/config-copier.xml", - "--task-path", - zk_task_path, - "--base-dir", - "/var/log/clickhouse-server/copier", - ] - cmd += cmd_options - - copiers = list(started_cluster.instances.keys()) - - for instance_name in copiers: - instance = started_cluster.instances[instance_name] - container = instance.get_docker_handle() - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "configs/config-copier.xml"), - "/etc/clickhouse-server/config-copier.xml", - ) - print("Copied copier config to {}".format(instance.name)) - exec_id = docker_api.exec_create(container.id, cmd, stderr=True) - output = docker_api.exec_start(exec_id).decode("utf8") - print(output) - copiers_exec_ids.append(exec_id) - print( - "Copier for {} ({}) has started".format(instance.name, instance.ip_address) - ) - - # Wait for copiers stopping and check their return codes - for exec_id, instance_name in zip(copiers_exec_ids, copiers): - instance = started_cluster.instances[instance_name] - while True: - res = docker_api.exec_inspect(exec_id) - if not res["Running"]: - break - time.sleep(0.5) - - assert res["ExitCode"] == 0, "Instance: {} ({}). Info: {}".format( - instance.name, instance.ip_address, repr(res) - ) - - try: - task.check() - finally: - zk.delete(zk_task_path, recursive=True) - - -# Tests - - -def test_trivial_copy(started_cluster): - execute_task(started_cluster, TaskTrivial(started_cluster), []) - - -def test_trivial_without_arguments(started_cluster): - execute_task(started_cluster, TaskReplicatedWithoutArguments(started_cluster), []) diff --git a/tests/integration/test_cluster_copier/test_two_nodes.py b/tests/integration/test_cluster_copier/test_two_nodes.py deleted file mode 100644 index 1bd3561f24f..00000000000 --- a/tests/integration/test_cluster_copier/test_two_nodes.py +++ /dev/null @@ -1,597 +0,0 @@ -import os -import sys -import time -import logging -import pytest - -from helpers.cluster import ClickHouseCluster -from helpers.test_tools import TSV - -import docker - -CURRENT_TEST_DIR = os.path.dirname(os.path.abspath(__file__)) -sys.path.insert(0, os.path.dirname(CURRENT_TEST_DIR)) - -cluster = ClickHouseCluster(__file__) - - -@pytest.fixture(scope="module") -def started_cluster(): - global cluster - try: - for name in ["first_of_two", "second_of_two"]: - instance = cluster.add_instance( - name, - main_configs=[ - "configs_two_nodes/conf.d/clusters.xml", - "configs_two_nodes/conf.d/ddl.xml", - "configs_two_nodes/conf.d/storage_configuration.xml", - ], - user_configs=["configs_two_nodes/users.xml"], - with_zookeeper=True, - ) - - cluster.start() - - for name in ["first_of_two", "second_of_two"]: - instance = cluster.instances[name] - instance.exec_in_container(["bash", "-c", "mkdir /jbod1"]) - instance.exec_in_container(["bash", "-c", "mkdir /jbod2"]) - instance.exec_in_container(["bash", "-c", "mkdir /external"]) - - yield cluster - - finally: - cluster.shutdown() - - -# Will copy table from `first` node to `second` -class TaskWithDifferentSchema: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_with_different_schema" - self.container_task_file = "/task_with_different_schema.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_with_different_schema.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - first.query("DROP DATABASE IF EXISTS db_different_schema SYNC") - second.query("DROP DATABASE IF EXISTS db_different_schema SYNC") - - first.query("CREATE DATABASE IF NOT EXISTS db_different_schema;") - first.query( - """CREATE TABLE db_different_schema.source - ( - Column1 String, - Column2 UInt32, - Column3 Date, - Column4 DateTime, - Column5 UInt16, - Column6 String, - Column7 String, - Column8 String, - Column9 String, - Column10 String, - Column11 String, - Column12 Decimal(3, 1), - Column13 DateTime, - Column14 UInt16 - ) - ENGINE = MergeTree() - PARTITION BY (toYYYYMMDD(Column3), Column3) - PRIMARY KEY (Column1, Column2, Column3, Column4, Column6, Column7, Column8, Column9) - ORDER BY (Column1, Column2, Column3, Column4, Column6, Column7, Column8, Column9) - SETTINGS index_granularity = 8192""" - ) - - first.query( - """INSERT INTO db_different_schema.source SELECT * FROM generateRandom( - 'Column1 String, Column2 UInt32, Column3 Date, Column4 DateTime, Column5 UInt16, - Column6 String, Column7 String, Column8 String, Column9 String, Column10 String, - Column11 String, Column12 Decimal(3, 1), Column13 DateTime, Column14 UInt16', 1, 10, 2) LIMIT 50;""" - ) - - second.query("CREATE DATABASE IF NOT EXISTS db_different_schema;") - second.query( - """CREATE TABLE db_different_schema.destination - ( - Column1 LowCardinality(String) CODEC(LZ4), - Column2 UInt32 CODEC(LZ4), - Column3 Date CODEC(DoubleDelta, LZ4), - Column4 DateTime CODEC(DoubleDelta, LZ4), - Column5 UInt16 CODEC(LZ4), - Column6 LowCardinality(String) CODEC(ZSTD), - Column7 LowCardinality(String) CODEC(ZSTD), - Column8 LowCardinality(String) CODEC(ZSTD), - Column9 LowCardinality(String) CODEC(ZSTD), - Column10 String CODEC(ZSTD(6)), - Column11 LowCardinality(String) CODEC(LZ4), - Column12 Decimal(3,1) CODEC(LZ4), - Column13 DateTime CODEC(DoubleDelta, LZ4), - Column14 UInt16 CODEC(LZ4) - ) ENGINE = MergeTree() - PARTITION BY toYYYYMMDD(Column3) - ORDER BY (Column9, Column1, Column2, Column3, Column4);""" - ) - - print("Preparation completed") - - def check(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - a = first.query("SELECT count() from db_different_schema.source") - b = second.query("SELECT count() from db_different_schema.destination") - assert a == b, "Count" - - a = TSV( - first.query( - """SELECT sipHash64(*) from db_different_schema.source - ORDER BY (Column1, Column2, Column3, Column4, Column5, Column6, Column7, Column8, Column9, Column10, Column11, Column12, Column13, Column14)""" - ) - ) - b = TSV( - second.query( - """SELECT sipHash64(*) from db_different_schema.destination - ORDER BY (Column1, Column2, Column3, Column4, Column5, Column6, Column7, Column8, Column9, Column10, Column11, Column12, Column13, Column14)""" - ) - ) - assert a == b, "Data" - - first.query("DROP DATABASE IF EXISTS db_different_schema SYNC") - second.query("DROP DATABASE IF EXISTS db_different_schema SYNC") - - -# Just simple copying, but table schema has TTL on columns -# Also table will have slightly different schema -class TaskTTL: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_ttl_columns" - self.container_task_file = "/task_ttl_columns.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_ttl_columns.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - first.query("DROP DATABASE IF EXISTS db_ttl_columns SYNC") - second.query("DROP DATABASE IF EXISTS db_ttl_columns SYNC") - - first.query("CREATE DATABASE IF NOT EXISTS db_ttl_columns;") - first.query( - """CREATE TABLE db_ttl_columns.source - ( - Column1 String, - Column2 UInt32, - Column3 Date, - Column4 DateTime, - Column5 UInt16, - Column6 String TTL now() + INTERVAL 1 MONTH, - Column7 Decimal(3, 1) TTL now() + INTERVAL 1 MONTH, - Column8 Tuple(Float64, Float64) TTL now() + INTERVAL 1 MONTH - ) - ENGINE = MergeTree() - PARTITION BY (toYYYYMMDD(Column3), Column3) - PRIMARY KEY (Column1, Column2, Column3) - ORDER BY (Column1, Column2, Column3) - SETTINGS index_granularity = 8192""" - ) - - first.query( - """INSERT INTO db_ttl_columns.source SELECT * FROM generateRandom( - 'Column1 String, Column2 UInt32, Column3 Date, Column4 DateTime, Column5 UInt16, - Column6 String, Column7 Decimal(3, 1), Column8 Tuple(Float64, Float64)', 1, 10, 2) LIMIT 50;""" - ) - - second.query("CREATE DATABASE IF NOT EXISTS db_ttl_columns;") - second.query( - """CREATE TABLE db_ttl_columns.destination - ( - Column1 String, - Column2 UInt32, - Column3 Date, - Column4 DateTime TTL now() + INTERVAL 1 MONTH, - Column5 UInt16 TTL now() + INTERVAL 1 MONTH, - Column6 String TTL now() + INTERVAL 1 MONTH, - Column7 Decimal(3, 1) TTL now() + INTERVAL 1 MONTH, - Column8 Tuple(Float64, Float64) - ) ENGINE = MergeTree() - PARTITION BY toYYYYMMDD(Column3) - ORDER BY (Column3, Column2, Column1);""" - ) - - print("Preparation completed") - - def check(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - a = first.query("SELECT count() from db_ttl_columns.source") - b = second.query("SELECT count() from db_ttl_columns.destination") - assert a == b, "Count" - - a = TSV( - first.query( - """SELECT sipHash64(*) from db_ttl_columns.source - ORDER BY (Column1, Column2, Column3, Column4, Column5, Column6, Column7, Column8)""" - ) - ) - b = TSV( - second.query( - """SELECT sipHash64(*) from db_ttl_columns.destination - ORDER BY (Column1, Column2, Column3, Column4, Column5, Column6, Column7, Column8)""" - ) - ) - assert a == b, "Data" - - first.query("DROP DATABASE IF EXISTS db_ttl_columns SYNC") - second.query("DROP DATABASE IF EXISTS db_ttl_columns SYNC") - - -class TaskSkipIndex: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_skip_index" - self.container_task_file = "/task_skip_index.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_skip_index.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - first.query("DROP DATABASE IF EXISTS db_skip_index SYNC") - second.query("DROP DATABASE IF EXISTS db_skip_index SYNC") - - first.query("CREATE DATABASE IF NOT EXISTS db_skip_index;") - first.query( - """CREATE TABLE db_skip_index.source - ( - Column1 UInt64, - Column2 Int32, - Column3 Date, - Column4 DateTime, - Column5 String, - INDEX a (Column1 * Column2, Column5) TYPE minmax GRANULARITY 3, - INDEX b (Column1 * length(Column5)) TYPE set(1000) GRANULARITY 4 - ) - ENGINE = MergeTree() - PARTITION BY (toYYYYMMDD(Column3), Column3) - PRIMARY KEY (Column1, Column2, Column3) - ORDER BY (Column1, Column2, Column3) - SETTINGS index_granularity = 8192""" - ) - - first.query( - """INSERT INTO db_skip_index.source SELECT * FROM generateRandom( - 'Column1 UInt64, Column2 Int32, Column3 Date, Column4 DateTime, Column5 String', 1, 10, 2) LIMIT 100;""" - ) - - second.query("CREATE DATABASE IF NOT EXISTS db_skip_index;") - second.query( - """CREATE TABLE db_skip_index.destination - ( - Column1 UInt64, - Column2 Int32, - Column3 Date, - Column4 DateTime, - Column5 String, - INDEX a (Column1 * Column2, Column5) TYPE minmax GRANULARITY 3, - INDEX b (Column1 * length(Column5)) TYPE set(1000) GRANULARITY 4 - ) ENGINE = MergeTree() - PARTITION BY toYYYYMMDD(Column3) - ORDER BY (Column3, Column2, Column1);""" - ) - - print("Preparation completed") - - def check(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - a = first.query("SELECT count() from db_skip_index.source") - b = second.query("SELECT count() from db_skip_index.destination") - assert a == b, "Count" - - a = TSV( - first.query( - """SELECT sipHash64(*) from db_skip_index.source - ORDER BY (Column1, Column2, Column3, Column4, Column5)""" - ) - ) - b = TSV( - second.query( - """SELECT sipHash64(*) from db_skip_index.destination - ORDER BY (Column1, Column2, Column3, Column4, Column5)""" - ) - ) - assert a == b, "Data" - - first.query("DROP DATABASE IF EXISTS db_skip_index SYNC") - second.query("DROP DATABASE IF EXISTS db_skip_index SYNC") - - -class TaskTTLMoveToVolume: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_ttl_move_to_volume" - self.container_task_file = "/task_ttl_move_to_volume.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_ttl_move_to_volume.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["first_of_two"] - - first.query("DROP DATABASE IF EXISTS db_move_to_volume SYNC") - second.query("DROP DATABASE IF EXISTS db_move_to_volume SYNC") - - first.query("CREATE DATABASE IF NOT EXISTS db_move_to_volume;") - first.query( - """CREATE TABLE db_move_to_volume.source - ( - Column1 UInt64, - Column2 Int32, - Column3 Date, - Column4 DateTime, - Column5 String - ) - ENGINE = MergeTree() - PARTITION BY (toYYYYMMDD(Column3), Column3) - PRIMARY KEY (Column1, Column2, Column3) - ORDER BY (Column1, Column2, Column3) - TTL Column3 + INTERVAL 1 MONTH TO VOLUME 'external' - SETTINGS storage_policy = 'external_with_jbods';""" - ) - - first.query( - """INSERT INTO db_move_to_volume.source SELECT * FROM generateRandom( - 'Column1 UInt64, Column2 Int32, Column3 Date, Column4 DateTime, Column5 String', 1, 10, 2) LIMIT 100;""" - ) - - second.query("CREATE DATABASE IF NOT EXISTS db_move_to_volume;") - second.query( - """CREATE TABLE db_move_to_volume.destination - ( - Column1 UInt64, - Column2 Int32, - Column3 Date, - Column4 DateTime, - Column5 String - ) ENGINE = MergeTree() - PARTITION BY toYYYYMMDD(Column3) - ORDER BY (Column3, Column2, Column1) - TTL Column3 + INTERVAL 1 MONTH TO VOLUME 'external' - SETTINGS storage_policy = 'external_with_jbods';""" - ) - - print("Preparation completed") - - def check(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - a = first.query("SELECT count() from db_move_to_volume.source") - b = second.query("SELECT count() from db_move_to_volume.destination") - assert a == b, "Count" - - a = TSV( - first.query( - """SELECT sipHash64(*) from db_move_to_volume.source - ORDER BY (Column1, Column2, Column3, Column4, Column5)""" - ) - ) - b = TSV( - second.query( - """SELECT sipHash64(*) from db_move_to_volume.destination - ORDER BY (Column1, Column2, Column3, Column4, Column5)""" - ) - ) - assert a == b, "Data" - - first.query("DROP DATABASE IF EXISTS db_move_to_volume SYNC") - second.query("DROP DATABASE IF EXISTS db_move_to_volume SYNC") - - -class TaskDropTargetPartition: - def __init__(self, cluster): - self.cluster = cluster - self.zk_task_path = "/clickhouse-copier/task_drop_target_partition" - self.container_task_file = "/task_drop_target_partition.xml" - - for instance_name, _ in cluster.instances.items(): - instance = cluster.instances[instance_name] - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "./task_drop_target_partition.xml"), - self.container_task_file, - ) - print( - "Copied task file to container of '{}' instance. Path {}".format( - instance_name, self.container_task_file - ) - ) - - def start(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - first.query("DROP DATABASE IF EXISTS db_drop_target_partition SYNC") - second.query("DROP DATABASE IF EXISTS db_drop_target_partition SYNC") - - first.query("CREATE DATABASE IF NOT EXISTS db_drop_target_partition;") - first.query( - """CREATE TABLE db_drop_target_partition.source - ( - Column1 UInt64, - Column2 Int32, - Column3 Date, - Column4 DateTime, - Column5 String - ) - ENGINE = MergeTree() - PARTITION BY (toYYYYMMDD(Column3), Column3) - PRIMARY KEY (Column1, Column2, Column3) - ORDER BY (Column1, Column2, Column3);""" - ) - - first.query( - """INSERT INTO db_drop_target_partition.source SELECT * FROM generateRandom( - 'Column1 UInt64, Column2 Int32, Column3 Date, Column4 DateTime, Column5 String', 1, 10, 2) LIMIT 100;""" - ) - - second.query("CREATE DATABASE IF NOT EXISTS db_drop_target_partition;") - second.query( - """CREATE TABLE db_drop_target_partition.destination - ( - Column1 UInt64, - Column2 Int32, - Column3 Date, - Column4 DateTime, - Column5 String - ) ENGINE = MergeTree() - PARTITION BY toYYYYMMDD(Column3) - ORDER BY (Column3, Column2, Column1);""" - ) - - # Insert data in target too. It has to be dropped. - first.query( - """INSERT INTO db_drop_target_partition.destination SELECT * FROM db_drop_target_partition.source;""" - ) - - print("Preparation completed") - - def check(self): - first = cluster.instances["first_of_two"] - second = cluster.instances["second_of_two"] - - a = first.query("SELECT count() from db_drop_target_partition.source") - b = second.query("SELECT count() from db_drop_target_partition.destination") - assert a == b, "Count" - - a = TSV( - first.query( - """SELECT sipHash64(*) from db_drop_target_partition.source - ORDER BY (Column1, Column2, Column3, Column4, Column5)""" - ) - ) - b = TSV( - second.query( - """SELECT sipHash64(*) from db_drop_target_partition.destination - ORDER BY (Column1, Column2, Column3, Column4, Column5)""" - ) - ) - assert a == b, "Data" - - first.query("DROP DATABASE IF EXISTS db_drop_target_partition SYNC") - second.query("DROP DATABASE IF EXISTS db_drop_target_partition SYNC") - - -def execute_task(started_cluster, task, cmd_options): - task.start() - - zk = started_cluster.get_kazoo_client("zoo1") - print("Use ZooKeeper server: {}:{}".format(zk.hosts[0][0], zk.hosts[0][1])) - - # Run cluster-copier processes on each node - docker_api = started_cluster.docker_client.api - copiers_exec_ids = [] - - cmd = [ - "/usr/bin/clickhouse", - "copier", - "--config", - "/etc/clickhouse-server/config-copier.xml", - "--task-path", - task.zk_task_path, - "--task-file", - task.container_task_file, - "--task-upload-force", - "true", - "--base-dir", - "/var/log/clickhouse-server/copier", - ] - cmd += cmd_options - - print(cmd) - - for instance_name in started_cluster.instances.keys(): - instance = started_cluster.instances[instance_name] - container = instance.get_docker_handle() - instance.copy_file_to_container( - os.path.join(CURRENT_TEST_DIR, "configs_two_nodes/config-copier.xml"), - "/etc/clickhouse-server/config-copier.xml", - ) - logging.info("Copied copier config to {}".format(instance.name)) - exec_id = docker_api.exec_create(container.id, cmd, stderr=True) - output = docker_api.exec_start(exec_id).decode("utf8") - logging.info(output) - copiers_exec_ids.append(exec_id) - logging.info( - "Copier for {} ({}) has started".format(instance.name, instance.ip_address) - ) - - # time.sleep(1000) - - # Wait for copiers stopping and check their return codes - for exec_id, instance in zip( - copiers_exec_ids, iter(started_cluster.instances.values()) - ): - while True: - res = docker_api.exec_inspect(exec_id) - if not res["Running"]: - break - time.sleep(1) - - assert res["ExitCode"] == 0, "Instance: {} ({}). Info: {}".format( - instance.name, instance.ip_address, repr(res) - ) - - try: - task.check() - finally: - zk.delete(task.zk_task_path, recursive=True) diff --git a/tests/integration/test_config_xml_full/configs/config.xml b/tests/integration/test_config_xml_full/configs/config.xml index ac59b3428e8..628e1432350 100644 --- a/tests/integration/test_config_xml_full/configs/config.xml +++ b/tests/integration/test_config_xml_full/configs/config.xml @@ -72,7 +72,7 @@ 8123