mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-11-10 17:44:23 +00:00
d91c97d15d
* Replace underscores with hyphens * remove temporary code * fix style check * fix collapse
168 lines
6.8 KiB
Markdown
168 lines
6.8 KiB
Markdown
# ﾂ环板-ｮﾂ嘉ｯﾂ偲 {#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`:
|
||
|
||
- 连接到动物园管理员和接收:
|
||
|
||
- 复制作业。
|
||
- 复制作业的状态。
|
||
|
||
- 它执行的工作。
|
||
|
||
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` 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。
|
||
|
||
## ﾂ暗ｪﾂ氾环催ﾂ団ﾂ法ﾂ人 {#running-clickhouse-copier}
|
||
|
||
该实用程序应手动运行:
|
||
|
||
``` bash
|
||
clickhouse-copier copier --daemon --config zookeeper.xml --task-path /task/path --base-dir /path/to/dir
|
||
```
|
||
|
||
参数:
|
||
|
||
- `daemon` — Starts `clickhouse-copier` 在守护进程模式。
|
||
- `config` — The path to the `zookeeper.xml` 带有连接到ZooKeeper的参数的文件。
|
||
- `task-path` — The path to the ZooKeeper node. This node is used for syncing `clickhouse-copier` 处理和存储任务。 任务存储在 `$task-path/description`.
|
||
- `base-dir` — The path to logs and auxiliary files. When it starts, `clickhouse-copier` 创建 `clickhouse-copier_YYYYMMHHSS_<PID>` 子目录 `$base-dir`. 如果省略此参数，则在以下目录中创建目录 `clickhouse-copier` 被推出。
|
||
|
||
## 动物园管理员的格式。xml {#format-of-zookeeper-xml}
|
||
|
||
``` xml
|
||
<yandex>
|
||
<logger>
|
||
<level>trace</level>
|
||
<size>100M</size>
|
||
<count>3</count>
|
||
</logger>
|
||
|
||
<zookeeper>
|
||
<node index="1">
|
||
<host>127.0.0.1</host>
|
||
<port>2181</port>
|
||
</node>
|
||
</zookeeper>
|
||
</yandex>
|
||
```
|
||
|
||
## 复制任务的配置 {#configuration-of-copying-tasks}
|
||
|
||
``` xml
|
||
<yandex>
|
||
<!-- Configuration of clusters as in an ordinary server config -->
|
||
<remote_servers>
|
||
<source_cluster>
|
||
<shard>
|
||
<internal_replication>false</internal_replication>
|
||
<replica>
|
||
<host>127.0.0.1</host>
|
||
<port>9000</port>
|
||
</replica>
|
||
</shard>
|
||
...
|
||
</source_cluster>
|
||
|
||
<destination_cluster>
|
||
...
|
||
</destination_cluster>
|
||
</remote_servers>
|
||
|
||
<!-- How many simultaneously active workers are possible. If you run more workers superfluous workers will sleep. -->
|
||
<max_workers>2</max_workers>
|
||
|
||
<!-- Setting used to fetch (pull) data from source cluster tables -->
|
||
<settings_pull>
|
||
<readonly>1</readonly>
|
||
</settings_pull>
|
||
|
||
<!-- Setting used to insert (push) data to destination cluster tables -->
|
||
<settings_push>
|
||
<readonly>0</readonly>
|
||
</settings_push>
|
||
|
||
<!-- Common setting for fetch (pull) and insert (push) operations. Also, copier process context uses it.
|
||
They are overlaid by <settings_pull/> and <settings_push/> respectively. -->
|
||
<settings>
|
||
<connect_timeout>3</connect_timeout>
|
||
<!-- Sync insert is set forcibly, leave it here just in case. -->
|
||
<insert_distributed_sync>1</insert_distributed_sync>
|
||
</settings>
|
||
|
||
<!-- Copying tasks description.
|
||
You could specify several table task in the same task description (in the same ZooKeeper node), they will be performed
|
||
sequentially.
|
||
-->
|
||
<tables>
|
||
<!-- A table task, copies one table. -->
|
||
<table_hits>
|
||
<!-- Source cluster name (from <remote_servers/> section) and tables in it that should be copied -->
|
||
<cluster_pull>source_cluster</cluster_pull>
|
||
<database_pull>test</database_pull>
|
||
<table_pull>hits</table_pull>
|
||
|
||
<!-- Destination cluster name and tables in which the data should be inserted -->
|
||
<cluster_push>destination_cluster</cluster_push>
|
||
<database_push>test</database_push>
|
||
<table_push>hits2</table_push>
|
||
|
||
<!-- Engine of destination tables.
|
||
If destination tables have not be created, workers create them using columns definition from source tables and engine
|
||
definition from here.
|
||
|
||
NOTE: If the first worker starts insert data and detects that destination partition is not empty then the partition will
|
||
be dropped and refilled, take it into account if you already have some data in destination tables. You could directly
|
||
specify partitions that should be copied in <enabled_partitions/>, they should be in quoted format like partition column of
|
||
system.parts table.
|
||
-->
|
||
<engine>
|
||
ENGINE=ReplicatedMergeTree('/clickhouse/tables/{cluster}/{shard}/hits2', '{replica}')
|
||
PARTITION BY toMonday(date)
|
||
ORDER BY (CounterID, EventDate)
|
||
</engine>
|
||
|
||
<!-- Sharding key used to insert data to destination cluster -->
|
||
<sharding_key>jumpConsistentHash(intHash64(UserID), 2)</sharding_key>
|
||
|
||
<!-- Optional expression that filter data while pull them from source servers -->
|
||
<where_condition>CounterID != 0</where_condition>
|
||
|
||
<!-- This section specifies partitions that should be copied, other partition will be ignored.
|
||
Partition names should have the same format as
|
||
partition column of system.parts table (i.e. a quoted text).
|
||
Since partition key of source and destination cluster could be different,
|
||
these partition names specify destination partitions.
|
||
|
||
NOTE: In spite of this section is optional (if it is not specified, all partitions will be copied),
|
||
it is strictly recommended to specify them explicitly.
|
||
If you already have some ready partitions on destination cluster they
|
||
will be removed at the start of the copying since they will be interpeted
|
||
as unfinished data from the previous copying!!!
|
||
-->
|
||
<enabled_partitions>
|
||
<partition>'2018-02-26'</partition>
|
||
<partition>'2018-03-05'</partition>
|
||
...
|
||
</enabled_partitions>
|
||
</table_hits>
|
||
|
||
<!-- Next table to copy. It is not copied until previous table is copying. -->
|
||
</table_visits>
|
||
...
|
||
</table_visits>
|
||
...
|
||
</tables>
|
||
</yandex>
|
||
```
|
||
|
||
`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。
|
||
|
||
[原始文章](https://clickhouse.tech/docs/en/operations/utils/clickhouse-copier/) <!--hide-->
|