[jira] [Commented] (FLINK-7289) Memory allocation of RocksDB can be problematic in container environments

["Truong Duc Kien (Jira)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/FLINK-7289?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16932200#comment-16932200 ] 

Truong Duc Kien commented on FLINK-7289:
----------------------------------------

In my experience, using jemalloc can reduce RocksDB usage by a lot, due to reduction in memory fragmentation. Jemalloc's profiler is also very useful in tracking down memory issues. To use jemalloc, we set the LD_PRELOAD environment variable before starting Task Managers.

 

Settings

 {{cache_index_and_filter_blocks = true}}

can reduce memory usage a bit, because indexes and filters are no longer pinned in memory. However, you'd pay a very high cost when cache misses: we've encounter orders of magnitude increase in latency when accessing state if this happens. Do not use if your job is latency-sensitive.

> Memory allocation of RocksDB can be problematic in container environments
> -------------------------------------------------------------------------
>
>                 Key: FLINK-7289
>                 URL: https://issues.apache.org/jira/browse/FLINK-7289
>             Project: Flink
>          Issue Type: Improvement
>          Components: Runtime / State Backends
>    Affects Versions: 1.2.0, 1.3.0, 1.4.0
>            Reporter: Stefan Richter
>            Priority: Major
>         Attachments: completeRocksdbConfig.txt
>
>
> Flink's RocksDB based state backend allocates native memory. The amount of allocated memory by RocksDB is not under the control of Flink or the JVM and can (theoretically) grow without limits.
> In container environments, this can be problematic because the process can exceed the memory budget of the container, and the process will get killed. Currently, there is no other option than trusting RocksDB to be well behaved and to follow its memory configurations. However, limiting RocksDB's memory usage is not as easy as setting a single limit parameter. The memory limit is determined by an interplay of several configuration parameters, which is almost impossible to get right for users. Even worse, multiple RocksDB instances can run inside the same process and make reasoning about the configuration also dependent on the Flink job.
> Some information about the memory management in RocksDB can be found here:
> https://github.com/facebook/rocksdb/wiki/Memory-usage-in-RocksDB
> https://github.com/facebook/rocksdb/wiki/RocksDB-Tuning-Guide
> We should try to figure out ways to help users in one or more of the following ways:
> - Some way to autotune or calculate the RocksDB configuration.
> - Conservative default values.
> - Additional documentation.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)