You are viewing a plain text version of this content. The canonical link for it is here.

Posted to issues@flink.apache.org by "Noam Liran (JIRA)" <ji...@apache.org> on 2018/06/05 20:35:00 UTC

[jira] [Commented] (FLINK-8845) Use WriteBatch to improve performance for recovery in RocksDB backend

    [ https://issues.apache.org/jira/browse/FLINK-8845?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16502447#comment-16502447 ] 

Noam Liran commented on FLINK-8845:
-----------------------------------

Hi [~srichter], [~sihuazhou],

I noticed that the code in RocksDBKeyedStateBackend does not disable WAL, even though it is disabled in other places (and in the benchmarks).

Is this on purpose?

 

Thanks,

Noam

 

> Use WriteBatch to improve performance for recovery in RocksDB backend
> ---------------------------------------------------------------------
>
>                 Key: FLINK-8845
>                 URL: https://issues.apache.org/jira/browse/FLINK-8845
>             Project: Flink
>          Issue Type: Improvement
>          Components: State Backends, Checkpointing
>    Affects Versions: 1.5.0
>            Reporter: Sihua Zhou
>            Assignee: Sihua Zhou
>            Priority: Major
>             Fix For: 1.5.0
>
>
> Base on {{WriteBatch}} we could get 30% ~ 50% performance lift when loading data into RocksDB.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)