You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@kafka.apache.org by "Eno Thereska (JIRA)" <ji...@apache.org> on 2017/05/19 08:08:05 UTC
[jira] [Updated] (KAFKA-4868) Optimize RocksDb config for fast
recovery/bulk load
[ https://issues.apache.org/jira/browse/KAFKA-4868?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Eno Thereska updated KAFKA-4868:
--------------------------------
Fix Version/s: (was: 0.11.0.0)
0.11.1.0
> Optimize RocksDb config for fast recovery/bulk load
> ---------------------------------------------------
>
> Key: KAFKA-4868
> URL: https://issues.apache.org/jira/browse/KAFKA-4868
> Project: Kafka
> Issue Type: Improvement
> Components: streams
> Affects Versions: 0.10.2.0
> Reporter: Eno Thereska
> Assignee: Bill Bejeck
> Fix For: 0.11.1.0
>
>
> RocksDb can be tuned to bulk-load data fast. Kafka Streams bulk-loads records during recovery. It is likely we can use a different config to make recovery faster, then revert to another config for normal operations like put/get. See https://github.com/facebook/rocksdb/wiki/performance-benchmarks for examples.
> Would be good to measure the performance gain as part of addressing this JIRA.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)