You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ozone.apache.org by "runzhiwang (Jira)" <ji...@apache.org> on 2020/04/01 09:12:00 UTC
[jira] [Updated] (HDDS-3283) Improve write efficiency by decreasing
the number of sync to disk
[ https://issues.apache.org/jira/browse/HDDS-3283?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
runzhiwang updated HDDS-3283:
-----------------------------
Summary: Improve write efficiency by decreasing the number of sync to disk (was: Improve write efficiency by improving RocksDB writeBatch)
> Improve write efficiency by decreasing the number of sync to disk
> -----------------------------------------------------------------
>
> Key: HDDS-3283
> URL: https://issues.apache.org/jira/browse/HDDS-3283
> Project: Hadoop Distributed Data Store
> Issue Type: Improvement
> Reporter: runzhiwang
> Assignee: runzhiwang
> Priority: Major
> Attachments: screenshot-1.png
>
>
> From the image, you can find the whole write cost 140ms, but RocksDB [writeBatch|https://github.com/apache/hadoop-ozone/blob/master/hadoop-hdds/framework/src/main/java/org/apache/hadoop/hdds/utils/db/RDBBatchOperation.java#L46] of two OM [response|https://github.com/apache/hadoop-ozone/blob/master/hadoop-ozone/ozone-manager/src/main/java/org/apache/hadoop/ozone/protocolPB/OzoneManagerProtocolServerSideTranslatorPB.java#L217], CreatKeyResponse and CommitKeyResponse, cost about 60ms, about 60 / 140 = 43%. I will find why it cost so much and improve it.
> !screenshot-1.png!
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: ozone-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: ozone-issues-help@hadoop.apache.org