You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@kudu.apache.org by "Jeffrey F. Lukman (JIRA)" <ji...@apache.org> on 2018/01/18 23:49:01 UTC
[jira] [Updated] (KUDU-2126) DeleteTablet RPC on an already deleted
tablet should be a no-op
[ https://issues.apache.org/jira/browse/KUDU-2126?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jeffrey F. Lukman updated KUDU-2126:
------------------------------------
Code Review: http://gerrit.cloudera.org:8080/9069
> DeleteTablet RPC on an already deleted tablet should be a no-op
> ---------------------------------------------------------------
>
> Key: KUDU-2126
> URL: https://issues.apache.org/jira/browse/KUDU-2126
> Project: Kudu
> Issue Type: Bug
> Components: tserver
> Affects Versions: 1.5.0
> Reporter: Adar Dembo
> Assignee: Jeffrey F. Lukman
> Priority: Major
> Labels: newbie
>
> This is remaining (but lower priority) work from KUDU-2114:
> bq. When observed on a live cluster, it was further observed that the tablet deletion requests were rather expensive. It appears that a DeleteTablet RPC on a tombstone is not a no-op; it always flushes the superblock twice, which generates two fsyncs. This should also be addressed.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)