[
https://issues.apache.org/jira/browse/HBASE-4528?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
dhruba borthakur updated HBASE-4528:
------------------------------------
Attachment: appendNoSyncPut3.txt
1. The flush of memstore waits for current transactions to quiesce before
committing the flushed files. This should address the problem pointed out by
Kannan.
2. The Hlog.syncer() does not throw an exception, instead causes the
regionserver to exit if it is unable to sync to hdfs. The assumption here is
that if hbase is unable to write/sync to hdfs, then the simplest and correct
error recovery is to exit. (For example, if the memstore flush fails, the
regionserver exits)
> The put operation can release the rowlock before sync-ing the Hlog
> ------------------------------------------------------------------
>
> Key: HBASE-4528
> URL: https://issues.apache.org/jira/browse/HBASE-4528
> Project: HBase
> Issue Type: Improvement
> Components: regionserver
> Reporter: dhruba borthakur
> Assignee: dhruba borthakur
> Attachments: appendNoSyncPut1.txt, appendNoSyncPut2.txt,
> appendNoSyncPut3.txt
>
>
> This allows for better throughput when there are hot rows. A single row
> update improves from 100 puts/sec/server to 5000 puts/sec/server.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
