[
https://issues.apache.org/jira/browse/CASSANDRA-2327?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13006801#comment-13006801
]
Vijay commented on CASSANDRA-2327:
----------------------------------
Took a look at dCS (Understand it is not thread safe currently)... I still
think we shouldn't block the rest of the CF's update for the Memtable flush...
As the CF which needs dCS is already frozen and updates will wait. dCS should
be a append operation into the commit log.
If dCS is a append, we can remove stop the world flush to be more granular to
be just flush for the Column family. To the least we should stop only the
writes into the commit log not the reads to some other Memtables....
Can we use the use the same Ticket to re-factor and continue this discussion on
commit log and flushLock's?
> Table.flusherLock is static final.. remove static.
> --------------------------------------------------
>
> Key: CASSANDRA-2327
> URL: https://issues.apache.org/jira/browse/CASSANDRA-2327
> Project: Cassandra
> Issue Type: Bug
> Components: Core
> Affects Versions: 0.7.4, 0.7.5
> Environment: JVM
> Reporter: Vijay
> Assignee: Vijay
> Priority: Minor
> Fix For: 0.7.5
>
>
> I see read and write latency spike when the system tables are
> flushing(according to opscentral)....
> Only reason which i can come-up with is probably because of the
> Table.flusherLock is static final... i think it should not be static because
> the flush is per keyspace and this lock will lock all the read operations
> because one table is going through a flush.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
