hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Gabriel Reid (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-7325) Replication reacts slowly on a lightly-loaded cluster
Date Thu, 13 Dec 2012 07:55:21 GMT

    [ https://issues.apache.org/jira/browse/HBASE-7325?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13530769#comment-13530769
] 

Gabriel Reid commented on HBASE-7325:
-------------------------------------

[~lhofhansl] I follow your point -- however, this is a situation where the cluster is almost
totally idle. 

If each region server is getting at least one mutation event per second (which I would assume
is still a very light load) then the polling is going to be happening once per second anyhow.
If the cluster is more heavily loaded, then the polling is going to be occurring at the rate
at which edits can be shipped to peers. 

This makes me think that if the 1 second interval polling on an idle cluster is a problem,
then replication on a loaded cluster will be a much bigger problem.
                
> Replication reacts slowly on a lightly-loaded cluster
> -----------------------------------------------------
>
>                 Key: HBASE-7325
>                 URL: https://issues.apache.org/jira/browse/HBASE-7325
>             Project: HBase
>          Issue Type: Bug
>          Components: Replication
>            Reporter: Gabriel Reid
>            Priority: Minor
>         Attachments: HBASE-7325.patch
>
>
> ReplicationSource uses a backing-off algorithm to sleep for an increasing duration when
an error is encountered in the replication run loop. However, this backing-off is also performed
when there is nothing found to replicate in the HLog.
> Assuming default settings (1 second base retry sleep time, and maximum multiplier of
10), this means that replication takes up to 10 seconds to occur when there is a break of
about 55 seconds without anything being written. As there is no error condition, and there
is apparently no substantial load on the regionserver in this situation, it would probably
make more sense to not back off in non-error situations.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message