hbase-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "stack (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-1111) [performance] Crash recovery takes way too long
Date Fri, 09 Jan 2009 00:28:59 GMT

    [ https://issues.apache.org/jira/browse/HBASE-1111?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12662191#action_12662191
] 

stack commented on HBASE-1111:
------------------------------

Yeah, just tried killing server that was carrying -ROOT-.  Took 20 minutes just processing
41 log files.  All clients were  dead by time cluster was again useable.

> [performance] Crash recovery takes way too long
> -----------------------------------------------
>
>                 Key: HBASE-1111
>                 URL: https://issues.apache.org/jira/browse/HBASE-1111
>             Project: Hadoop HBase
>          Issue Type: Improvement
>            Reporter: stack
>
> Watching hbase recover from crashes, its taking way too long:
> 1. Must wait first on lease to expire (if server is rebooted, it should cancel the old
servers' lease but make sure the lease expiration code runs)
> 2. Master splits logs.  This is single-threaded.  At least a maximum of 64 logs but seems
to run slow anyways.
> 3. Assign out the regions that were on dead-server (minutes or even tens of minutes could
have elapsed at this stage)
> 4. Wait on the regionservers to open.  If small cluster, because regionservers open regions
in series, could take a long time opening a bunch of issues.  Meantime the regions are not
available, clients will likely timeout.
> 5. To make things worse, I've seen load-balancer cut in to 'help out' telling regionserver
close some of its regions though its busy opening a bunch.
> Andrew Purtell notes that HBASE-1110 will change a bunch of the above.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message