hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "stack (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HBASE-2782) QOS for META table access
Date Tue, 14 Sep 2010 23:50:36 GMT

    [ https://issues.apache.org/jira/browse/HBASE-2782?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12909530#action_12909530

stack commented on HBASE-2782:

This patch changes the api for rpc.   It likely messes up Gary's work on making rpc pluggable;
i.e. secure and non-secure rpc.  Let me ask him what he thinks of this.

Whats this change mean?

-  private static final int MAX_QUEUE_SIZE_PER_HANDLER = 100;
+  private static final int MAX_QUEUE_SIZE_PER_HANDLER = 1000;

QoSFunction has to be in  HRS?  We've been doing work to break up the massive classes.

How about a unit test?

> QOS for META table access
> -------------------------
>                 Key: HBASE-2782
>                 URL: https://issues.apache.org/jira/browse/HBASE-2782
>             Project: HBase
>          Issue Type: Improvement
>          Components: regionserver
>    Affects Versions: 0.89.20100621
>            Reporter: Todd Lipcon
>            Assignee: ryan rawson
>             Fix For: 0.90.0
>         Attachments: HBASE-2782.txt
> I'd like to brainstorm some ideas on how we can prioritize reads and writes to META above
reads and writes to other tables. I've noticed that if the regionserver hosting META is under
heavy load, then lots of other operations take much longer than they should. For example,
I'm currently running 120 threads of YCSB across 3 client nodes hitting a 5-node cluster.
Doing a full scan of META (only 600 rows) takes upwards of 30 seconds in the shell, since
all of the handler threads are tied up and there's a long RPC queue. 

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

View raw message