hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Heng Chen (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-15765) RPC handlers should steal from other queues in the same or higher priority
Date Tue, 17 May 2016 02:27:12 GMT

    [ https://issues.apache.org/jira/browse/HBASE-15765?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15285893#comment-15285893

Heng Chen commented on HBASE-15765:

we can steal 1 RPC every ~3seconds if I read the patch right. 
It is not steal task every 3 seconds.  In the patch, we firstly get task from our original
queue, if timeout (3s), then we will try to steal task from other queue.

 the handlers still do not steal from the queues in the same tier, but a different "shard"
Sorry,  i am not sure what is "queues in the same tier"?
If i understand correctly,  the queues in one handler pools are in the same priority level,
right?  Or you mean general pool and replication pool are in the same tier?

> RPC handlers should steal from other queues in the same or higher priority
> --------------------------------------------------------------------------
>                 Key: HBASE-15765
>                 URL: https://issues.apache.org/jira/browse/HBASE-15765
>             Project: HBase
>          Issue Type: Improvement
>            Reporter: Enis Soztutar
>         Attachments: HBASE-15765.patch, HBASE-15765_v1.patch
> With the simple rpc scheduler model by default, a request first falls in one type of
queue (priority, general, replication) and it will get "sharded" in a queue within that priority
level (for example there are 2 queues for the high priority level). The handlers can only
take from their specific queues, and nothing else. 
> Even if a request is waiting in a high priority queue, the handlers within the same priority
level or a lower priority level will not see these requests (which is the root cause for HBASE-15613).
We should be able to steal from other queues, without losing the prioritization and sharding

This message was sent by Atlassian JIRA

View raw message