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-8884) Pluggable RpcScheduler
Date Tue, 10 Sep 2013 04:45:18 GMT

    [ https://issues.apache.org/jira/browse/HBASE-8884?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13762717#comment-13762717
] 

stack commented on HBASE-8884:
------------------------------

As is, it is hard to follow what is going on.

+ Do we have to have a thread local up in the parent server class as the means of keeping
context across the calls; can this not be in handler?  A context it gives each Call?
+ Does CallRunner have to be a Runnable?  You see how elsewhere in hbase we the notion of
Callable?  It seems to have much what you introduce here with the CallRunner?  Would be good
to have it all align.

Agree more refactor would help.  Thanks Chao Shi.  I want to be able to add pooling of buffers
across requests.  At the moment it is difficult figuring how/where to insert.  Thanks.
                
> Pluggable RpcScheduler
> ----------------------
>
>                 Key: HBASE-8884
>                 URL: https://issues.apache.org/jira/browse/HBASE-8884
>             Project: HBase
>          Issue Type: Improvement
>          Components: IPC/RPC
>            Reporter: Chao Shi
>            Assignee: Chao Shi
>             Fix For: 0.98.0
>
>         Attachments: hbase-8884.patch, hbase-8884-v2.patch, hbase-8884-v3.patch, hbase-8884-v4.patch,
hbase-8884-v5.patch, hbase-8884-v6.patch, hbase-8884-v7.patch, hbase-8884-v8.patch
>
>
> Today, the RPC scheduling mechanism is pretty simple: it execute requests in isolated
thread-pools based on their priority. In the current implementation, all normal get/put requests
are using the same pool. We'd like to add some per-user or per-region level isolation, so
that a misbehaved user/region will not saturate the thread-pool and cause DoS to others easily.
The idea is similar to FairScheduler in MR. The current scheduling code is not standalone
and is mixed with others (Connection#processRequest). The issue is the first step to extract
it to an interface, so that people are free to write and test their own implementations.
> This patch doesn't make it completely pluggable yet, as some parameters are pass from
constructor. This is because HMaster and HRegionServer both use RpcServer and they have different
thread-pool size config. Let me know if you have a solution to this.

--
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