hama-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "ChiaHung Lin (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HAMA-413) Remove limitation on the number of tasks
Date Wed, 24 Aug 2011 06:25:29 GMT

    [ https://issues.apache.org/jira/browse/HAMA-413?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13090024#comment-13090024
] 

ChiaHung Lin commented on HAMA-413:
-----------------------------------

Originally we have groom servers heartbeating to bspmaster for requesting task assign and
updating task status. After HAMA-346, the master plays a role to proactively schedule tasks,
and doReport() is used by groom server for reporting tasks status back to master; but seemingly
it's moved to offerService() because of the ticket HAMA-298.  

Can you give a bit more explain on the root cause of `File does not exist' issue? Last time
I observed this issue and then solved it by setting zk at client side (e.g. PiEstimator, SerializePrinting)
imposing client to check if data has been written to hdfs by BSPPeer; and the result shows
it worked as expected. If this is not the case, then we will need to find out the main problem
behind it.

> Remove limitation on the number of tasks
> ----------------------------------------
>
>                 Key: HAMA-413
>                 URL: https://issues.apache.org/jira/browse/HAMA-413
>             Project: Hama
>          Issue Type: Sub-task
>          Components: bsp
>    Affects Versions: 0.3.0
>            Reporter: Edward J. Yoon
>            Assignee: Edward J. Yoon
>             Fix For: 0.4.0
>
>         Attachments: HAMA-413_v01.patch, HAMA-413_v02.patch, HAMA-413_v03.patch, HAMA_413_v04.patch
>
>
> By HAMA-410 patch, BSPPeer object will be constructed at child process. Now we can just
remove limitation on the number of tasks.
> Here's TODO list:
> 1. The number of tasks per groom should be configurable e.g., 'bsp.local.tasks.maximum'.
> 2. The 'totalTaskCapacity' should be calculated at BSPMaster.getClusterStatus().
> 3. When scheduling tasks, consider how to allocate them.
> 4. Each BSPPeer should know all created peers of Hama cluster by job. It can be listed
based on actions of GroomServer.
> 5. In examples, 'cluster.getGroomServers()' can be changed to 'cluster.getMaxTasks()'.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message