[
https://issues.apache.org/jira/browse/HAMA-413?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13089470#comment-13089470
]
Edward J. Yoon commented on HAMA-413:
-------------------------------------
Now, ClusterStatus.getActiveGroomNames() method returns the names of groom
servers and their host names e.g., ["groomd_test.com_50000", "test.com"], ...
It was the pair of 'groom server name' and 'peer name' e.g.,
["groomd_test.com_50000", "test.com:61000"], ....
Others are the same with before. So, changed below part only in PiEstimator.
{code}
PiEstimator:
// Choose one as a master
for (String hostName : cluster.getActiveGroomNames().values()) {
conf.set(MASTER_TASK, hostName + ":" + Constants.DEFAULT_PEER_PORT);
break;
}
{code}
> 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
>
>
> 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
