You are viewing a plain text version of this content. The canonical link for it is here.
Posted to yarn-issues@hadoop.apache.org by "Sandy Ryza (JIRA)" <ji...@apache.org> on 2013/05/11 01:05:18 UTC
[jira] [Updated] (YARN-394) RM should be able to return requests
that it cannot fulfill
[ https://issues.apache.org/jira/browse/YARN-394?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Sandy Ryza updated YARN-394:
----------------------------
Description:
Currently, the RM has no way of returning requests that cannot be met. e.g. if the app wants a specific node and that node dies, then the RM should return that request instead of holding onto to it indefinitely.
Some situations in which this would be useful are:
* After YARN-392, requests are location specific, and the locations that were requested are no longer in the cluster.
* A high memory machine is lost, and resource requests above certain sizes are no longer able to be satisfied anywhere.
* All nodes in the cluster become unavailable.
At these points, there is no way the RM can inform the apps about its inability to allocate requests.
was:Currently, the RM has no way of returning requests that cannot be met. e.g. if the app wants a specific node and that node dies, then the RM should return that request instead of holding onto to it indefinitely. Currently, since every request can be met at * locality such a situation is hard to repro. It can however happen that all nodes in a cluster become unavailable. At that point, there is no way the RM can inform the apps about its inability to allocate requests.
> RM should be able to return requests that it cannot fulfill
> -----------------------------------------------------------
>
> Key: YARN-394
> URL: https://issues.apache.org/jira/browse/YARN-394
> Project: Hadoop YARN
> Issue Type: Sub-task
> Reporter: Bikas Saha
> Assignee: Bikas Saha
>
> Currently, the RM has no way of returning requests that cannot be met. e.g. if the app wants a specific node and that node dies, then the RM should return that request instead of holding onto to it indefinitely.
> Some situations in which this would be useful are:
> * After YARN-392, requests are location specific, and the locations that were requested are no longer in the cluster.
> * A high memory machine is lost, and resource requests above certain sizes are no longer able to be satisfied anywhere.
> * All nodes in the cluster become unavailable.
> At these points, there is no way the RM can inform the apps about its inability to allocate requests.
--
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