[ 
https://issues.apache.org/jira/browse/YARN-5605?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15471261#comment-15471261
 ] 

ASF GitHub Bot commented on YARN-5605:
--------------------------------------

Github user templedf commented on a diff in the pull request:

    https://github.com/apache/hadoop/pull/124#discussion_r77868830
  
    --- Diff: 
hadoop-yarn-project/hadoop-yarn/hadoop-yarn-server/hadoop-yarn-server-resourcemanager/src/main/java/org/apache/hadoop/yarn/server/resourcemanager/scheduler/fair/FSLeafQueue.java
 ---
    @@ -316,26 +377,12 @@ public Resource assignContainer(FSSchedulerNode node) 
{
           return assigned;
         }
     
    -    // Apps that have resource demands.
    -    TreeSet<FSAppAttempt> pendingForResourceApps =
    -        new TreeSet<FSAppAttempt>(policy.getComparator());
    -    readLock.lock();
    -    try {
    -      for (FSAppAttempt app : runnableApps) {
    -        Resource pending = app.getAppAttemptResourceUsage().getPending();
    -        if (!pending.equals(Resources.none())) {
    -          pendingForResourceApps.add(app);
    -        }
    -      }
    -    } finally {
    -      readLock.unlock();
    -    }
    -    for (FSAppAttempt sched : pendingForResourceApps) {
    +    for (FSAppAttempt sched : fetchAppsWithDemand()) {
           if (SchedulerAppUtils.isPlaceBlacklisted(sched, node, LOG)) {
             continue;
    --- End diff --
    
    It would be nice to replace this _continue_ by wrapping the next few lines 
in the _if_.


> Preempt containers (all on one node) to meet the requirement of starved 
> applications
> ------------------------------------------------------------------------------------
>
>                 Key: YARN-5605
>                 URL: https://issues.apache.org/jira/browse/YARN-5605
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: fairscheduler
>            Reporter: Karthik Kambatla
>            Assignee: Karthik Kambatla
>         Attachments: yarn-5605-1.patch
>
>
> Required items:
> # Identify starved applications
> # Identify a node that has enough containers from applications over their 
> fairshare.
> # Preempt those containers



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org
For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org

Reply via email to