[ 
https://issues.apache.org/jira/browse/YARN-1680?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14276599#comment-14276599
 ] 

Chen He commented on YARN-1680:
-------------------------------

To address the twice blacklist issue (a node is blacklist by App and later by 
cluster). 
I propose two steps:
1. Every time, App asks for blacklist addition, we check wether the nodes in 
addition are in cluster blacklist or not (O(m), m is the nodes in blacklist 
addition). If so, remove this node from addition. 
2. It is possible that App unblacklist a node (put it in blacklist removal) but 
the cluster still blacklist it. In this situation, the clusterResource does not 
contain this node resource. Then, we need to remove this node from App's 
blacklist removal set in headroom caculation.  

> availableResources sent to applicationMaster in heartbeat should exclude 
> blacklistedNodes free memory.
> ------------------------------------------------------------------------------------------------------
>
>                 Key: YARN-1680
>                 URL: https://issues.apache.org/jira/browse/YARN-1680
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>    Affects Versions: 2.2.0, 2.3.0
>         Environment: SuSE 11 SP2 + Hadoop-2.3 
>            Reporter: Rohith
>            Assignee: Chen He
>         Attachments: YARN-1680-WIP.patch, YARN-1680-v2.patch, 
> YARN-1680-v2.patch, YARN-1680.patch
>
>
> There are 4 NodeManagers with 8GB each.Total cluster capacity is 32GB.Cluster 
> slow start is set to 1.
> Job is running reducer task occupied 29GB of cluster.One NodeManager(NM-4) is 
> become unstable(3 Map got killed), MRAppMaster blacklisted unstable 
> NodeManager(NM-4). All reducer task are running in cluster now.
> MRAppMaster does not preempt the reducers because for Reducer preemption 
> calculation, headRoom is considering blacklisted nodes memory. This makes 
> jobs to hang forever(ResourceManager does not assing any new containers on 
> blacklisted nodes but returns availableResouce considers cluster free 
> memory). 



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

Reply via email to