You are viewing a plain text version of this content. The canonical link for it is here.

Posted to yarn-dev@hadoop.apache.org by "Prashant Golash (Jira)" <ji...@apache.org> on 2019/10/28 20:42:00 UTC

[jira] [Created] (YARN-9939) Killing running containers on UNHEALTHY nodes

Prashant Golash created YARN-9939:
-------------------------------------

             Summary: Killing running containers on UNHEALTHY nodes
                 Key: YARN-9939
                 URL: https://issues.apache.org/jira/browse/YARN-9939
             Project: Hadoop YARN
          Issue Type: Improvement
            Reporter: Prashant Golash


Currently, we kill the running containers when a node becomes unhealthy. Ideally, we should let current containers running and finish. I propose a config to disable killing the currently running containers. So, killing only happens when

removeNode {

  if (!node.unhealthy || (node.unhealthy && enableKillingOnUnhealthyNode) {

     // Kill containers

  } 

}



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-dev-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-dev-help@hadoop.apache.org