You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Marcelo Vanzin (JIRA)" <ji...@apache.org> on 2015/09/15 20:24:45 UTC
[jira] [Created] (SPARK-10622) Race condition between scheduler and
YARN executor status update
Marcelo Vanzin created SPARK-10622:
--------------------------------------
Summary: Race condition between scheduler and YARN executor status update
Key: SPARK-10622
URL: https://issues.apache.org/jira/browse/SPARK-10622
Project: Spark
Issue Type: Bug
Components: YARN
Affects Versions: 1.6.0
Reporter: Marcelo Vanzin
Priority: Critical
This is a follow up to SPARK-8167. From the comment left in the code:
{quote}
TODO there's a race condition where while we are querying the ApplicationMaster for the executor loss reason, there is the potential that tasks will be scheduled on the executor that failed. We should fix this by having this onDisconnected event also "blacklist" executors so that tasks are not assigned to them.
{quote}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org