ankuriitg commented on issue #24208: [SPARK-27272][CORE] Enable blacklisting of node/executor on fetch failures by default URL: https://github.com/apache/spark/pull/24208#issuecomment-476355672 I do not have any instances where the current version is too aggressive but I think that can be a case in some instances. So, I think it may be useful to track the failures before blacklisting a node. I realize that MAX_FAILED_EXEC_PER_NODE is at the application level and I want to keep it that way, as there is a possibility that we may not observe another fetch failure from the same stage but we may get it from another stage or another stage attempt (this was observed in my situation).
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
