Eric Liang created SPARK-17370: ---------------------------------- Summary: Shuffle service files not invalidated when a slave is lost Key: SPARK-17370 URL: https://issues.apache.org/jira/browse/SPARK-17370 Project: Spark Issue Type: Bug Reporter: Eric Liang
DAGScheduler invalidates shuffle files when an executor loss event occurs, but not when the external shuffle service is enabled. This is because when shuffle service is on, the shuffle file lifetime can exceed the executor lifetime. However, it doesn't invalidate shuffle files when the shuffle service itself is lost (due to whole slave loss). This can cause long hangs when slaves are lost since the file loss is not detected until a subsequent stage attempts to read the shuffle files. -- This message was sent by Atlassian JIRA (v6.3.4#6332) --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@spark.apache.org For additional commands, e-mail: issues-h...@spark.apache.org