[ https://issues.apache.org/jira/browse/SPARK-12253?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15049918#comment-15049918 ]
Apache Spark commented on SPARK-12253: -------------------------------------- User 'andrewor14' has created a pull request for this issue: https://github.com/apache/spark/pull/10240 > UnifiedMemoryManager race condition: storage can starve new tasks > ----------------------------------------------------------------- > > Key: SPARK-12253 > URL: https://issues.apache.org/jira/browse/SPARK-12253 > Project: Spark > Issue Type: Bug > Components: Spark Core > Affects Versions: 1.6.0 > Reporter: Andrew Or > Assignee: Andrew Or > Priority: Blocker > > The following race condition is possible with the existing code in unified > memory management: > (1) Existing tasks collectively occupy all execution memory > (2) New task comes in and blocks while existing tasks spill > (3) After tasks finish spilling, another task jumps in and puts in a large > block, stealing the freed memory > (4) New task still cannot acquire memory and goes back to sleep -- 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