Andrew Or created SPARK-12253: --------------------------------- Summary: 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