You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@flink.apache.org by "Alexander Fedulov (Jira)" <ji...@apache.org> on 2022/02/10 14:14:00 UTC

[jira] [Created] (FLINK-26074) Improve FlameGraphs scalability for high parallelism jobs

Alexander Fedulov created FLINK-26074:
-----------------------------------------

             Summary: Improve FlameGraphs scalability for high parallelism jobs
                 Key: FLINK-26074
                 URL: https://issues.apache.org/jira/browse/FLINK-26074
             Project: Flink
          Issue Type: Improvement
            Reporter: Alexander Fedulov


The FlameGraph feature added in FLINK-13550 issues 1 RPC call per subtask. This may cause performance problems for jobs with high paralleism and a lot of subtask running on the same TaskManager. It should be possible to improve this by grouping thread sampling requests using 
{code:java}
ThreadMXBean.getThreadInfo(long[] ids, int maxDepth){code}
instead of the currently used individual calls
{code:java}
ThreadMXBean.getThreadInfo(long id, int maxDepth){code}



--
This message was sent by Atlassian Jira
(v8.20.1#820001)