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

Posted to issues@beam.apache.org by "Sam Whittle (Jira)" <ji...@apache.org> on 2021/02/01 15:05:00 UTC

[jira] [Created] (BEAM-11730) Reduce context switches for dataflow streaming appliance getdata reads

Sam Whittle created BEAM-11730:
----------------------------------

             Summary: Reduce context switches for dataflow streaming appliance getdata reads
                 Key: BEAM-11730
                 URL: https://issues.apache.org/jira/browse/BEAM-11730
             Project: Beam
          Issue Type: Bug
          Components: runner-dataflow
            Reporter: Sam Whittle
            Assignee: Sam Whittle


Currently reads are batched and issued from a separate thread pool of reading threads.  However in the case that there is not read queuing due to the max # of parallel requests, switching threads is unnecessary and adds additional context swithing overhead.

In a benchmark I observed 5% cpu spent on LockSupport.park which some googling indicates is due to context switching.



--
This message was sent by Atlassian Jira
(v8.3.4#803005)