gianm opened a new pull request, #20655:
URL: https://github.com/apache/druid/pull/20655
Two changes related to how Scan queries schedule segments for processing:
1) ScanQueryRunnerFactory now skips segments that cannot possibly
emit a row that makes it into the resultset. There was previously
some logic doing this, but it effectively led to extra time
chunks being scanned beyond what was really necessary.
2) ServerManager now builds one segment runner per descriptor in
descriptor order when calling QueryRunnerFactory#mergeRunners.
This enables ScanQueryRunnerFactory to correctly match up segments
and intervals. Previously this could cause out-of-order results
with VSF on-demand loading.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
