chenboat edited a comment on pull request #6778:
URL: https://github.com/apache/pinot/pull/6778#issuecomment-917298474
@Jackie-Jiang The segment zk metadata read method has this comment before it
saying the op is very expensive. Either it is outdated or we should be careful
about reading a lot of segment's zk metadata all together. Our prod cluster has
million of segments and thus is pretty big. I understand today's code already
performs the read of all segments. We want extra protection and ramp up and
down mechanism. The number of look back days is such a knob we can turn.
btw, I also noticed some of our large cluster's retention job failed -- we
need to check zk access is the root cause.
https://github.com/apache/pinot/blob/7e9ca6a5a4afe0d4e283ac1307c45430e474cbf2/pinot-common/src/main/java/org/apache/pinot/common/metadata/ZKMetadataProvider.java#L271-L275
--
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]
