[
https://issues.apache.org/jira/browse/KUDU-18?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15930607#comment-15930607
]
Todd Lipcon commented on KUDU-18:
---------------------------------
Just updating this issue to note that it's still relevant, and actually
potentially causing some problems for concurrent write + long query scenarios.
If a long query is running while an ingest workload is going, the flushes
during those scans essentially do not free memory because of the retention by
the scanners.
> Handle "slow readers" not holding too much memory
> -------------------------------------------------
>
> Key: KUDU-18
> URL: https://issues.apache.org/jira/browse/KUDU-18
> Project: Kudu
> Issue Type: Improvement
> Components: tablet
> Affects Versions: M3
> Reporter: Todd Lipcon
>
> Currently if a scanner is held open, it can hold on to resources from the
> tablet indefinitely. This includes memory resources like
> MemRowSet/DeltaMemStore which can be quite large. We should figure out a way
> to forceably expire slow scanners or otherwise migrate them to the flushed
> copies.
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
