[
https://issues.apache.org/jira/browse/KUDU-3407?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17623529#comment-17623529
]
Song Jiacheng commented on KUDU-3407:
-------------------------------------
Thank you for your comment, [~aserbin]!
Yes, the test will be needed to test this and also other policies like you
said. Would it be more suitable to create another issue to develop the
testbench? It seems not strongly related to this patch.
And I'm working on the patch and the test both.
> MM: Give a chance to do other OP while server is under memory pressure
> ----------------------------------------------------------------------
>
> Key: KUDU-3407
> URL: https://issues.apache.org/jira/browse/KUDU-3407
> Project: Kudu
> Issue Type: Improvement
> Components: compaction
> Affects Versions: 1.14.0
> Reporter: Song Jiacheng
> Priority: Major
>
> For now, if the server is under pressure(60% memory as default),
> MaintenanceManager always find a memory-flush operation to run. So if all the
> tservers are under pressure for a long time, there will be many pending
> operations, which will lead to many problem, like redos not compact, undo not
> delete, etc..
> It might be better if we add a parameter to give a change to do other ops,
> the formula is like this:
> Do other works? = (1 - (memory_now - pressure_threshold) / (soft_limit -
> pressure_threshold)) * kChance
> kChange should be configurable.
> This will give a probability to run other maintenance operations.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
