advancedxy commented on PR #428:
URL:
https://github.com/apache/incubator-uniffle/pull/428#issuecomment-1362608703
> > > `if (usedMemory.get() - preAllocatedSize.get() - inFlushSize.get() >
highWaterMark) { `
> >
> >
> > If I understand this code correctly, `usedMemory` is not updated for
preAllocated buffer. `inFlushSize` is not related to this PR.
`preAllocatedSize` is still decreased but slightly slowly.
> > In that sense, it will have less change to trigger flush. Therefore
`LOCAL_ORDER` is not influenced?
>
> In original logic, flush will be trigger when cache data, but in this pr,
it will be trigger by another rpc request.
Yeah, that's possible.... But the flush trigger is not non-deterministic
anyway, it's trigged by outside's requests, which may vary. I still don't get
why this kind of change would affect `LOCAL_ORDER` optimization or bring
performance penalty here.
--
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]
