Re: [PATCH] sched/fair: prevent unbounded task iteration in load balance

From: Josh Don
Date: Thu Jun 20 2024 - 17:33:03 EST


Hey Vincent,

> I went back in the archive to remember how I came up with this patch.
> I thought that it was fixing a problem raised by
> zhangqiao22@xxxxxxxxxx but my memory was wrong and it isn't. Instead
> it's fixing a theoretical case described in the email thread:
> https://lore.kernel.org/lkml/20220818083133.GA536@vingu-book/
>
> So I wonder if it's worth adding a new debugfs entry for a case that
> nobody might have ever faced or at least complained about. I know that
> I asked you to go in this direction whereas you were originally
> proposing a revert. After more time to think about this, I'm no longer
> convinced that it's worth adding a new debugfs interface finally.
>
> I put some comments below but maybe it would be better to simply
> revert b0defa7ae03ec as nobody yet complains with this problem so far.
> Let see what other will say or if someone finally faced the problem
> but a revert may finally be a better option.

Sure, I have no problem with replacing this instead with a simple
revert of the original patch. It doesn't seem outlandish that someone
might see some benefit from this new interface, with a particularly
antagonistic set of threads and affinities. But, from my side I don't
have a strong preference either way.

I'll go ahead and send a revert :)

Best,
Josh