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

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Date: Thu, 20 Jun 2024 14:32:37 -0700
From: Josh Don <joshdon@...gle.com>
To: Vincent Guittot <vincent.guittot@...aro.org>
Cc: Ingo Molnar <mingo@...hat.com>, Peter Zijlstra <peterz@...radead.org>, 
	Juri Lelli <juri.lelli@...hat.com>, Dietmar Eggemann <dietmar.eggemann@....com>, 
	Steven Rostedt <rostedt@...dmis.org>, Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>, 
	Daniel Bristot de Oliveira <bristot@...hat.com>, Valentin Schneider <vschneid@...hat.com>, linux-kernel@...r.kernel.org, 
	Zhang Qiao <zhangqiao22@...wei.com>
Subject: Re: [PATCH] sched/fair: prevent unbounded task iteration in load balance

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@...wei.com 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