linux-kernel - Re: [PATCH v3 3/5] sched/fair: Switch to task based throttle model

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]

Message-ID: <20250904084056.GF42@bytedance>
Date: Thu, 4 Sep 2025 16:40:56 +0800
From: Aaron Lu <ziqianlu@...edance.com>
To: "Bezdeka, Florian" <florian.bezdeka@...mens.com>
Cc: "kprateek.nayak@....com" <kprateek.nayak@....com>,
	"liusongtang@...edance.com" <liusongtang@...edance.com>,
	"dietmar.eggemann@....com" <dietmar.eggemann@....com>,
	"zhouchuyi@...edance.com" <zhouchuyi@...edance.com>,
	"bigeasy@...utronix.de" <bigeasy@...utronix.de>,
	"mgorman@...e.de" <mgorman@...e.de>,
	"Kiszka, Jan" <jan.kiszka@...mens.com>,
	"vincent.guittot@...aro.org" <vincent.guittot@...aro.org>,
	"chengming.zhou@...ux.dev" <chengming.zhou@...ux.dev>,
	"mingo@...hat.com" <mingo@...hat.com>,
	"rostedt@...dmis.org" <rostedt@...dmis.org>,
	"joshdon@...gle.com" <joshdon@...gle.com>,
	"vschneid@...hat.com" <vschneid@...hat.com>,
	"xii@...gle.com" <xii@...gle.com>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"peterz@...radead.org" <peterz@...radead.org>,
	"bsegall@...gle.com" <bsegall@...gle.com>,
	"juri.lelli@...hat.com" <juri.lelli@...hat.com>
Subject: Re: [PATCH v3 3/5] sched/fair: Switch to task based throttle model

Hi Florian,

On Thu, Sep 04, 2025 at 07:33:03AM +0000, Bezdeka, Florian wrote:
> Hi Aaron,
> 
> On Wed, 2025-09-03 at 19:35 +0800, Aaron Lu wrote:
> > 
> > > [..snip..]
> > > > 
> > 
> > Just want to add that with the above diff applied, I also tested
> > songtang's stress test[0] and Jan's rt deadlock reproducer[1] and didn't
> > see any problem.
> 
> Thanks a lot for taking the reproducer into account. But: To trigger
> PREEMPT_RT needs to be enabled, otherwise the rwlock in the epoll
> infrastructure (that we highly stress) won't sleep. Just to be sure:
> PREEMPT_RT was enabled on your end?
>

Yes, understood.

I've PREEMPT_RT enabled when running Jan's rt deadlock reproducer. I
also run base and make sure there is hung happened in base before
testing this series. Normally, base would hung in 2 minutes and when
testing this series, I'll give it 5 minutes to see if anything abnormal
happened.

> > 
> > [0]: https://lore.kernel.org/lkml/20250715072218.GA304@bytedance/
> > [1]: https://lore.kernel.org/all/7483d3ae-5846-4067-b9f7-390a614ba408@siemens.com/