linux-kernel - Re: [PATCH] sched/fair: Do not wakeup-preempt same-prio SCHED

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

Message-ID: <eb6313e5fb4bdb45df20351967694ebdd105ee2a.camel@gmx.de>
Date:   Tue, 19 Sep 2023 11:48:18 +0200
From:   Mike Galbraith <efault@....de>
To:     Ingo Molnar <mingo@...nel.org>
Cc:     K Prateek Nayak <kprateek.nayak@....com>,
        "Peter Zijlstra (Intel)" <peterz@...radead.org>,
        linux-kernel@...r.kernel.org, linux-tip-commits@...r.kernel.org,
        x86@...nel.org, Chen Yu <yu.c.chen@...el.com>,
        Gautham Shenoy <gautham.shenoy@....com>
Subject: Re: [PATCH] sched/fair: Do not wakeup-preempt same-prio SCHED_OTHER
 tasks

On Tue, 2023-09-19 at 11:02 +0200, Ingo Molnar wrote:
>
> BTW., if overscheduling is still an issue...

The trouble I had with overscheduling was mostly about annoying insta-
preempt creating useless overhead, and that the RUN_TO_PARITY thing
ended. All I see now is the expected 60/40 indeed != 50/50, so things
are gonna shift a bit.

Most of the testing I've done lately has been due to fretting over the
desktop perhaps getting the short end of that shift, but after much
poking and prodding, everything seems just fine here.

	-Mike