linux-kernel - Re: Kernel 6.14.11 dl_server_timer(...) causing IPI/Function Call Interrupts on isolcpu/nohz

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: <aTBJPCiI9iVNYTWR@jlelli-thinkpadt14gen4.remote.csb>
Date: Wed, 3 Dec 2025 15:29:16 +0100
From: Juri Lelli <juri.lelli@...hat.com>
To: David Haufe <dhaufe@...plextrading.com>
Cc: linux-kernel@...r.kernel.org
Subject: Re: Kernel 6.14.11 dl_server_timer(...) causing IPI/Function Call
 Interrupts on isolcpu/nohz_full cores, performance regression

On 25/11/25 13:33, David Haufe wrote:
> f237e524f3c7 ("sched/deadline: Make dl-server nohz full aware") <--
> patch applied
> 219a63335b67 ("sched/deadline: Don't count nr_running twice for
> dl_server proxy tasks") <-- exists in mainline 6.17
> 7620177e8108 ("sched/deadline: Fix RT task potential starvation when
> expiry time passed") <-- exists in mainline 6.17
> cccb45d7c429 ("sched/deadline: Less agressive dl_server handling") <--
> slightly different code but exists in mainline 6.17
> 
> The "nohz full aware" patch does stop the hrtimer interrupts. I will
> watch for that merge and can patch locally for now. Thank you!

Thanks for testing and reporting!

Unfortunately (as I mentioned) I will be soon traveling + pto until
essentially next year. So, apologies, but I will most probably need to
defer cleaning up and send out a proper version to beginning of 2026.
Hope that's OK.

Best,
Juri