From mboxrd@z Thu Jan 1 00:00:00 1970 From: Sebastian Andrzej Siewior Subject: Re: Kernel thread's CPU affinity with isolcpus kernel boot argument Date: Thu, 25 Feb 2016 17:35:43 +0100 Message-ID: <56CF2D5F.60306@linutronix.de> References: <5698D4D0.3020907@etas.com> <20160225141806.GB16161@linutronix.de> <56CF1A2A.1050203@bristot.me> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: "linux-rt-users@vger.kernel.org" To: Daniel Bristot de Oliveira , Mathias Koehrer Return-path: Received: from www.linutronix.de ([62.245.132.108]:54341 "EHLO Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757854AbcBYQfr (ORCPT ); Thu, 25 Feb 2016 11:35:47 -0500 In-Reply-To: <56CF1A2A.1050203@bristot.me> Sender: linux-rt-users-owner@vger.kernel.org List-ID: On 02/25/2016 04:13 PM, Daniel Bristot de Oliveira wrote: > On 02/25/2016 11:18 AM, Sebastian Andrzej Siewior wrote: >> not that I am aware of. There are a few per-CPU threads which have t= o >> stay the way they are. I would have expected that others like kworke= r/u* >> respect the isol CPUs and stay away. >=20 > Isolcpus is applied only for user-space threads. For instance, you > still need to move rcu offload callbacks away from isolated CPUs, and > all other kernel threads as well. RCU is special since this is a per-CPU thread. However Paul did make an option where you can move those to another CPU. > In the special case of kworker/u* threads, you need to use a special > interface to do it. The interface is the following file: >=20 > /sys/devices/virtual/workqueue/cpumask I see it documented in "Documentation/ABI". Oh wait=E2=80=A6 > It was implemented on the following commit: >=20 > 042f7df workqueue: Allow modifying low level unbound workqueue cpumas= k >=20 > But the default CPU mask is the "cpu_possible_mask". >=20 > Sometime ago I sent a patch to modify the default mask of the kworker= /u* > threads, to avoid them on isolated CPUs by default, but it was not > acked. It was not explicitly nacked, though. >=20 > http://www.gossamer-threads.com/lists/linux/kernel/2218495 >=20 > Should I try it again? Atleast they do have a default cpumask which you can modify. I don't see why the kworker should be special here and avoid the isolcpu mask. I *do* support the default mask being !isolcpus and not cpu_possible. If you have the time to try again, please do so. >=20 > -- Daniel >=20 Sebastian -- To unsubscribe from this list: send the line "unsubscribe linux-rt-user= s" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html