From: Waiman Long <llong@redhat.com> To: Frederic Weisbecker <frederic@kernel.org>, LKML <linux-kernel@vger.kernel.org> Cc: Tejun Heo <tj@kernel.org>, Peter Zijlstra <peterz@infradead.org>, Juri Lelli <juri.lelli@redhat.com>, Alex Belits <abelits@marvell.com>, Nitesh Lal <nilal@redhat.com>, Thomas Gleixner <tglx@linutronix.de>, Nicolas Saenz <nsaenzju@redhat.com>, Christoph Lameter <cl@gentwo.de>, Marcelo Tosatti <mtosatti@redhat.com>, Zefan Li <lizefan.x@bytedance.com>, cgroups@vger.kernel.org Subject: Re: [RFC PATCH 0/6] cpuset: Allow to modify isolcpus through cpuset Date: Fri, 16 Jul 2021 14:02:50 -0400 [thread overview] Message-ID: <8ea7a78f-948e-75e8-1c4f-59b349c858f6@redhat.com> (raw) In-Reply-To: <20210714135420.69624-1-frederic@kernel.org> On 7/14/21 9:54 AM, Frederic Weisbecker wrote: > The fact that "isolcpus=" behaviour can't be modified at runtime is an > eternal source of discussion and debate opposing a useful feature against > a terrible interface. > > I've long since tried to figure out a proper way to control this at > runtime using cpusets, which isn't easy as a boot time single cpumask > is difficult to map to a hierarchy of cpusets that can even overlap. I have a cpuset patch that allow disabling of load balancing in a cgroup-v2 setting: https://lore.kernel.org/lkml/20210621184924.27493-1-longman@redhat.com/ The idea of cpuset partition is that there will be no overlap of cpus in different partitions. So there will be no confusion whether a cpu is load-balanced or not. > > The idea here is to map the boot-set isolation behaviour to any cpuset > directory whose cpumask is a subset of "isolcpus=". I let you browse > for details on the last patch. > > Note this is still WIP and half-baked, but I figured it's important to > validate the interface early. Using different cpumasks for different isolated properties is the easy part. The hard part is to make different subsystems to change their behavior as the isolation masks change dynamically at run time. Currently, they check the housekeeping cpumask only at boot time or when certain events happen. Cheers, Longman
WARNING: multiple messages have this Message-ID (diff)
From: Waiman Long <llong-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org> To: Frederic Weisbecker <frederic-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>, LKML <linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org> Cc: Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>, Peter Zijlstra <peterz-wEGCiKHe2LqWVfeAwA7xHQ@public.gmane.org>, Juri Lelli <juri.lelli-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, Alex Belits <abelits-eYqpPyKDWXRBDgjK7y7TUQ@public.gmane.org>, Nitesh Lal <nilal-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, Thomas Gleixner <tglx-hfZtesqFncYOwBW4kG4KsQ@public.gmane.org>, Nicolas Saenz <nsaenzju-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, Christoph Lameter <cl-LoxgEY9JZOazQB+pC5nmwQ@public.gmane.org>, Marcelo Tosatti <mtosatti-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>, Zefan Li <lizefan.x-EC8Uxl6Npydl57MIdRCFDg@public.gmane.org>, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org Subject: Re: [RFC PATCH 0/6] cpuset: Allow to modify isolcpus through cpuset Date: Fri, 16 Jul 2021 14:02:50 -0400 [thread overview] Message-ID: <8ea7a78f-948e-75e8-1c4f-59b349c858f6@redhat.com> (raw) In-Reply-To: <20210714135420.69624-1-frederic-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org> On 7/14/21 9:54 AM, Frederic Weisbecker wrote: > The fact that "isolcpus=" behaviour can't be modified at runtime is an > eternal source of discussion and debate opposing a useful feature against > a terrible interface. > > I've long since tried to figure out a proper way to control this at > runtime using cpusets, which isn't easy as a boot time single cpumask > is difficult to map to a hierarchy of cpusets that can even overlap. I have a cpuset patch that allow disabling of load balancing in a cgroup-v2 setting: https://lore.kernel.org/lkml/20210621184924.27493-1-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org/ The idea of cpuset partition is that there will be no overlap of cpus in different partitions. So there will be no confusion whether a cpu is load-balanced or not. > > The idea here is to map the boot-set isolation behaviour to any cpuset > directory whose cpumask is a subset of "isolcpus=". I let you browse > for details on the last patch. > > Note this is still WIP and half-baked, but I figured it's important to > validate the interface early. Using different cpumasks for different isolated properties is the easy part. The hard part is to make different subsystems to change their behavior as the isolation masks change dynamically at run time. Currently, they check the housekeeping cpumask only at boot time or when certain events happen. Cheers, Longman
next prev parent reply other threads:[~2021-07-16 18:02 UTC|newest] Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-07-14 13:54 [RFC PATCH 0/6] cpuset: Allow to modify isolcpus through cpuset Frederic Weisbecker 2021-07-14 13:54 ` Frederic Weisbecker 2021-07-14 13:54 ` [RFC PATCH 1/6] pci: Decouple HK_FLAG_WQ and HK_FLAG_DOMAIN cpumask fetch Frederic Weisbecker 2021-07-14 13:54 ` [RFC PATCH 2/6] workqueue: " Frederic Weisbecker 2021-07-14 13:54 ` Frederic Weisbecker 2021-07-14 13:54 ` [RFC PATCH 3/6] net: " Frederic Weisbecker 2021-07-14 13:54 ` [RFC PATCH 4/6] sched/isolation: Split domain housekeeping mask from the rest Frederic Weisbecker 2021-07-14 13:54 ` Frederic Weisbecker 2021-07-14 13:54 ` [RFC PATCH 5/6] sched/isolation: Make HK_FLAG_DOMAIN mutable Frederic Weisbecker 2021-07-14 13:54 ` Frederic Weisbecker 2021-07-21 14:28 ` Vincent Donnefort 2021-07-14 13:54 ` [RFC PATCH 6/6] cpuset: Add cpuset.isolation_mask file Frederic Weisbecker 2021-07-14 13:54 ` Frederic Weisbecker 2021-07-14 16:31 ` Marcelo Tosatti 2021-07-19 13:26 ` Frederic Weisbecker 2021-07-19 13:26 ` Frederic Weisbecker 2021-07-19 15:41 ` Marcelo Tosatti 2021-07-19 15:41 ` Marcelo Tosatti 2021-07-14 16:52 ` Peter Zijlstra 2021-07-14 16:52 ` Peter Zijlstra 2021-07-14 23:13 ` Frederic Weisbecker 2021-07-14 23:13 ` Frederic Weisbecker 2021-07-14 23:44 ` Valentin Schneider 2021-07-14 23:44 ` Valentin Schneider 2021-07-15 0:07 ` Frederic Weisbecker 2021-07-15 0:07 ` Frederic Weisbecker 2021-07-15 9:04 ` Peter Zijlstra 2021-07-15 9:04 ` Peter Zijlstra 2021-07-19 13:17 ` Frederic Weisbecker 2021-07-19 13:17 ` Frederic Weisbecker 2021-07-16 18:02 ` Waiman Long [this message] 2021-07-16 18:02 ` [RFC PATCH 0/6] cpuset: Allow to modify isolcpus through cpuset Waiman Long 2021-07-19 13:57 ` Frederic Weisbecker 2021-07-19 13:57 ` Frederic Weisbecker
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=8ea7a78f-948e-75e8-1c4f-59b349c858f6@redhat.com \ --to=llong@redhat.com \ --cc=abelits@marvell.com \ --cc=cgroups@vger.kernel.org \ --cc=cl@gentwo.de \ --cc=frederic@kernel.org \ --cc=juri.lelli@redhat.com \ --cc=linux-kernel@vger.kernel.org \ --cc=lizefan.x@bytedance.com \ --cc=mtosatti@redhat.com \ --cc=nilal@redhat.com \ --cc=nsaenzju@redhat.com \ --cc=peterz@infradead.org \ --cc=tglx@linutronix.de \ --cc=tj@kernel.org \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.