All of lore.kernel.org
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Waiman Long <longman@redhat.com>
Cc: "Tejun Heo" <tj@kernel.org>, "Zefan Li" <lizefan.x@bytedance.com>,
	"Johannes Weiner" <hannes@cmpxchg.org>,
	"Jonathan Corbet" <corbet@lwn.net>,
	"Shuah Khan" <shuah@kernel.org>,
	cgroups@vger.kernel.org, linux-kernel@vger.kernel.org,
	linux-doc@vger.kernel.org, linux-kselftest@vger.kernel.org,
	"Andrew Morton" <akpm@linux-foundation.org>,
	"Roman Gushchin" <guro@fb.com>, "Phil Auld" <pauld@redhat.com>,
	"Juri Lelli" <juri.lelli@redhat.com>,
	"Frederic Weisbecker" <frederic@kernel.org>,
	"Marcelo Tosatti" <mtosatti@redhat.com>,
	"Michal Koutný" <mkoutny@suse.com>
Subject: Re: [PATCH v9 4/7] cgroup/cpuset: Add a new isolated cpus.partition type
Date: Wed, 12 Jan 2022 16:21:00 +0100	[thread overview]
Message-ID: <Yd7x3P+wGCVfYtza@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20211205183220.818872-5-longman@redhat.com>

On Sun, Dec 05, 2021 at 01:32:17PM -0500, Waiman Long wrote:
> Cpuset v1 uses the sched_load_balance control file to determine if load
> balancing should be enabled.  Cpuset v2 gets rid of sched_load_balance
> as its use may require disabling load balancing at cgroup root.
> 
> For workloads that require very low latency like DPDK, the latency
> jitters caused by periodic load balancing may exceed the desired
> latency limit.
> 
> When cpuset v2 is in use, the only way to avoid this latency cost is to
> use the "isolcpus=" kernel boot option to isolate a set of CPUs. After
> the kernel boot, however, there is no way to add or remove CPUs from
> this isolated set. For workloads that are more dynamic in nature, that
> means users have to provision enough CPUs for the worst case situation
> resulting in excess idle CPUs.
> 
> To address this issue for cpuset v2, a new cpuset.cpus.partition type
> "isolated" is added which allows the creation of a cpuset partition
> without load balancing. This will allow system administrators to
> dynamically adjust the size of isolated partition to the current need
> of the workload without rebooting the system.

you can, ofcourse, create lots of 1 cpu partitions, which is effectively
what you're doing, except there was a problem with that which you also
forgot to mention.



  reply	other threads:[~2022-01-12 15:21 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-05 18:32 [PATCH v9 0/7] cgroup/cpuset: Add new cpuset partition type & empty effecitve cpus Waiman Long
2021-12-05 18:32 ` [PATCH v9 1/7] cgroup/cpuset: Don't let child cpusets restrict parent in default hierarchy Waiman Long
2021-12-13 20:41   ` Tejun Heo
2021-12-15 12:23     ` Michal Koutný
     [not found]       ` <20211215122336.GB25459-9OudH3eul5jcvrawFnH+a6VXKuFTiq87@public.gmane.org>
2021-12-15 17:59         ` Waiman Long
2021-12-15 17:59           ` Waiman Long
     [not found]           ` <8d73dc26-74e1-d763-d897-6e03cdac3c8c-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2021-12-17 15:48             ` [PATCH] cgroup/cpuset: Make child cpusets restrict parents on v1 hierarchy Michal Koutný
2021-12-17 15:48               ` Michal Koutný
2021-12-17 16:34               ` Waiman Long
2022-01-12 21:25               ` Tejun Heo
2021-12-05 18:32 ` [PATCH v9 3/7] cgroup/cpuset: Refining features and constraints of a partition Waiman Long
2021-12-15 14:49   ` Michal Koutný
2021-12-15 16:29     ` Waiman Long
2021-12-15 16:29       ` Waiman Long
2021-12-16  9:28       ` Michal Koutný
2021-12-05 18:32 ` [PATCH v9 4/7] cgroup/cpuset: Add a new isolated cpus.partition type Waiman Long
2022-01-12 15:21   ` Peter Zijlstra [this message]
     [not found]     ` <Yd7x3P+wGCVfYtza-Nxj+rRp3nVydTX5a5knrm8zTDFooKrT+cvkQGrU6aU0@public.gmane.org>
2022-01-12 15:40       ` Waiman Long
2022-01-12 15:40         ` Waiman Long
     [not found]         ` <0cf37ac0-69c7-2da4-22a6-58e78dc35cef-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-01-12 21:23           ` Tejun Heo
2022-01-12 21:23             ` Tejun Heo
2021-12-05 18:32 ` [PATCH v9 5/7] cgroup/cpuset: Show invalid partition reason string Waiman Long
2021-12-05 18:32 ` [PATCH v9 6/7] cgroup/cpuset: Update description of cpuset.cpus.partition in cgroup-v2.rst Waiman Long
2021-12-13 21:00   ` Tejun Heo
     [not found]     ` <Ybe0YWEo7Wp7wib9-NiLfg/pYEd1N0TnZuCh8vA@public.gmane.org>
2021-12-15 14:44       ` Michal Koutný
2021-12-15 14:44         ` Michal Koutný
     [not found]         ` <20211215144450.GC25459-9OudH3eul5jcvrawFnH+a6VXKuFTiq87@public.gmane.org>
2021-12-15 18:16           ` Waiman Long
2021-12-15 18:16             ` Waiman Long
     [not found]             ` <96018978-6b7f-1e7f-1012-9df7f7996ec5-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2021-12-15 18:35               ` Tejun Heo
2021-12-15 18:35                 ` Tejun Heo
2021-12-15 18:55                 ` Waiman Long
     [not found]                   ` <58c06961-ffc4-27d7-01d2-4c91b0c9161d-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2022-01-12 21:21                     ` Tejun Heo
2022-01-12 21:21                       ` Tejun Heo
2021-12-05 18:32 ` [PATCH v9 7/7] kselftest/cgroup: Add cpuset v2 partition root state test Waiman Long
     [not found] ` <20211205183220.818872-1-longman-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
2021-12-05 18:32   ` [PATCH v9 2/7] cgroup/cpuset: Allow no-task partition to have empty cpuset.cpus.effective Waiman Long
2021-12-05 18:32     ` Waiman Long
2021-12-13 20:45     ` Tejun Heo
     [not found]       ` <Ybew7d2oE2gLcLNO-NiLfg/pYEd1N0TnZuCh8vA@public.gmane.org>
2021-12-15  3:24         ` Waiman Long
2021-12-15  3:24           ` Waiman Long
2021-12-15 10:36           ` Michal Koutný
2021-12-09 15:39   ` [PATCH v9 0/7] cgroup/cpuset: Add new cpuset partition type & empty effecitve cpus Waiman Long
2021-12-09 15:39     ` Waiman Long

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=Yd7x3P+wGCVfYtza@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=akpm@linux-foundation.org \
    --cc=cgroups@vger.kernel.org \
    --cc=corbet@lwn.net \
    --cc=frederic@kernel.org \
    --cc=guro@fb.com \
    --cc=hannes@cmpxchg.org \
    --cc=juri.lelli@redhat.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-kselftest@vger.kernel.org \
    --cc=lizefan.x@bytedance.com \
    --cc=longman@redhat.com \
    --cc=mkoutny@suse.com \
    --cc=mtosatti@redhat.com \
    --cc=pauld@redhat.com \
    --cc=shuah@kernel.org \
    --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: link
Be 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.