From: Peter Zijlstra <peterz@infradead.org>
To: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Ingo Molnar <mingo@kernel.org>,
LKML <linux-kernel@vger.kernel.org>,
Mel Gorman <mgorman@techsingularity.net>,
Rik van Riel <riel@surriel.com>, Yi Wang <wang.yi59@zte.com.cn>,
zhong.weidong@zte.com.cn, Yi Liu <liu.yi24@zte.com.cn>,
Frederic Weisbecker <frederic@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH v2] sched/core: Don't mix isolcpus and housekeeping CPUs
Date: Fri, 26 Oct 2018 10:42:55 +0200 [thread overview]
Message-ID: <20181026084255.GZ3109@worktop.c.hoisthospitality.com> (raw)
In-Reply-To: <20181025182317.GE18466@linux.vnet.ibm.com>
On Thu, Oct 25, 2018 at 11:53:17PM +0530, Srikar Dronamraju wrote:
> >
> > You can create multiple partitions with cpusets but still have an
> > unbound task in the root cgroup. That would suffer the exact same
> > problems.
> >
>
> I probably don't understand this. Even if the child cgroups has
> cpu_exclusive or sched_load_balance reset, the tasks in root cgroup has
> access to all cpus in system. Right?
The crucial word being 'access'. The root group will not impose a limit
on the affinity of tasks. So you can indeed have affinities that span
load balancing domains.
And yes, that leads to 'interesting' but specified behaviour.
prev parent reply other threads:[~2018-10-26 8:50 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-10-24 3:02 [PATCH v2] sched/core: Don't mix isolcpus and housekeeping CPUs Srikar Dronamraju
2018-10-24 8:56 ` Mel Gorman
2018-10-24 9:46 ` Srikar Dronamraju
2018-10-24 10:15 ` Peter Zijlstra
2018-10-24 10:41 ` Srikar Dronamraju
2018-10-24 11:21 ` Mel Gorman
2018-10-24 10:31 ` Mel Gorman
2018-10-24 10:03 ` Peter Zijlstra
2018-10-24 10:30 ` Srikar Dronamraju
2018-10-25 0:07 ` Peter Zijlstra
2018-10-25 17:30 ` Srikar Dronamraju
2018-10-26 8:41 ` Peter Zijlstra
2018-10-26 9:30 ` Srikar Dronamraju
2018-10-25 18:23 ` Srikar Dronamraju
2018-10-26 8:42 ` Peter Zijlstra [this message]
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=20181026084255.GZ3109@worktop.c.hoisthospitality.com \
--to=peterz@infradead.org \
--cc=frederic@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=liu.yi24@zte.com.cn \
--cc=mgorman@techsingularity.net \
--cc=mingo@kernel.org \
--cc=riel@surriel.com \
--cc=srikar@linux.vnet.ibm.com \
--cc=tglx@linutronix.de \
--cc=wang.yi59@zte.com.cn \
--cc=zhong.weidong@zte.com.cn \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).