From: Nick Piggin <nickpiggin@yahoo.com.au>
To: Paul Jackson <pj@sgi.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Paul Menage <menage@google.com>,
linux-kernel@vger.kernel.org,
Dinakar Guniguntala <dino@in.ibm.com>,
cpw@sgi.com, Ingo Molnar <mingo@elte.hu>
Subject: Re: [PATCH] cpuset and sched domains: sched_load_balance flag
Date: Sun, 30 Sep 2007 05:21:02 +1000 [thread overview]
Message-ID: <200709300521.03356.nickpiggin@yahoo.com.au> (raw)
In-Reply-To: <20070930104403.24828.48263.sendpatchset@jackhammer.engr.sgi.com>
On Sunday 30 September 2007 20:44, Paul Jackson wrote:
> From: Paul Jackson <pj@sgi.com>
>
> Add a new per-cpuset flag called 'sched_load_balance'.
>
> When enabled in a cpuset (the default value) it tells the kernel
> scheduler that the scheduler should provide the normal load
> balancing on the CPUs in that cpuset, sometimes moving tasks
> from one CPU to a second CPU if the second CPU is less loaded
> and if that task is allowed to run there.
I don't like adding these funny special case sort of things like this.
The user should just be able to specify exactly the partitioning of
tasks required, and cpusets should ask the scheduler to do the best
job of load balancing possible.
I implemented that with my patches to do automatic discovery
of the largest set of disjoint cpusets.
>From there, the problem that cpusets has, is that it lacks a good
way to specify that the machine should be partitioned (IIRC because
stuff defaults to going into the root cpuset which covers all CPUs?).
Instead of adding these "I want the scheduler to do something a bit
vague but hopefully good albeit with some downsides" flags, there
should be a way to say "I want to partition the CPUs like so...", IMO.
Barring that (ie. maybe you always want a root cpuset to cover all
CPUs), then maybe we should retain the spanning sched domains
in order to balance the root cpuset, and add another set of domains
according to cpuset partitioning. This could be entirely transparent
to userspace, I think (using my patch).
Just my opinion. Good to see more thought going into this area, because
it is something that sched-domains can do really well but is underused.
next prev parent reply other threads:[~2007-09-30 11:52 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-09-30 10:44 [PATCH] cpuset and sched domains: sched_load_balance flag Paul Jackson
2007-09-29 19:21 ` Nick Piggin [this message]
2007-09-30 18:07 ` Paul Jackson
2007-09-30 3:34 ` Nick Piggin
2007-10-01 3:42 ` Paul Jackson
2007-10-02 13:05 ` Nick Piggin
2007-10-03 6:58 ` Paul Jackson
2007-10-02 16:09 ` Nick Piggin
2007-10-03 9:55 ` Paul Jackson
2007-10-02 17:56 ` Nick Piggin
2007-10-03 11:38 ` Paul Jackson
2007-10-02 19:25 ` Nick Piggin
2007-10-03 12:14 ` Paul Jackson
2007-10-02 19:53 ` Nick Piggin
2007-10-03 12:41 ` Paul Jackson
2007-10-02 20:30 ` Nick Piggin
2007-10-03 17:46 ` Paul Jackson
2007-10-03 12:17 ` Paul Jackson
2007-10-02 20:31 ` Nick Piggin
2007-10-03 17:44 ` Paul Jackson
2007-10-01 18:15 ` Paul Jackson
2007-10-02 13:35 ` Nick Piggin
2007-10-03 6:22 ` [patch] sched: fix sched-domains partitioning by cpusets Ingo Molnar
2007-10-03 6:56 ` Paul Jackson
2007-10-02 15:46 ` Nick Piggin
2007-10-03 9:21 ` Paul Jackson
2007-10-02 17:23 ` Nick Piggin
2007-10-03 10:08 ` Paul Jackson
2007-10-03 9:35 ` Ingo Molnar
2007-10-03 9:39 ` Paul Jackson
2007-10-02 17:29 ` Nick Piggin
2007-10-03 7:20 ` Ingo Molnar
2007-10-03 7:25 ` [PATCH] cpuset and sched domains: sched_load_balance flag Paul Jackson
2007-10-02 16:14 ` Nick Piggin
2007-09-30 10:44 ` [PATCH] cpuset decrustify update and validate masks Paul Jackson
2007-09-30 17:33 ` [PATCH] cpuset and sched domains: sched_load_balance flag Ingo Molnar
2007-10-02 20:22 ` Randy Dunlap
2007-10-02 20:57 ` Paul Jackson
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=200709300521.03356.nickpiggin@yahoo.com.au \
--to=nickpiggin@yahoo.com.au \
--cc=akpm@linux-foundation.org \
--cc=cpw@sgi.com \
--cc=dino@in.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=menage@google.com \
--cc=mingo@elte.hu \
--cc=pj@sgi.com \
/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