All of lore.kernel.org
 help / color / mirror / Atom feed
From: Matthew Dobson <colpatch@us.ibm.com>
To: george anzinger <george@mvista.com>
Cc: Mike Kravetz <kravetz@us.ibm.com>,
	Davide Libenzi <davidel@xmailserver.org>,
	lse-tech@lists.sourceforge.net,
	lkml <linux-kernel@vger.kernel.org>
Subject: Re: [Lse-tech] Re: Real Time Runqueue
Date: Mon, 19 Nov 2001 12:23:42 -0800	[thread overview]
Message-ID: <3BF96A4E.FE21CC31@us.ibm.com> (raw)
In-Reply-To: <20011116154701.G1152@w-mikek2.des.beaverton.ibm.com> <Pine.LNX.4.40.0111161620050.998-100000@blue1.dev.mcafeelabs.com> <20011116163224.H1152@w-mikek2.des.beaverton.ibm.com> <3BF61AEB.2C186512@mvista.com>

george anzinger wrote:
> A couple of addition points.  There should be an API to declare cpu
> affinity, and cpu affinity should be passed thru fork and exec.  You may
> need to be god (root) to use the API however.  (I think cpu affinity is
> currently passed thru fork and exec, by the way.)

There is...  there is a launch_policy patch on
http://sourceforge.net/projects/lse, that offers 2 ways of setting a processes
CPU affinity.  A process can muck around with its own affinity through prctl(),
and root can muck around with the CPU affinity of any process through
/proc/<pid>/cpus_allowed and /proc/<pid>/launch_policy.  And the launch_policy
*is* inherited from parent to child.

The cpus_allowed part comes from Andrew Morton and controls the processes
affinity.  I've extended that to include the launch_policy part which sets the
affinity to be passed on through fork/exec.

Enjoy!

-matt

  reply	other threads:[~2001-11-19 20:28 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2001-11-16 20:20 Real Time Runqueue Mike Kravetz
2001-11-16 20:26 ` Richard Gooch
2001-11-16 22:44 ` Davide Libenzi
2001-11-16 23:47   ` Mike Kravetz
2001-11-17  0:28     ` Davide Libenzi
2001-11-17  0:32       ` Mike Kravetz
2001-11-17  8:08         ` [Lse-tech] " george anzinger
2001-11-19 20:23           ` Matthew Dobson [this message]
2001-11-19 15:15         ` Victor Yodaiken
2001-11-19 16:30         ` [Lse-tech] " Andi Kleen
2001-11-19 17:06           ` Davide Libenzi
2001-11-19 18:23           ` Richard Gooch
2001-11-19 19:07             ` Mike Kravetz
2001-11-19 18:32           ` george anzinger
2001-11-19 18:40             ` Andi Kleen
  -- strict thread matches above, loose matches on Subject: below --
2001-11-16 22:41 Jesse Pollard
2001-11-17  8:41 ` [Lse-tech] " george anzinger

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=3BF96A4E.FE21CC31@us.ibm.com \
    --to=colpatch@us.ibm.com \
    --cc=davidel@xmailserver.org \
    --cc=george@mvista.com \
    --cc=kravetz@us.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lse-tech@lists.sourceforge.net \
    /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.