From: Erich Focht <efocht@hpce.nec.com>
To: Andi Kleen <ak@suse.de>
Cc: LSE <lse-tech@lists.sourceforge.net>,
linux-kernel <linux-kernel@vger.kernel.org>
Subject: Re: [Lse-tech] Node affine NUMA scheduler extension
Date: Tue, 27 May 2003 13:39:29 +0200 [thread overview]
Message-ID: <200305271339.29151.efocht@hpce.nec.com> (raw)
In-Reply-To: <20030527100148.GE31510@wotan.suse.de>
On Tuesday 27 May 2003 12:01, Andi Kleen wrote:
> > > allocate memory on the wrong node. I found a lot of code runs very
> > > badly until the cache decay parameter is set to 0 (no special cache
> > > affinity) to allow quick initial migration.
> >
> > Interesting observation, I didn't make it when I tried the lazy
> > homenode (quite a while ago). But I was focusing on MPI jobs. So what
> > if we add a condition to CAN_MIGRATE which disables the cache affinity
> > before the first load balance?
>
> What I currently have is two cache decay variables: one is used if the
> homenode is not assigned, the other otherwise. Both are sysctls too.
> But it obviously only works with lazy homenode, but the state is the same.
> I'm still not completely happy with it though.
>
> Why exactly did you gave up to use the lazy homenode?
I left the loadbalancer to decide on where the homenode should be. And
the decision wasn't good enough (it lead to unbalanced nodes, that's
certainly not the case on Opteron :-). So it made sense to have a
specialized homenode chooser which considered the node loads instead
of changing the normal load balancer.
BTW: do you assign the homenode at first load balancing or at first
cross-node balancing?
> > similar to sched_balance_exec(). Tasks have a default initial load
> > balancing policy of being migrated (and selecting the homenode) at
> > exec(). This can be changed (with prctl) to fork(). The ilb policy is
> > inheritable. Works fine for OpenMP jobs.
>
> Hmm, I should try that I guess. Where do you call it? At the end of
> do_fork? I tried to hack up wake_up_forked_process() to do it, but it
> required large scale changes all over the scheduler so I eventually gave
> up.
For the processes with ilb_policy=FORK I chose the homenode and set
the cpu before the task is woken up. It is done in do_fork right after
the task structure has been cloned. wake_up_forked_process was changed
to lock the rq of the child (and not the one of current) and not set
the cpu any more. I don't think there was more...
Regards,
Erich
next prev parent reply other threads:[~2003-05-27 11:23 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
2003-05-27 8:31 Node affine NUMA scheduler extension Erich Focht
2003-05-27 9:11 ` [Lse-tech] " Andi Kleen
2003-05-27 9:54 ` Erich Focht
2003-05-27 10:01 ` Andi Kleen
2003-05-27 11:39 ` Erich Focht [this message]
2003-05-27 11:40 ` Andi Kleen
2003-05-27 11:50 ` Erich Focht
2003-05-27 15:38 ` Martin J. Bligh
2003-05-27 21:28 ` Erich Focht
2003-05-27 21:51 ` Martin J. Bligh
2003-05-28 17:02 ` Erich Focht
2003-05-28 17:13 ` Martin J. Bligh
2003-05-28 18:14 ` Rick Lindsley
2003-05-28 19:32 ` Martin J. Bligh
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=200305271339.29151.efocht@hpce.nec.com \
--to=efocht@hpce.nec.com \
--cc=ak@suse.de \
--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 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).