From: Andi Kleen <ak@muc.de>
To: Andrew Morton <akpm@osdl.org>
Cc: Andi Kleen <ak@muc.de>, linux-kernel@vger.kernel.org
Subject: Re: 2.6.4-mm1
Date: 11 Mar 2004 21:21:36 +0100
Date: Thu, 11 Mar 2004 21:21:36 +0100 [thread overview]
Message-ID: <20040311202136.GA59610@colin2.muc.de> (raw)
In-Reply-To: <20040311112852.4f56cf34.akpm@osdl.org>
> > For SMT there is a patch from Intel pending that teaches x86-64
> > to set up the SMT scheduler. They said they got slightly better
> > benchmark results. The SMT setup seems to be racy though.
>
> Am I correct in thinking that this patch provides the necessary hooks to
> integrate x86_4 into the new functionality which sched-domains provides, or
> is the Intel patch independent of sched-domains?
It sets up the sched-domains code to know about HyperThreading CPUs
on x86-64 too (basically same thing as the i386 code does with a
few minor tweaks)
So it's dependent on that.
I will send it to you in separate mail.
> > Some kind of SMT scheduler is definitely needed, we have a serious
> > regression compared to 2.4 here right now. I'm not sure this
> > is the right approach though, it seems to be far too complex.
>
> Well that's discouraging. I really do want to push this thing along a bit.
>
> Yours is the only report of regression of which I am aware. Is the reason
> understood?
I think the reason is that it doesn't do balance on clone/fork. The
normal scheduler also doesn't do that, but for some reason it still does
better on the benchmarks (but worse than the old 2.4 -aa/Intel O(1) HT
scheduler)
> And is anyone developing alternative SMT enhancements?
I thought there was a patch from Ingo Molnar? ("shared runqueue")
I must admit I never tried it, just remember seeing the patches.
Also I've been playing with the entitlement scheduler to fix
some of the interactivity problems I have on UP, but it also
seems to still have problems.
-Andi
next prev parent reply other threads:[~2004-03-11 20:21 UTC|newest]
Thread overview: 75+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <1ysXv-wm-11@gated-at.bofh.it>
[not found] ` <1yuG3-2XI-15@gated-at.bofh.it>
2004-03-17 23:21 ` 2.6.4-mm1 Andi Kleen
2004-03-11 19:28 ` 2.6.4-mm1 Andrew Morton
2004-03-11 20:21 ` Andi Kleen [this message]
2004-03-11 20:48 ` 2.6.4-mm1 Andrew Morton
2004-03-11 23:37 ` 2.6.4-mm1 Nick Piggin
[not found] ` <1yxuq-6y6-13@gated-at.bofh.it>
2004-03-17 23:25 ` 2.6.4-mm1 Andi Kleen
2004-03-11 13:45 ` 2.6.4-mm1 Mickael Marchand
2004-03-11 14:48 ` 2.6.4-mm1 Andi Kleen
2004-03-11 15:10 ` 2.6.4-mm1 Mickael Marchand
2004-03-11 15:20 ` 2.6.4-mm1 Andi Kleen
2004-03-11 21:43 ` 2.6.4-mm1 Joe Thornber
2004-03-11 21:57 ` 2.6.4-mm1 Joe Thornber
2004-03-11 21:59 ` 2.6.4-mm1 Joel Becker
2004-03-11 22:02 ` 2.6.4-mm1 Joel Becker
2004-03-11 22:11 ` 2.6.4-mm1 Chris Friesen
2004-03-11 23:37 ` 2.6.4-mm1 Andi Kleen
2004-03-12 8:22 ` 2.6.4-mm1 Joe Thornber
2004-03-12 9:49 ` 2.6.4-mm1 Joe Thornber
2004-03-12 12:11 ` 2.6.4-mm1 Mickael Marchand
2004-03-12 12:35 ` 2.6.4-mm1 Joe Thornber
2004-03-12 22:48 ` 2.6.4-mm1 Hugo Mills
2004-03-11 21:38 ` 2.6.4-mm1 Joe Thornber
2004-03-11 23:33 ` 2.6.4-mm1 Andi Kleen
[not found] <1yygN-7Ut-65@gated-at.bofh.it>
[not found] ` <1yyqt-83X-23@gated-at.bofh.it>
[not found] ` <1yyqs-83X-17@gated-at.bofh.it>
[not found] ` <1yyJK-8mD-41@gated-at.bofh.it>
[not found] ` <1yzPs-1bI-21@gated-at.bofh.it>
[not found] ` <1yGe9-7Rk-23@gated-at.bofh.it>
[not found] ` <1yI6f-1Bj-3@gated-at.bofh.it>
[not found] ` <1yQdz-1Uf-7@gated-at.bofh.it>
[not found] ` <1yRCI-3lE-19@gated-at.bofh.it>
2004-03-19 5:58 ` 2.6.4-mm1 Andi Kleen
2004-03-12 13:49 ` 2.6.4-mm1 Joe Thornber
2004-03-12 14:03 ` 2.6.4-mm1 Andi Kleen
[not found] ` <1yTO6-5JU-25@gated-at.bofh.it>
[not found] ` <1yU7Z-624-11@gated-at.bofh.it>
2004-03-19 6:00 ` 2.6.4-mm1 Andi Kleen
2004-03-14 16:13 2.6.4-mm1 Nakajima, Jun
2004-03-14 17:04 ` 2.6.4-mm1 Grzegorz Kulewski
-- strict thread matches above, loose matches on Subject: below --
2004-03-14 8:04 2.6.4-mm1 Nakajima, Jun
2004-03-14 8:31 ` 2.6.4-mm1 Andrew Morton
2004-03-12 23:04 2.6.4-mm1 Subodh Shrivastava
2004-03-12 23:55 ` 2.6.4-mm1 Andrew Morton
2004-03-13 13:12 ` 2.6.4-mm1 SUBODH SHRIVASTAVA
[not found] <A6974D8E5F98D511BB910002A50A6647615F4D9F@hdsmsx402.hd.intel.com>
2004-03-12 15:48 ` 2.6.4-mm1 Len Brown
2004-03-12 3:04 2.6.4-mm1 Nakajima, Jun
2004-03-12 3:14 ` 2.6.4-mm1 Andi Kleen
2004-03-12 4:24 ` 2.6.4-mm1 Nick Piggin
2004-03-12 14:14 ` 2.6.4-mm1 Andi Kleen
2004-03-12 14:38 ` 2.6.4-mm1 Nick Piggin
2004-03-11 18:46 2.6.4-mm1 Nakajima, Jun
2004-03-11 7:31 2.6.4-mm1 Andrew Morton
2004-03-11 8:26 ` 2.6.4-mm1 Jens Axboe
2004-03-11 8:30 ` 2.6.4-mm1 Andrew Morton
2004-03-11 9:34 ` 2.6.4-mm1 Matthias Urlichs
2004-03-11 9:17 ` 2.6.4-mm1 Mickael Marchand
2004-03-11 11:06 ` 2.6.4-mm1 Andrew Morton
2004-03-11 11:22 ` 2.6.4-mm1 Anton Blanchard
2004-03-11 12:23 ` 2.6.4-mm1 Mickael Marchand
2004-03-11 13:40 ` 2.6.4-mm1 jlnance
2004-03-11 19:25 ` 2.6.4-mm1 Mike Fedyk
2004-03-11 22:22 ` 2.6.4-mm1 Andrew Morton
2004-03-11 13:49 ` 2.6.4-mm1 Anton Blanchard
2004-03-11 23:29 ` 2.6.4-mm1 Nick Piggin
2004-03-12 2:03 ` 2.6.4-mm1 Nick Piggin
2004-03-12 2:12 ` 2.6.4-mm1 Anton Blanchard
2004-03-12 5:11 ` 2.6.4-mm1 Anton Blanchard
2004-03-11 13:52 ` 2.6.4-mm1 Anton Blanchard
2004-03-11 15:23 ` 2.6.4-mm1 William Lee Irwin III
2004-03-11 15:54 ` 2.6.4-mm1 William Lee Irwin III
2004-03-11 17:06 ` 2.6.4-mm1 Redeeman
2004-03-11 17:53 ` 2.6.4-mm1 Norberto Bensa
2004-03-11 18:09 ` 2.6.4-mm1 Andrew Morton
2004-03-11 18:14 ` 2.6.4-mm1 Redeeman
2004-03-11 18:46 ` 2.6.4-mm1 Andrew Morton
2004-03-11 20:58 ` 2.6.4-mm1 Redeeman
2004-03-11 21:10 ` 2.6.4-mm1 Redeeman
2004-03-11 18:22 ` 2.6.4-mm1 Norberto Bensa
2004-03-11 20:29 ` 2.6.4-mm1 Felipe Alfaro Solana
2004-03-12 1:03 ` 2.6.4-mm1 Neil Brown
2004-03-12 1:22 ` 2.6.4-mm1 Andrew Morton
2004-03-12 5:48 ` 2.6.4-mm1 Neil Brown
2004-03-12 7:50 ` 2.6.4-mm1 Andrew Morton
2004-03-13 10:25 ` 2.6.4-mm1 Neil Brown
2004-03-12 9:04 ` 2.6.4-mm1 Helge Hafting
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=20040311202136.GA59610@colin2.muc.de \
--to=ak@muc.de \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.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 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).