From: Andi Kleen <andi@firstfloor.org>
To: William Lee Irwin III <wli@holomorphy.com>
Cc: Ingo Molnar <mingo@elte.hu>, Andi Kleen <andi@firstfloor.org>,
Satyam Sharma <satyam.sharma@gmail.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org,
Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: Re: [patch] i386, numaq: enable TSCs again
Date: Fri, 25 May 2007 10:22:59 +0200 [thread overview]
Message-ID: <20070525082259.GH8094@one.firstfloor.org> (raw)
In-Reply-To: <20070525081944.GZ31925@holomorphy.com>
On Fri, May 25, 2007 at 01:19:44AM -0700, William Lee Irwin III wrote:
> On Fri, May 25, 2007 at 10:08:27AM +0200, Ingo Molnar wrote:
> > Andi, Andrew, do you remember why we disabled TSCs on NUMAQ? It was
> > slightly async between CPUs, right? In that case we should try the patch
> > below.
>
> I remember. It was far beyond "slightly async;" they would drift
> minutes apart during reasonable amounts of uptime, though it would take
> at least several days to drift so far (I don't recall how long it took).
sched_clock should handle that.
> TSC synchronization is uniformly impossible on NUMA-Q. Bootlogs showing
> the results of the attempts are still extant. They shouldn't end up too
> far apart right after booting, but I don't have even ballpark estimates.
> I'd hazard a guess of a few seconds.
You should mark_tsc_instable(), but not tsc disable. In a release or two
hopefully even that will be obsolete.
-Andi
next prev parent reply other threads:[~2007-05-25 8:23 UTC|newest]
Thread overview: 59+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-05-25 7:10 [patch] sched_clock(): cleanups Ingo Molnar
2007-05-25 7:22 ` Satyam Sharma
2007-05-25 7:25 ` Ingo Molnar
2007-05-25 7:26 ` Ingo Molnar
2007-05-25 7:35 ` Satyam Sharma
2007-05-25 7:39 ` Peter Zijlstra
2007-05-25 7:58 ` Andi Kleen
2007-05-25 8:02 ` Ingo Molnar
2007-05-25 8:16 ` Peter Zijlstra
2007-05-25 8:21 ` Andi Kleen
2007-05-25 7:38 ` Andi Kleen
2007-05-25 7:31 ` Andi Kleen
2007-05-25 7:39 ` Ingo Molnar
2007-05-25 7:43 ` Ingo Molnar
2007-05-25 7:49 ` Ingo Molnar
2007-05-25 7:54 ` [patch] x86_64: fix sched_clock() Ingo Molnar
2007-05-25 8:02 ` Andi Kleen
2007-05-25 8:04 ` Ingo Molnar
2007-05-25 8:20 ` Andi Kleen
2007-05-25 8:34 ` Ingo Molnar
2007-05-25 8:41 ` Andi Kleen
2007-05-25 8:44 ` Ingo Molnar
2007-05-25 8:45 ` Andi Kleen
2007-05-25 8:55 ` Ingo Molnar
2007-05-25 8:55 ` Andrew Morton
2007-05-25 9:03 ` Andi Kleen
2007-05-25 9:19 ` Ingo Molnar
2007-05-25 9:46 ` Andi Kleen
2007-05-25 10:12 ` Ingo Molnar
2007-05-25 11:20 ` Andi Kleen
2007-05-25 11:26 ` Ingo Molnar
2007-05-25 11:31 ` Ingo Molnar
2007-05-25 11:46 ` [patch] sched_clock: fix preempt count imbalance Ingo Molnar
2007-05-25 11:50 ` [patch] sched_clock(): cleanups, #2 Ingo Molnar
2007-05-25 11:55 ` Andi Kleen
2007-05-25 12:02 ` Ingo Molnar
2007-05-25 12:15 ` Andi Kleen
2007-05-25 16:17 ` Andrew Morton
2007-05-25 16:26 ` Daniel Walker
2007-05-25 16:33 ` Andi Kleen
2007-05-25 16:49 ` Linus Torvalds
2007-05-25 18:08 ` Andi Kleen
2007-05-25 19:14 ` Ingo Molnar
2007-05-25 19:45 ` Linus Torvalds
2007-05-25 10:27 ` [patch] x86_64: fix sched_clock() Ingo Molnar
2007-05-25 11:05 ` Andi Kleen
2007-05-28 3:12 ` Rusty Russell
2007-05-25 8:08 ` [patch] i386, numaq: enable TSCs again Ingo Molnar
2007-05-25 8:19 ` William Lee Irwin III
2007-05-25 8:22 ` Andi Kleen [this message]
2007-05-25 8:25 ` William Lee Irwin III
2007-05-25 8:31 ` Ingo Molnar
2007-05-25 8:38 ` William Lee Irwin III
2007-05-25 8:41 ` Ingo Molnar
2007-05-25 18:16 ` Dave Hansen
2007-05-25 18:23 ` john stultz
2007-05-25 8:15 ` [patch] x86_64: fix sched_clock() Peter Zijlstra
2007-05-25 8:16 ` Ingo Molnar
2007-05-25 8:22 ` [patch] sched_clock(): cleanups Peter Zijlstra
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=20070525082259.GH8094@one.firstfloor.org \
--to=andi@firstfloor.org \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=satyam.sharma@gmail.com \
--cc=wli@holomorphy.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 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.