From: thockin@hockin.org
To: Willy Tarreau <w@1wt.eu>
Cc: Andi Kleen <ak@suse.de>, Lee Revell <rlrevell@joe-job.com>,
Luca Tettamanti <kronos.it@gmail.com>,
linux-kernel@vger.kernel.org, john stultz <johnstul@us.ibm.com>
Subject: Re: AMD X2 unsynced TSC fix?
Date: Sat, 28 Oct 2006 12:18:00 -0700 [thread overview]
Message-ID: <20061028191800.GA20701@hockin.org> (raw)
In-Reply-To: <20061028191515.GA1603@1wt.eu>
On Sat, Oct 28, 2006 at 09:15:15PM +0200, Willy Tarreau wrote:
> > While gtod is time critical and often appears high on profile lists it is
> > normally not as time critical as you're claiming it is; especially not
> > time critical enough to warrant such radical action.
>
> Yes it was, because the small gain of using a dual core with such
> a workload was clearly lost by that change. IIRC, I reached 25000
> sessions/s on dual core with TSC if I didn't care about the clock,
> 20000 without TSC, and 18000 on single core+TSC. But with the sniffer,
> it was even worse : I had 500 kpps in dual-core+TSC, 70kpps without
> TSC and 300 kpps with single-core+TSC. Since I had to buy the same
> machines for both uses, this last argument was enough for me to stick
> to a single core.
Was the problem that they were not synced at poweron or that they would
drift due to power-states?
Did you try running with idle=poll, to avoid ever entering C1 state (hlt)?
next prev parent reply other threads:[~2006-10-28 19:18 UTC|newest]
Thread overview: 65+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-10-27 17:15 AMD X2 unsynced TSC fix? Lee Revell
2006-10-27 20:18 ` Luca Tettamanti
2006-10-27 23:04 ` thockin
2006-10-28 0:00 ` Luca Tettamanti
2006-10-28 0:17 ` Lee Revell
2006-10-28 2:46 ` thockin
2006-10-28 3:59 ` Andi Kleen
2006-10-28 6:32 ` thockin
2006-10-28 9:14 ` Vojtech Pavlik
2006-10-28 18:22 ` Lee Revell
2006-10-28 19:57 ` Vojtech Pavlik
2006-10-28 22:54 ` thockin
2006-10-28 1:04 ` Andi Kleen
2006-10-28 3:28 ` Lee Revell
2006-10-28 5:28 ` Willy Tarreau
2006-10-28 18:08 ` Lee Revell
2006-10-28 19:14 ` thockin
2006-10-30 17:22 ` Langsdorf, Mark
2006-10-28 18:37 ` Andi Kleen
2006-10-28 19:15 ` Willy Tarreau
2006-10-28 19:18 ` thockin [this message]
2006-10-28 19:32 ` Willy Tarreau
2006-10-28 19:42 ` thockin
2006-10-28 20:16 ` Willy Tarreau
2006-10-28 19:33 ` Andi Kleen
2006-10-28 20:04 ` Willy Tarreau
2006-10-28 20:11 ` Andi Kleen
2006-10-28 20:36 ` Willy Tarreau
2006-10-29 1:28 ` Lee Revell
2006-10-28 21:00 ` Lee Revell
2006-10-31 11:12 ` Pádraig Brady
2006-10-31 15:31 ` Willy Tarreau
2006-10-30 20:30 ` Christoph Lameter
2006-10-27 20:35 ` Andi Kleen
2006-10-27 20:41 ` Lee Revell
2006-10-27 21:48 ` Chris Friesen
2006-10-27 22:08 ` Lee Revell
2006-10-28 3:58 ` Sergio Monteiro Basto
2006-10-28 4:06 ` Andi Kleen
2006-10-28 4:22 ` Sergio Monteiro Basto
2006-10-30 3:10 ` Sergio Monteiro Basto
2006-10-30 15:23 ` Andi Kleen
[not found] ` <1162253008.2999.9.camel@localhost.portugal>
2006-10-31 0:14 ` Lee Revell
2006-10-31 0:25 ` john stultz
2006-10-31 2:41 ` Siddha, Suresh B
2006-10-31 15:05 ` Sergio Monteiro Basto
2006-11-01 1:46 ` Sergio Monteiro Basto
2006-11-01 2:44 ` Siddha, Suresh B
2006-11-08 0:22 ` Sergio Monteiro Basto
2006-11-08 19:53 ` Thomas Gleixner
2006-11-09 0:39 ` Sergio Monteiro Basto
2006-11-09 1:13 ` john stultz
2006-11-09 1:27 ` Sergio Monteiro Basto
2006-11-15 1:51 ` Sergio Monteiro Basto
[not found] ` <20061115193514.41C01102C011@mail.goron.de>
2006-11-16 1:38 ` Sergio Monteiro Basto
2006-11-16 1:45 ` Sergio Monteiro Basto
2006-10-28 6:35 ` thockin
2006-10-28 6:46 ` Andrew Morton
2006-10-28 6:49 ` thockin
2006-10-28 7:13 ` Andrew Morton
2006-10-28 7:25 ` thockin
2006-10-28 9:46 ` Andi Kleen
2006-10-28 9:45 ` Andi Kleen
2006-10-28 9:48 ` Andi Kleen
2006-10-27 21:58 ` Friedrich Göpel
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=20061028191800.GA20701@hockin.org \
--to=thockin@hockin.org \
--cc=ak@suse.de \
--cc=johnstul@us.ibm.com \
--cc=kronos.it@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rlrevell@joe-job.com \
--cc=w@1wt.eu \
/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.