From: Andrea Arcangeli <andrea@suse.de>
To: "Martin J. Bligh" <Martin.Bligh@us.ibm.com>
Cc: Pavel Machek <pavel@elf.ucw.cz>,
Alan Cox <alan@lxorguk.ukuu.org.uk>,
Mikael Pettersson <mikpe@csd.uu.se>,
john stultz <johnstul@us.ibm.com>,
Marcelo Tosatti <marcelo@conectiva.com.br>,
lkml <linux-kernel@vger.kernel.org>,
Leah Cunningham <leahc@us.ibm.com>,
wilhelm.nuesser@sap.com, paramjit@us.ibm.com, msw@redhat.com
Subject: Re: [PATCH] tsc-disable_B9
Date: Tue, 27 Aug 2002 00:49:47 +0200 [thread overview]
Message-ID: <20020826224946.GW9899@dualathlon.random> (raw)
In-Reply-To: <159220000.1030387536@flay>
On Mon, Aug 26, 2002 at 11:45:36AM -0700, Martin J. Bligh wrote:
> >> And following your argument that these apps have been silenty broken
> >> since 1999, if there's no broken app out there, nobody will ever get the
> >> instruction fault. If there's any app broken out there we probably like
> >
> > No. rdtsc is still usefull if you are clever and statistically filter
> > out. Also rdtsc provides you number of cycles, so if you want to know
> > how many cycles mov %eax,%ebx takes, you can do that even on
> > speedstep. Anything that correlates rdtsc to real time is broken, however.
>
> It's not correlating it to real time that's the problem. It's getting resceduled
> inbetween calls that hurts. Take your example.
>
> rdtsc
> mov %eax,%ebx
> <- get rescheduled here
> rdtsc
>
> Broken. May even take negative "time".
you need to save %edx too, then it would be perfectly safe on a
synchronized TSC hardware (as far as the reschedule doesn't take more
than 2^64 ticks).
Andrea
prev parent reply other threads:[~2002-08-26 22:44 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-08-08 1:53 [PATCH] tsc-disable_B9 john stultz
2002-08-08 2:15 ` [PATCH] cyclone-timer_A9 john stultz
2002-08-08 13:18 ` Alan Cox
2002-08-09 2:03 ` john stultz
2002-08-08 13:17 ` [PATCH] tsc-disable_B9 Alan Cox
2002-08-09 2:30 ` john stultz
2002-08-09 9:17 ` Alan Cox
2002-08-09 17:46 ` john stultz
2002-08-09 18:49 ` george anzinger
2002-08-09 20:58 ` john stultz
2002-08-13 1:23 ` James Cleverdon
2002-08-11 20:16 ` Alan Cox
2002-08-15 16:56 ` Andrea Arcangeli
2002-08-16 11:15 ` Alan Cox
2002-08-16 13:19 ` Mikael Pettersson
2002-08-21 13:12 ` Andrea Arcangeli
2002-08-21 14:10 ` Alan Cox
2002-08-21 14:33 ` Andrea Arcangeli
2002-08-21 15:01 ` Alan Cox
2002-08-21 16:13 ` Andrea Arcangeli
2002-08-21 16:25 ` Alan Cox
2002-08-21 17:17 ` Andrea Arcangeli
2002-08-21 17:34 ` Alan Cox
2002-08-26 16:10 ` Pavel Machek
2002-08-26 18:45 ` Martin J. Bligh
2002-08-26 19:00 ` Pavel Machek
2002-08-26 19:05 ` Alan Cox
2002-08-26 20:19 ` Martin J. Bligh
2002-08-26 19:18 ` Richard B. Johnson
2002-08-26 19:42 ` Pavel Machek
2002-08-26 20:23 ` Alan Cox
2002-08-26 22:49 ` Andrea Arcangeli [this message]
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=20020826224946.GW9899@dualathlon.random \
--to=andrea@suse.de \
--cc=Martin.Bligh@us.ibm.com \
--cc=alan@lxorguk.ukuu.org.uk \
--cc=johnstul@us.ibm.com \
--cc=leahc@us.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=marcelo@conectiva.com.br \
--cc=mikpe@csd.uu.se \
--cc=msw@redhat.com \
--cc=paramjit@us.ibm.com \
--cc=pavel@elf.ucw.cz \
--cc=wilhelm.nuesser@sap.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox