From: Andi Kleen <ak@suse.de>
To: discuss@x86-64.org
Cc: cpufreq@lists.linux.org.uk, linux-kernel@vger.kernel.org, "Gulam,
Nagib" <nagib.gulam@amd.com>
Subject: Re: [discuss] Re: [PATCH] Allow all Opteron processors to change pstate at same time
Date: Wed, 26 Jul 2006 20:53:40 +0200 [thread overview]
Message-ID: <200607262053.40123.ak@suse.de> (raw)
In-Reply-To: <84EA05E2CA77634C82730353CBE3A84303218F09@SAUSEXMB1.amd.com>
> In contrast, the same machine running with TSC and standard
> PN! sees massive drift, upwards of an hour, within an hour.
Do you see the same drift when you lock date on a single CPU
with taskset?
> If the TSCnow! patch reduces measured drift down to a second
> a week, would you consider that acceptable?
No because even one second a week will break timing badly
over time.
I believe the only good solution unless hardware helps would
be to use per CPU TSC offsets as discussed earlier. Even that
is a bit risky because there can be still very small drifts,
but they should be limited by a clock tick error max and
might work out.
-Andi
WARNING: multiple messages have this Message-ID (diff)
From: Andi Kleen <ak@suse.de>
To: discuss@x86-64.org
Cc: "Langsdorf, Mark" <mark.langsdorf@amd.com>,
"Gulam, Nagib" <nagib.gulam@amd.com>,
linux-kernel@vger.kernel.org, cpufreq@lists.linux.org.uk
Subject: Re: [discuss] Re: [PATCH] Allow all Opteron processors to change pstate at same time
Date: Wed, 26 Jul 2006 20:53:40 +0200 [thread overview]
Message-ID: <200607262053.40123.ak@suse.de> (raw)
In-Reply-To: <84EA05E2CA77634C82730353CBE3A84303218F09@SAUSEXMB1.amd.com>
> In contrast, the same machine running with TSC and standard
> PN! sees massive drift, upwards of an hour, within an hour.
Do you see the same drift when you lock date on a single CPU
with taskset?
> If the TSCnow! patch reduces measured drift down to a second
> a week, would you consider that acceptable?
No because even one second a week will break timing badly
over time.
I believe the only good solution unless hardware helps would
be to use per CPU TSC offsets as discussed earlier. Even that
is a bit risky because there can be still very small drifts,
but they should be limited by a clock tick error max and
might work out.
-Andi
next prev parent reply other threads:[~2006-07-26 18:53 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-07-06 20:31 [PATCH] Allow all Opteron processors to change pstate at same time Mark Langsdorf
2006-07-07 12:10 ` Andi Kleen
2006-07-07 17:36 ` [discuss] " Langsdorf, Mark
2006-07-10 12:45 ` Joachim Deguara
2006-07-10 13:02 ` Joachim Deguara
2006-07-07 18:14 ` Scott Lampert
2006-07-07 18:26 ` Langsdorf, Mark
2006-07-11 12:55 ` Joachim Deguara
2006-07-11 13:07 ` Andi Kleen
2006-07-11 13:14 ` Arjan van de Ven
2006-07-11 16:15 ` Alan Cox
2006-07-11 16:01 ` Arjan van de Ven
2006-07-11 16:01 ` Arjan van de Ven
2006-07-11 16:04 ` Andi Kleen
2006-07-11 13:31 ` Langsdorf, Mark
2006-07-11 13:34 ` Arjan van de Ven
2006-07-11 13:51 ` Andi Kleen
2006-07-11 13:14 ` [OT] Evolution use (was: Re: [discuss] Re: [PATCH] Allow all Opteron processors to change pstate at same time) Xavier Bestel
2006-07-12 14:06 ` [discuss] Re: [PATCH] Allow all Opteron processors to change pstate at same time Joachim Deguara
2006-07-12 14:54 ` Andi Kleen
2006-07-25 21:47 ` Langsdorf, Mark
2006-07-26 11:31 ` Joachim Deguara
2006-07-26 16:42 ` Langsdorf, Mark
2006-07-26 16:54 ` Andi Kleen
2006-07-26 16:54 ` Andi Kleen
2006-07-26 18:34 ` Langsdorf, Mark
2006-07-26 18:53 ` Andi Kleen [this message]
2006-07-26 18:53 ` Andi Kleen
-- strict thread matches above, loose matches on Subject: below --
2006-07-12 16:11 shin, jacob
2006-07-12 16:14 ` Langsdorf, Mark
2006-07-13 13:06 ` Pavel Machek
2006-07-13 14:32 ` Joachim Deguara
2006-07-16 1:56 ` Pavel Machek
2006-07-17 7:37 ` Joachim Deguara
2006-07-20 15:59 ` Pavel Machek
2006-07-13 13:37 Bhavana Nagendra
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=200607262053.40123.ak@suse.de \
--to=ak@suse.de \
--cc=cpufreq@lists.linux.org.uk \
--cc=discuss@x86-64.org \
--cc=linux-kernel@vger.kernel.org \
--cc=nagib.gulam@amd.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.