From: Lee Revell <rlrevell@joe-job.com>
To: John Reiser <jreiser@BitWagon.com>
Cc: Andi Kleen <ak@suse.de>, Stephane Eranian <eranian@hpl.hp.com>,
Ray Bryant <raybry@mpdtxmail.amd.com>,
discuss@x86-64.org, linux-kernel@vger.kernel.org,
perfctr-devel@lists.sourceforge.net
Subject: Re: [Perfctr-devel] Re: Enabling RDPMC in user space by default
Date: Tue, 29 Nov 2005 14:05:43 -0500 [thread overview]
Message-ID: <1133291144.4627.1.camel@mindpipe> (raw)
In-Reply-To: <438C9E1B.8040204@BitWagon.com>
On Tue, 2005-11-29 at 10:29 -0800, John Reiser wrote:
> Andi Kleen wrote:
> > I think it's also a useful convention - RDTSC is becomming more and more
> > useless and you cannot expect user applications who just want to
> > measure some cycles to rely on ever changing instable or non existing
> > performance counter APIs.
>
> Users are even more unhappy with ever-changing ABIs -- such as the
> kernel taking away RDTSC.
>
> RDTSC+perfctr [Pettersson] still is the fastest way for user-mode code
> to count something that is highly correlated with both "billable"
> CPU time and "code quality" for a fixed task. With a little care
> RDTSC is close enough to monotonic that I find it very useful.
> Please don't take away user-mode RDTSC.
>
The kernel didn't take this away, the hardware vendors did. For years
although it was risky on paper it was perfectly usable as a cheap high
res timer. I agree that it's unfortunate.
Lee
next prev parent reply other threads:[~2005-11-29 19:05 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2005-11-29 15:15 Enabling RDPMC in user space by default Andi Kleen
2005-11-29 16:04 ` Mikael Pettersson
2005-11-29 16:17 ` Andi Kleen
2005-11-29 16:56 ` Ray Bryant
2005-11-29 16:15 ` Andi Kleen
2005-11-29 18:09 ` [Perfctr-devel] " Stephane Eranian
2005-11-29 18:13 ` Andi Kleen
2005-11-29 18:29 ` John Reiser
2005-11-29 18:38 ` Andi Kleen
2005-11-29 19:05 ` Lee Revell [this message]
2005-11-29 21:43 ` Nicholas Miell
2005-11-29 21:52 ` Andi Kleen
2005-11-29 22:19 ` Stephane Eranian
2005-11-29 22:51 ` [discuss] " Andi Kleen
2005-11-30 16:01 ` Stephane Eranian
2005-11-30 16:23 ` Andi Kleen
2005-12-01 23:41 ` Stephane Eranian
2005-12-02 0:07 ` Andi Kleen
2005-12-02 7:09 ` Stephane Eranian
2005-12-02 11:36 ` Andi Kleen
2005-11-29 22:33 ` Nicholas Miell
2005-11-29 22:43 ` Andi Kleen
2005-11-29 23:02 ` Nicholas Miell
2005-11-29 23:17 ` Andi Kleen
2005-11-29 23:29 ` Nicholas Miell
2005-11-29 23:39 ` Andi Kleen
2005-11-29 23:56 ` David Gibson
2005-11-30 0:34 ` Andi Kleen
2005-11-30 0:52 ` David Gibson
2005-11-30 1:04 ` [discuss] " Andi Kleen
2005-11-30 0:50 ` Ray Bryant
2005-11-30 0:38 ` Andi Kleen
2005-11-30 7:38 ` Stephane Eranian
2005-11-30 8:22 ` Nicholas Miell
2005-11-30 15:48 ` Stephane Eranian
2005-11-29 23:07 ` David Gibson
2005-11-29 23:18 ` [discuss] " Andi Kleen
2005-11-29 23:28 ` Bernd Schmidt
2005-11-29 23:46 ` [discuss] " Andi Kleen
2005-11-30 2:39 ` Zwane Mwaikambo
2005-11-30 3:38 ` Andi Kleen
2005-12-01 4:08 ` Zwane Mwaikambo
2005-12-01 13:05 ` Andi Kleen
2005-12-01 17:01 ` Zwane Mwaikambo
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=1133291144.4627.1.camel@mindpipe \
--to=rlrevell@joe-job.com \
--cc=ak@suse.de \
--cc=discuss@x86-64.org \
--cc=eranian@hpl.hp.com \
--cc=jreiser@BitWagon.com \
--cc=linux-kernel@vger.kernel.org \
--cc=perfctr-devel@lists.sourceforge.net \
--cc=raybry@mpdtxmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox