From: David Miller <davem@davemloft.net>
To: arjan@infradead.org
Cc: mingo@elte.hu, paulus@samba.org, tglx@linutronix.de,
linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org,
akpm@linux-foundation.org, eranian@googlemail.com,
dada1@cosmosbay.com, robert.richter@amd.com, hpa@zytor.com,
a.p.zijlstra@chello.nl, rostedt@goodmis.org
Subject: Re: [patch 0/3] [Announcement] Performance Counters for Linux
Date: Thu, 04 Dec 2008 23:52:38 -0800 (PST) [thread overview]
Message-ID: <20081204.235238.229578299.davem@davemloft.net> (raw)
In-Reply-To: <20081204230206.6e083d51@infradead.org>
From: Arjan van de Ven <arjan@infradead.org>
Date: Thu, 4 Dec 2008 23:02:06 -0800
> On Fri, 5 Dec 2008 07:31:31 +0100
> Ingo Molnar <mingo@elte.hu> wrote:
>
> > Btw., i'm curious, why would we want to do that? It skews the results
> > if the task continues executing and counters stop. To get the highest
> > quality profiling output the counters should follow the true state of
> > the task that is profiled - and events should be passed to the
> > monitoring task asynchronously. The _events_ can contain precise
> > coupled information
> > - but the counters should continue.
>
> btw stopping the task on counter overflow is an issue for things that
> want to self profile, like JITs
They can fork off a thread to do this.
No blocking on couter overflow leads to inaccurate results.
This is a pretty fundamental aspect of perf counter usage.
next prev parent reply other threads:[~2008-12-05 7:52 UTC|newest]
Thread overview: 74+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-12-04 23:44 [patch 0/3] [Announcement] Performance Counters for Linux Thomas Gleixner
2008-12-04 23:44 ` [patch 1/3] performance counters: core code Thomas Gleixner
2008-12-05 10:55 ` Paul Mackerras
2008-12-05 11:20 ` Ingo Molnar
2008-12-04 23:44 ` [patch 2/3] performance counters: documentation Thomas Gleixner
2008-12-05 0:33 ` Paul Mackerras
2008-12-05 0:37 ` David Miller
2008-12-05 2:50 ` Arjan van de Ven
2008-12-05 3:26 ` David Miller
2008-12-05 2:33 ` Andi Kleen
2008-12-04 23:45 ` [patch 3/3] performance counters: x86 support Thomas Gleixner
2008-12-05 0:22 ` [patch 0/3] [Announcement] Performance Counters for Linux Paul Mackerras
2008-12-05 6:31 ` Ingo Molnar
2008-12-05 7:02 ` Arjan van de Ven
2008-12-05 7:52 ` David Miller [this message]
2008-12-05 7:03 ` Ingo Molnar
2008-12-05 7:03 ` Ingo Molnar
2008-12-05 7:16 ` Peter Zijlstra
2008-12-05 7:57 ` Paul Mackerras
2008-12-05 8:03 ` Peter Zijlstra
2008-12-05 8:07 ` David Miller
2008-12-05 8:11 ` Ingo Molnar
2008-12-05 8:17 ` David Miller
2008-12-05 8:24 ` Ingo Molnar
2008-12-05 8:27 ` David Miller
2008-12-05 8:42 ` Ingo Molnar
2008-12-05 8:49 ` David Miller
2008-12-05 12:13 ` Ingo Molnar
2008-12-05 12:13 ` Ingo Molnar
2008-12-05 12:39 ` Andi Kleen
2008-12-05 20:08 ` David Miller
2008-12-10 3:48 ` Paul Mundt
2008-12-10 4:42 ` Paul Mackerras
2008-12-10 8:43 ` Mikael Pettersson
2008-12-10 10:28 ` Andi Kleen
2008-12-10 10:23 ` Paul Mundt
2008-12-10 11:03 ` Andi Kleen
2008-12-10 11:03 ` Andi Kleen
2008-12-10 10:28 ` Andi Kleen
2008-12-05 15:00 ` Arjan van de Ven
2008-12-05 9:16 ` Paul Mackerras
2008-12-05 7:57 ` David Miller
2008-12-05 8:18 ` Ingo Molnar
2008-12-05 8:20 ` David Miller
2008-12-05 7:54 ` Paul Mackerras
2008-12-05 8:08 ` Ingo Molnar
2008-12-05 8:15 ` David Miller
2008-12-05 13:25 ` Ingo Molnar
2008-12-05 9:10 ` Paul Mackerras
2008-12-05 12:07 ` Ingo Molnar
2008-12-06 0:05 ` Paul Mackerras
2008-12-06 1:23 ` Mikael Pettersson
2008-12-06 12:34 ` Peter Zijlstra
2008-12-07 5:15 ` Paul Mackerras
2008-12-08 7:18 ` stephane eranian
2008-12-08 11:11 ` Ingo Molnar
2008-12-08 11:58 ` David Miller
2008-12-09 0:21 ` stephane eranian
2008-12-09 0:21 ` stephane eranian
2008-12-05 0:22 ` H. Peter Anvin
2008-12-05 0:43 ` Paul Mackerras
2008-12-05 1:12 ` David Miller
2008-12-05 6:10 ` Ingo Molnar
2008-12-05 7:50 ` David Miller
2008-12-05 9:34 ` Paul Mackerras
2008-12-05 10:41 ` Ingo Molnar
2008-12-05 10:05 ` Ingo Molnar
2008-12-05 3:30 ` Andrew Morton
2008-12-06 2:36 ` stephane eranian
2008-12-08 2:12 ` [perfmon2] [patch 0/3] [Announcement] Performance Counters forLinux Dan Terpstra
2008-12-10 16:27 ` [patch 0/3] [Announcement] Performance Counters for Linux Rob Fowler
2008-12-10 16:27 ` [perfmon2] " Rob Fowler
2008-12-10 17:11 ` Andi Kleen
2008-12-10 17:11 ` Andi Kleen
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=20081204.235238.229578299.davem@davemloft.net \
--to=davem@davemloft.net \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=arjan@infradead.org \
--cc=dada1@cosmosbay.com \
--cc=eranian@googlemail.com \
--cc=hpa@zytor.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=paulus@samba.org \
--cc=robert.richter@amd.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
/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