* perf timechart segfault
@ 2010-10-24 16:23 Sitsofe Wheeler
2010-10-24 17:03 ` Arjan van de Ven
0 siblings, 1 reply; 3+ messages in thread
From: Sitsofe Wheeler @ 2010-10-24 16:23 UTC (permalink / raw)
To: Peter Zijlstra, Paul Mackerras, Ingo Molnar,
Arnaldo Carvalho de Melo
Cc: linux-kernel
Hi,
I've run into a couple of issues using perf timechart:
1. (On 2.6.36) If I issue
echo 0 > /proc/sys/kernel/perf_event_paranoid
as root before running
perf timechart record echo
as a normal user the following is printed:
Fatal: Permission error - are you root?
Consider tweaking /proc/sys/kernel/perf_event_paranoid.
Shouldn't it just say it needs root permissions for a timechart
record?
2. (On -tip) Running
perf timechart record echo
outputs
invalid or unsupported event: 'power:power_start'
Run 'perf list' for a list of valid events
3. (On 2.6.36) I can't seem to convince timechart to ever capture more
than 34000 samples. When trying to record using
perf timechart record -fga sleep 10
and then creating a graph using perf timechart, it only ever outputs
a few seconds worth.
--
Sitsofe | http://sucs.org/~sits/
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: perf timechart segfault
2010-10-24 16:23 perf timechart segfault Sitsofe Wheeler
@ 2010-10-24 17:03 ` Arjan van de Ven
2010-10-24 17:11 ` Ingo Molnar
0 siblings, 1 reply; 3+ messages in thread
From: Arjan van de Ven @ 2010-10-24 17:03 UTC (permalink / raw)
To: Sitsofe Wheeler
Cc: Peter Zijlstra, Paul Mackerras, Ingo Molnar,
Arnaldo Carvalho de Melo, linux-kernel
On Sun, 24 Oct 2010 17:23:02 +0100
Sitsofe Wheeler <sitsofe@yahoo.com> wrote:
> Hi,
>
> I've run into a couple of issues using perf timechart:
>
> 1. (On 2.6.36) If I issue
> echo 0 > /proc/sys/kernel/perf_event_paranoid
> as root before running
> perf timechart record echo
> as a normal user the following is printed:
>
> Fatal: Permission error - are you root?
> Consider tweaking /proc/sys/kernel/perf_event_paranoid.
>
> Shouldn't it just say it needs root permissions for a timechart
> record?
timechart needs root perms since it gets very global data.
>
> 2. (On -tip) Running
> perf timechart record echo
> outputs
> invalid or unsupported event: 'power:power_start'
> Run 'perf list' for a list of valid events
tip broke ABI :-(
That's one for Ingo to deal with for now.
>
> 3. (On 2.6.36) I can't seem to convince timechart to ever capture more
> than 34000 samples. When trying to record using
> perf timechart record -fga sleep 10
> and then creating a graph using perf timechart, it only ever
> outputs a few seconds worth.
does this happen even without the "fga" ?
I've used timechart to capture a minute of data before
(but... you need a rather quiet system for that to be useful.... you
otherwise get an impossibly big SVG file)
--
Arjan van de Ven Intel Open Source Technology Centre
For development, discussion and tips for power savings,
visit http://www.lesswatts.org
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: perf timechart segfault
2010-10-24 17:03 ` Arjan van de Ven
@ 2010-10-24 17:11 ` Ingo Molnar
0 siblings, 0 replies; 3+ messages in thread
From: Ingo Molnar @ 2010-10-24 17:11 UTC (permalink / raw)
To: Arjan van de Ven
Cc: Sitsofe Wheeler, Peter Zijlstra, Paul Mackerras,
Arnaldo Carvalho de Melo, linux-kernel
* Arjan van de Ven <arjan@infradead.org> wrote:
> > 2. (On -tip) Running
> > perf timechart record echo
> > outputs
> > invalid or unsupported event: 'power:power_start'
> > Run 'perf list' for a list of valid events
>
> tip broke ABI :-(
hm, i'm not aware of that - where, which commit?
Thanks,
Ingo
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2010-10-24 17:11 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-10-24 16:23 perf timechart segfault Sitsofe Wheeler
2010-10-24 17:03 ` Arjan van de Ven
2010-10-24 17:11 ` Ingo Molnar
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.