linux-kernel - Re: [PATCH 0/5] perf kmem: Add more functions and show more statistics

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20091124184927.GA4994@nowhere>
Date:	Tue, 24 Nov 2009 19:49:35 +0100
From:	Frederic Weisbecker <fweisbec@...il.com>
To:	Ingo Molnar <mingo@...e.hu>
Cc:	Li Zefan <lizf@...fujitsu.com>,
	Pekka Enberg <penberg@...helsinki.fi>,
	Eduard - Gabriel Munteanu <eduard.munteanu@...ux360.ro>,
	Peter Zijlstra <peterz@...radead.org>,
	LKML <linux-kernel@...r.kernel.org>,
	"linux-mm@...ck.org" <linux-mm@...ck.org>
Subject: Re: [PATCH 0/5] perf kmem: Add more functions and show more
	statistics

On Tue, Nov 24, 2009 at 11:07:24AM +0100, Ingo Molnar wrote:
> 
> * Li Zefan <lizf@...fujitsu.com> wrote:
> 
> > > 3)
> > > 
> > > it doesnt seem to be working on one of my boxes, which has perf and kmem 
> > > events as well:
> > > 
> > > aldebaran:~/linux/linux/tools/perf> perf kmem record
> > > ^C[ perf record: Woken up 1 times to write data ]
> > > [ perf record: Captured and wrote 0.050 MB perf.data (~2172 samples) ]
> > > 
> > 
> > Seems no kmem event is recorded. No sure what happened here.
> > 
> > Might be that the parameters that perf-kmem passes to perf-record
> > are not properly selected?
> > 
> > Do perf-sched and perf-timechart work on this box?
> 
> yeah:
> 
> aldebaran:~> perf sched record sleep 1
> [ perf record: Woken up 1 times to write data ]
> [ perf record: Captured and wrote 0.017 MB perf.data (~758 samples) ]
> aldebaran:~> perf trace | tail -5
>          distccd-20944 [010]  1792.787376: sched_stat_runtime: comm=distccd pid=20944 runtime=11196 [ns] vruntime=696395420043 [ns]
>             init-0     [009]  1792.914837: sched_stat_wait: comm=x86_64-linux-gc pid=881 delay=10686 [ns]
>             init-0     [009]  1792.915082: sched_stat_sleep: comm=events/9 pid=44 delay=2183651362 [ns]
>               as-889   [013]  1793.008008: sched_stat_runtime: comm=as pid=889 runtime=156807 [ns] vruntime=1553569219042 [ns]
>             init-0     [004]  1793.154400: sched_stat_wait: comm=events/4 pid=39 delay=12155 [ns]
> 
> aldebaran:~> perf kmem record sleep 1
> [ perf record: Woken up 1 times to write data ]
> [ perf record: Captured and wrote 0.078 MB perf.data (~3398 samples) ]
> aldebaran:~> perf trace | tail -5
> aldebaran:~> 
> 
> the perf.data has mmap and exit events - but no kmem events.
> 
> I've attached the config, in case it matters. It runs latest -tip, with 
> your latest series applied as well.
> 
> 	Ingo



I think this is a problem external to kmem events. It's about
trace events/perf in general. It looks like we have some losses.
Steve and Arjan have reported similar things.

I'll investigate this way.

Thanks.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/