From: Frederic Weisbecker <fweisbec@gmail.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>,
Jens Axboe <jens.axboe@oracle.com>,
Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>,
linux-kernel@vger.kernel.org, Paul Mackerras <paulus@samba.org>,
Tom Zanussi <tzanussi@gmail.com>,
Steven Rostedt <srostedt@redhat.com>,
Thomas Gleixner <tglx@linutronix.de>,
Greg Kroah-Hartman <gregkh@suse.de>
Subject: Re: [PATCH 00/12] perf lock: New subcommand "perf lock", for analyzing lock statistics
Date: Mon, 1 Feb 2010 18:58:14 +0100 [thread overview]
Message-ID: <20100201175812.GC5241@nowhere> (raw)
In-Reply-To: <20100201092239.GA22578@elte.hu>
On Mon, Feb 01, 2010 at 10:22:39AM +0100, Ingo Molnar wrote:
>
> * Peter Zijlstra <peterz@infradead.org> wrote:
>
> > On Sun, 2010-01-31 at 22:07 +0100, Frederic Weisbecker wrote:
> > >
> > > - We are using the -M option from perf tools which multiplexes every
> > > event buffers, which means every cpu commit their lock events in
> > > the same buffer. Couple that with the two above reasons, it's supposed
> > > to scale at worst.
> >
> > Why are you doing that? That seems like asking for trouble..
>
> But as i said i already tried with -M off and it didnt cure the slowdown.
Ah.. I've tested the lock events in an atom (two hardware threads) and there
is quite a slowdown too.
Anyway, the patches to remove the string copies from critical lock events
are soon to be ready now. I just suspect there are other problems somewhere
else that cause the slowdown.
>
> that -M was just copied over from perf sched (where it makes sense).
>
> Ingo
For now it is necessary, because we need the events to be ordered by time,
otherwise the state machine in perf lock would be broken.
We can certainly reorder the events in post-processing, but lock events
tend to grow the file _very_ quickly, so I fear this is going to require
lot of memory. I'll try to find a smart way to fix that.
next prev parent reply other threads:[~2010-02-01 17:58 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-01-22 13:39 [PATCH 00/12] perf lock: New subcommand "perf lock", for analyzing lock statistics Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 01/12] perf tools: Add __data_loc support Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 02/12] perf: Add util/include/linuxhash.h to include hash.h of kernel Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 03/12] lockdep: Add information of file and line where lock inited to struct lockdep_map Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 04/12] lockdep: Add file and line to initialize sequence of spinlock Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 05/12] lockdep: Add file and line to initialize sequence of rwlock Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 06/12] lockdep: Add file and line to initialize sequence of rwsem Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 07/12] lockdep: Add file and line to initialize sequence of rwsem (x86) Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 08/12] lockdep: Add file and line to initialize sequence of mutex Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 09/12] lockdep: Fix the way to initialize class_mutex for information of file and line Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 10/12] perf lock: Enhance information of lock trace events Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 11/12] perf lock: New subcommand "perf lock", for analyzing lock statistics Hitoshi Mitake
2010-01-28 6:51 ` Hitoshi Mitake
2010-01-28 14:28 ` [PATCH] perf: Add util/include/linux/config.h for including generated autoconf.h of kernel Hitoshi Mitake
2010-01-28 14:44 ` Peter Zijlstra
2010-01-30 11:44 ` Hitoshi Mitake
2010-01-28 22:27 ` Paul Mackerras
2010-01-30 11:51 ` Hitoshi Mitake
2010-01-22 13:39 ` [PATCH 12/12] Revert "perf record: Intercept all events" Hitoshi Mitake
2010-01-25 2:23 ` Arnaldo Carvalho de Melo
2010-01-25 14:47 ` Hitoshi Mitake
2010-01-25 14:50 ` Peter Zijlstra
2010-01-25 14:57 ` Arnaldo Carvalho de Melo
2010-01-26 7:17 ` Hitoshi Mitake
2010-01-22 16:42 ` [PATCH 00/12] perf lock: New subcommand "perf lock", for analyzing lock statistics Jason Baron
2010-01-22 16:48 ` Peter Zijlstra
2010-01-22 16:52 ` Peter Zijlstra
2010-01-23 6:57 ` Ingo Molnar
2010-01-25 14:15 ` Hitoshi Mitake
2010-01-25 14:48 ` Peter Zijlstra
2010-01-26 7:04 ` Hitoshi Mitake
2010-01-26 4:26 ` Greg KH
2010-01-29 14:34 ` Jens Axboe
2010-01-30 12:00 ` Hitoshi Mitake
2010-01-31 20:44 ` Jens Axboe
2010-01-31 21:07 ` Frederic Weisbecker
2010-01-31 21:11 ` Jens Axboe
2010-02-01 9:15 ` Peter Zijlstra
2010-02-01 9:22 ` Ingo Molnar
2010-02-01 17:58 ` Frederic Weisbecker [this message]
2010-02-01 13:23 ` Jens Axboe
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=20100201175812.GC5241@nowhere \
--to=fweisbec@gmail.com \
--cc=gregkh@suse.de \
--cc=jens.axboe@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=mitake@dcl.info.waseda.ac.jp \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=srostedt@redhat.com \
--cc=tglx@linutronix.de \
--cc=tzanussi@gmail.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