linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
To: Peter Zijlstra <peterz@infradead.org>
Cc: David Ahern <dsahern@gmail.com>,
	linux-kernel@vger.kernel.org, mingo@kernel.org, jolsa@redhat.com,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Namhyung Kim <namhyung@kernel.org>,
	Mike Galbraith <efault@gmx.de>,
	Stephane Eranian <eranian@google.com>
Subject: Re: [PATCH 4/5] perf record: mmap output file - v5
Date: Tue, 12 Nov 2013 12:07:51 -0300	[thread overview]
Message-ID: <20131112150751.GA19321@ghostprotocols.net> (raw)
In-Reply-To: <20131112145707.GV5056@laptop.programming.kicks-ass.net>

Em Tue, Nov 12, 2013 at 03:57:07PM +0100, Peter Zijlstra escreveu:
> On Tue, Nov 12, 2013 at 07:46:56AM -0700, David Ahern wrote:
> > When recording raw_syscalls for the entire system, e.g.,
> >     perf record -e raw_syscalls:*,sched:sched_switch -a -- sleep 1
> > 
> > you end up with a negative feedback loop as perf itself calls write() fairly
> > often. This patch handles the problem by mmap'ing the file in chunks of 64M at
> > a time and copies events from the event buffers to the file avoiding write
> > system calls.
> 
> You know this completely fails the moment you trace faults, because
> every new access to one of those pages (to mark it dirty) will trigger a
> fault. And we'll take a bunch more faults -- one for each page -- than
> we ever did write() syscalls.

So we should provide a neon lettered warning when doing that, no? :-)
 
> Anyway the over all performance improvements still make it worth it. But
> the above seems like a false argument in favour of this.

  reply	other threads:[~2013-11-12 15:08 UTC|newest]

Thread overview: 42+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-11-12 14:46 [PATCH 0/5] perf record: mmap output file - v5 David Ahern
2013-11-12 14:46 ` [PATCH 1/5] perf record: Fix segfault with --no-mmap-pages David Ahern
2013-11-12 21:57   ` [tip:perf/urgent] " tip-bot for David Ahern
2013-11-12 14:46 ` [PATCH 2/5] perf tool: Round mmap pages to power 2 - v2 David Ahern
2013-11-12 21:57   ` [tip:perf/urgent] perf evlist: " tip-bot for David Ahern
2013-11-12 14:46 ` [PATCH 3/5] perf tool: Refactor mmap_pages parsing David Ahern
2013-11-12 21:57   ` [tip:perf/urgent] perf evlist: " tip-bot for David Ahern
2013-11-12 14:46 ` [PATCH 4/5] perf record: mmap output file - v5 David Ahern
2013-11-12 14:57   ` Peter Zijlstra
2013-11-12 15:07     ` Arnaldo Carvalho de Melo [this message]
2013-11-12 15:19       ` Peter Zijlstra
2013-11-12 15:36         ` David Ahern
2013-11-12 21:11           ` Ingo Molnar
2013-11-13 11:34             ` Peter Zijlstra
2013-11-13 11:50               ` Ingo Molnar
2013-11-13 12:16                 ` Peter Zijlstra
2013-11-13 14:29                 ` David Ahern
2013-11-15 16:41               ` David Ahern
2013-11-18  9:01                 ` Peter Zijlstra
2013-11-18  9:40                   ` Ingo Molnar
2013-11-19  0:24                     ` Namhyung Kim
2013-11-19  0:34                       ` David Ahern
2013-11-19  1:48                         ` Namhyung Kim
2013-11-19  2:02                         ` Namhyung Kim
2013-11-19  2:13                         ` Namhyung Kim
2013-11-19  2:17                           ` David Ahern
2013-11-19  2:30                             ` Namhyung Kim
2013-11-19  2:33                               ` David Ahern
2013-11-19  2:36                                 ` Namhyung Kim
2013-11-19  6:58                                 ` Ingo Molnar
2013-11-19 11:48                                   ` Peter Zijlstra
2013-11-19 11:49                                     ` Peter Zijlstra
2013-11-19 13:13                                       ` Ingo Molnar
2013-11-19 13:45                                         ` Peter Zijlstra
2013-11-19 15:31                                           ` Ingo Molnar
2013-11-19 16:09                                             ` David Ahern
2013-11-19 16:14                                               ` Ingo Molnar
2013-11-19 12:08                         ` Peter Zijlstra
2013-11-19  6:54                       ` Ingo Molnar
2013-11-12 14:46 ` [PATCH 5/5] perf record: Handle out of space failures writing data with mmap David Ahern
2013-11-12 21:19   ` Ingo Molnar
2013-11-13 14:33     ` David Ahern

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=20131112150751.GA19321@ghostprotocols.net \
    --to=acme@ghostprotocols.net \
    --cc=dsahern@gmail.com \
    --cc=efault@gmx.de \
    --cc=eranian@google.com \
    --cc=fweisbec@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=namhyung@kernel.org \
    --cc=peterz@infradead.org \
    /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;
as well as URLs for NNTP newsgroup(s).