All of lore.kernel.org
 help / color / mirror / Atom feed
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: Ingo Molnar <mingo@elte.hu>
Cc: Theodore Tso <tytso@MIT.EDU>,
	Frederic Weisbecker <fweisbec@gmail.com>, Jan Kara <jack@suse.cz>,
	Steven Rostedt <rostedt@goodmis.org>,
	Thomas Gleixner <tglx@linutronix.de>,
	Li Zefan <lizf@cn.fujitsu.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	Masami Hiramatsu <mhiramat@redhat.com>,
	LKML <linux-kernel@vger.kernel.org>,
	Douglas Santos <douglas.santos@polymtl.ca>
Subject: Re: [PATCH 0/18] Allow different tracers to be compiled independently
Date: Tue, 23 Mar 2010 08:27:47 -0400	[thread overview]
Message-ID: <20100323122747.GA14954@Krystal> (raw)
In-Reply-To: <20100323080526.GB4848@elte.hu>

* Ingo Molnar (mingo@elte.hu) wrote:
> 
> * Theodore Tso <tytso@MIT.EDU> wrote:
> 
> > 
> > On Mar 22, 2010, at 9:04 PM, Frederic Weisbecker wrote:
> > > 
> > > I don't know. Yeah this first looks like a good idea but once 
> > > CONFIG_EVENT_TRACING is enabled, each tracepoint is a lightweight thing 
> > > and induce a tiny overhead, probably hard to notice, and this is going to 
> > > be even more the case after the jmp label optimization patches.
> > > 
> > > I liked the fact we had a general tracing kernel once the above config is 
> > > selected. And we don't bother telling people that to use tool X you need 
> > > CONFIG_EVENT_Y, and you need to rebuild your kernel, etc...
> > 
> > Indeed, a lot of the value of tracepoints goes away if people are compiling 
> > kernels without them and we need to get a special "tracing kernel" installed 
> > before we can debug a problem.
> > 
> > So I'd hope we can do the necessary optimization work so people don't feel 
> > it's necessary to enable or disable tracepoints by subsystem....
> 
> Yeah, agreed. Ultra-embedded can disable them all, but other than that i think 
> we should not make it too finegrained as a lot of tooling value is in the 
> 'critical mass' that tracepoints have achieved. The power events tracepoints 
> are most useful when combined with scheduling events, etc.
> 

We're in complete agreement here. When I considered if it was worth it to create
such a per-tracepoint group compile-time disabling in the first place, I decided
not to do it precisely due to the added-value that comes with the availability
of system-wide tracepoints. And I think with the static jump patching, we are
now at a point where the overhead is stunningly low.

Now, space-wise, the one thing I would consider appropriate as a compromise for
small embedded systems would be to allow the TRACE_EVENT probes to be compiled
as modules.

Thanks,

Mathieu


-- 
Mathieu Desnoyers
Operating System Efficiency R&D Consultant
EfficiOS Inc.
http://www.efficios.com

  reply	other threads:[~2010-03-23 12:27 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-03-23  0:32 [PATCH 0/18] Allow different tracers to be compiled independently Jan Kara
2010-03-23  0:32 ` [PATCH 01/18] trace: Allow <linux/tracepoint.h> to create empty tracepoints Jan Kara
2010-03-23  1:06   ` Steven Rostedt
2010-03-26  1:30     ` Jan Kara
2010-03-23  0:32 ` [PATCH 02/18] block: Generate blktrace trace points only if blktrace is enabled Jan Kara
2010-03-23  0:32 ` [PATCH 03/18] mm: Generate kmemtrace trace points only if they are enabled Jan Kara
2010-03-23  0:32   ` Jan Kara
2010-03-23  0:32 ` [PATCH 04/18] mac80211: Generate trace points only if api tracer enabled Jan Kara
2010-03-23  1:11   ` Johannes Berg
2010-03-23 23:54     ` Steven Rostedt
2010-03-23  0:32 ` [PATCH 05/18] workqueue: Generate trace points only when workqueue " Jan Kara
2010-03-23  0:32 ` [PATCH 06/18] sched: Generate trace points only if scheduler tracing is enabled Jan Kara
2010-03-23  1:07   ` Frederic Weisbecker
2010-03-23 23:52     ` Steven Rostedt
2010-03-24  0:31       ` Frederic Weisbecker
2010-03-23  0:32 ` [PATCH 07/18] ext4: Provide config options for enabling ext4 and jbd2 tracing Jan Kara
2010-03-23  0:32 ` [PATCH 08/18] lockdep: Provide config option for enabling lock tracepoints Jan Kara
2010-03-23  0:32 ` [PATCH 09/18] module: Provide config option to enable tracing of module load / unload Jan Kara
2010-03-23  0:32 ` [Cluster-devel] [PATCH 10/18] gfs2: Provide config option for enabling trace points Jan Kara
2010-03-23  0:32   ` Jan Kara
2010-03-23 12:01   ` [Cluster-devel] " Steven Whitehouse
2010-03-23 12:01     ` Steven Whitehouse
2010-03-23 23:56     ` Steven Rostedt
2010-03-24 11:20       ` Steven Whitehouse
2010-03-24 11:20         ` Steven Whitehouse
2010-03-24 12:09         ` Steven Rostedt
2010-03-23  0:32 ` [PATCH 11/18] i915: Provide config option for enabling tracepoints Jan Kara
2010-03-23  8:42   ` Chris Wilson
2010-03-23  8:42     ` Chris Wilson
2010-03-23  0:32 ` [PATCH 12/18] timer: Provide config option for enabling timer tracepoints Jan Kara
2010-03-23  2:01   ` Thomas Gleixner
2010-03-23  3:01     ` Steven Rostedt
2010-03-23  0:32 ` [PATCH 13/18] acpi: Provide config option to enable power tracepoints Jan Kara
2010-03-23  0:32 ` [PATCH 14/18] net: Provide config option for enabling SKB tracing Jan Kara
2010-03-23  0:32 ` [PATCH 15/18] net: Provide config option for enabling NAPI tracing Jan Kara
2010-03-23  0:32 ` [PATCH 16/18] Generate empty tracepoints if syscall tracing is disabled Jan Kara
2010-03-23  0:32   ` Jan Kara
2010-03-23  0:32 ` [PATCH 17/18] kvm: Provide config option for enabling KVM trace events Jan Kara
2010-03-23  0:32 ` [PATCH 18/18] Create config option for enabling IRQ tracepoints Jan Kara
2010-03-23  1:04 ` [PATCH 0/18] Allow different tracers to be compiled independently Frederic Weisbecker
2010-03-23  3:34   ` Theodore Tso
2010-03-23  8:05     ` Ingo Molnar
2010-03-23 12:27       ` Mathieu Desnoyers [this message]
2010-03-23 13:18         ` Steven Rostedt
2010-03-26  0:20   ` Jan Kara
2010-03-26 19:09     ` Frederic Weisbecker

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=20100323122747.GA14954@Krystal \
    --to=mathieu.desnoyers@efficios.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=douglas.santos@polymtl.ca \
    --cc=fweisbec@gmail.com \
    --cc=jack@suse.cz \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lizf@cn.fujitsu.com \
    --cc=mhiramat@redhat.com \
    --cc=mingo@elte.hu \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    --cc=tytso@MIT.EDU \
    /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 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.