LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Richard J Moore <richardj_moore@uk.ibm.com>
To: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
Cc: Andrew Morton <akpm@osdl.org>,
	Greg Kroah-Hartman <gregkh@suse.de>,
	Christoph Hellwig <hch@infradead.org>,
	linux-kernel@vger.kernel.org, ltt-dev@shafik.org,
	"Martin J. Bligh" <mbligh@mbligh.org>,
	Ingo Molnar <mingo@redhat.com>,
	Douglas Niehaus <niehaus@eecs.ku.edu>,
	systemtap@sources.redhat.com,
	Thomas Gleixner <tglx@linutronix.de>
Subject: Re: [PATCH 0/4] Linux Kernel Markers
Date: Sat, 13 Jan 2007 01:33:29 +0000	[thread overview]
Message-ID: <OFAB3D8A6C.1643F2D3-ON80257262.000581E4-80257262.00088F04@uk.ibm.com> (raw)
In-Reply-To: <20061220235216.GA28643@Krystal>



Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> wrote on 20/12/2006
23:52:16:

> Hi,
>
> You will find, in the following posts, the latest revision of the Linux
Kernel
> Markers. Due to the need some tracing projects (LTTng, SystemTAP) has of
this
> kind of mechanism, it could be nice to consider it for mainstream
inclusion.
>
> The following patches apply on 2.6.20-rc1-git7.
>
> Signed-off-by : Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>

Mathiue, FWIW I like this idea. A few years ago I implemented something
similar, but that had no explicit clients. Consequently I made my hooks
code more generalized than is needed in practice. I do remember that Karim
reworked the LTT instrumentation to use hooks and it worked fine.

You've got the same optimizations for x86 by modifying an instruction's
immediate operand and thus avoiding a d-cache hit. The only real caveat is
the need to avoid the unsynchronised cross modification erratum. Which
means that all processors will need to issue a serializing operation before
executing a Marker whose state is changed. How is that handled?

One additional thing we did, which might be useful at some future point,
was adding a /proc interface. We reflected the current instrumentation
though /proc and gave the status of each hook. We even talked about being
able to enable or disabled instrumentation by writing to /proc but I don't
think we ever implemented this.

It's high time we settled the issue of instrumentation. It gets my vote,

Good luck!

Richard

- -
Richard J Moore
IBM Linux Technology Centre


  parent reply	other threads:[~2007-01-13  1:33 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2006-12-20 23:52 Mathieu Desnoyers
2006-12-20 23:57 ` [PATCH 1/4] Linux Kernel Markers : Architecture agnostic code Mathieu Desnoyers
2006-12-20 23:59 ` [PATCH 2/4] Linux Kernel Markers : kconfig menus Mathieu Desnoyers
2006-12-21  0:00 ` [PATCH 3/4] Linux Kernel Markers : i386 optimisation Mathieu Desnoyers
2006-12-21  0:01 ` [PATCH 4/4] Linux Kernel Markers : powerpc optimisation Mathieu Desnoyers
2007-01-13  1:33 ` Richard J Moore [this message]
2007-01-13  5:45   ` [PATCH 0/4] Linux Kernel Markers Mathieu Desnoyers
2007-01-16 17:41     ` [PATCH 0/4 update] Linux Kernel Markers - i386 : pIII erratum 49 : XMC Mathieu Desnoyers
2007-01-16 18:35       ` Frank Ch. Eigler
2007-01-16 21:27       ` [PATCH 0/4 update] kprobes and traps Mathieu Desnoyers
2007-01-17 12:25         ` S. P. Prasanna
2007-01-16 17:56   ` [PATCH 1/2] lockdep missing barrier() Mathieu Desnoyers
2007-01-24  4:26     ` Andrew Morton
2007-01-24 16:51       ` Mathieu Desnoyers
2007-01-24 17:24         ` [PATCH] order of lockdep off/on in vprintk() should be changed Mathieu Desnoyers
2007-01-24 17:55           ` [PATCH] minimize lockdep_on/off side-effect Mathieu Desnoyers
2007-01-16 17:56   ` [PATCH 2/2] lockdep reentrancy Mathieu Desnoyers
2007-01-24  4:29     ` Andrew Morton
2007-01-24 16:55       ` Mathieu Desnoyers
2007-07-03 17:08 [patch 0/4] Linux Kernel Markers Mathieu Desnoyers
2007-07-03 18:01 ` Mathieu Desnoyers
2007-07-05  2:00 ` Frank Ch. Eigler
2007-07-11 21:43   ` Mathieu Desnoyers
2007-07-14  1:29 Mathieu Desnoyers
2007-08-12 15:10 Mathieu Desnoyers
2007-08-20 20:27 Mathieu Desnoyers
2007-08-27 16:05 Mathieu Desnoyers
2007-08-30 17:12 ` Christoph Hellwig
2007-08-31  1:16   ` Andrew Morton
2007-09-17 18:46 Mathieu Desnoyers

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=OFAB3D8A6C.1643F2D3-ON80257262.000581E4-80257262.00088F04@uk.ibm.com \
    --to=richardj_moore@uk.ibm.com \
    --cc=akpm@osdl.org \
    --cc=gregkh@suse.de \
    --cc=hch@infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ltt-dev@shafik.org \
    --cc=mathieu.desnoyers@polymtl.ca \
    --cc=mbligh@mbligh.org \
    --cc=mingo@redhat.com \
    --cc=niehaus@eecs.ku.edu \
    --cc=systemtap@sources.redhat.com \
    --cc=tglx@linutronix.de \
    --subject='Re: [PATCH 0/4] Linux Kernel Markers' \
    /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

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).