Date: Thu, 23 Oct 2008 20:45:02 -0400
From: Mathieu Desnoyers <compudj@krystal.dyndns.org>
To: ltt-dev@lists.casi.polymtl.ca, "Martin J. Bligh" <mbligh@mbligh.org>,
       Steven Rostedt <rostedt@goodmis.org>, Ingo Molnar <mingo@elte.hu>,
       Linus Torvalds <torvalds@linux-foundation.org>,
       Andrew Morton <akpm@linux-foundation.org>,
       Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linux-kernel@vger.kernel.org, systemtap@sources.redhat.com,
       kernel-trace-list@redhat.com
Subject: LTTng 0.44 and LTTV 0.11.3
Message-ID: <20081024004502.GA21759@Krystal>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Content-Disposition: inline
User-Agent: Mutt/1.5.16 (2007-06-11)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 2656
Lines: 54

Hi,

Here is why I have been a bit more quiet in the past days. I announce
the release of LTTng 0.44 based on kernel 2.6.27.2. The highlights :

- includes trace_clock() patchset, which will also be posted on LKML for
  review shortly (v2 of LTTng timestamping).

- includes the specialized probes I have been talking about with the
  Google team. This will mainly please Steven who want to write into C
  structures without any marker overhead. Now you have it in LTTng.
  There are restrictions about which types can be written into a
  structure though, as not every types can be exported portably (e.g. no
  bitfields can be used). This is made possible by optionally splitting
  the marker declaration from the marker call to let someone declare a
  marker only to keep track of the associated event types.

  For details, see :
  http://git.kernel.org/?p=linux/kernel/git/compudj/linux-2.6-lttng.git;a=commitdiff;h=37f78b629d1eca204aa7edd282599727b7a8a377

- I created specialized probes for the main events generated by tbench
  and went from 960 -> 1125 MB/s (~2000MB/s without tracing) in flight
  recorder mode. That should please Martin for whom every cycle counts.
  ;) We might want to dissect ltt-type-serializer.o, ltt-relay.o and
  ltt-relay-alloc.o, because almost all the slowdown is located within
  these "core" objects.

  For details, see :
  http://git.kernel.org/?p=linux/kernel/git/compudj/linux-2.6-lttng.git;a=commitdiff;h=0ac863964d4d2877eada0383e62d2021cfca6958

- I have also vastly simplified locking in the markers and tracepoints
  by using _only_ the modules mutex. I actually took this mutex out of
  module.c and created its own file so tracepoints and markers can use
  it. That should please Lai Jiangshan. Although he may have some work
  to do to see how his new probes manager might benefit from it.

  See :
  http://git.kernel.org/?p=linux/kernel/git/compudj/linux-2.6-lttng.git;a=commitdiff;h=7aea87ac46df7613d68034f5904bc8d575069076
  and
  http://git.kernel.org/?p=linux/kernel/git/compudj/linux-2.6-lttng.git;a=commitdiff;h=5f6814237f7a67650e7b6214d916825e3f8fc1b7
  http://git.kernel.org/?p=linux/kernel/git/compudj/linux-2.6-lttng.git;a=commitdiff;h=410ba66a1cbe27a611e1c18c0a53e87b4652a2c9

So hopefully everyone will be happy with this new release. :)

Mathieu

-- 
Mathieu Desnoyers
OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F  BA06 3F25 A8FE 3BAE 9A68
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/