[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20090802144242.GB22659@elte.hu>
Date: Sun, 2 Aug 2009 16:42:42 +0200
From: Ingo Molnar <mingo@...e.hu>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: Peter Zijlstra <a.p.zijlstra@...llo.nl>,
linux-kernel@...r.kernel.org,
Frederic Weisbecker <fweisbec@...il.com>,
Jason Baron <jbaron@...hat.com>,
Paul Mackerras <paulus@...ba.org>
Subject: Re: [PATCH 04/13] ftrace: perf_counter intergration
* Steven Rostedt <rostedt@...dmis.org> wrote:
>
> On Thu, 23 Jul 2009, Peter Zijlstra wrote:
>
> > Adds possible second part to the assign argument of TP_EVENT().
> >
> > TP_perf_assign(
> > __perf_count(foo);
> > __perf_addr(bar);
> > )
> >
> > Which, when specified make the swcounter increment with @foo instead
> > of the usual 1, and report @bar for PERF_SAMPLE_ADDR (data address
> > associated with the event) when this triggers a counter overflow.
>
> Looks good,
>
> Acked-by: Steven Rostedt <rostedt@...dmis.org>
looks good to me too - but i skipped it for now because it has build
failures:
In file included from include/trace/ftrace.h:424,
from include/trace/define_trace.h:57,
from include/trace/events/ext4.h:678,
from fs/ext4/super.c:51:
include/trace/events/ext4.h: In function ftrace_profile_ext4_discard_blocks:
include/trace/events/ext4.h:345: error: count redeclared as different kind of symbol
include/trace/events/ext4.h:345: error: previous definition of count was here
config attached.
Ingo
View attachment "config-Sun_Aug__2_14_09_10_CEST_2009.bad" of type "text/plain" (76155 bytes)
Powered by blists - more mailing lists