[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20090315053301.GC20949@elte.hu>
Date: Sun, 15 Mar 2009 06:33:01 +0100
From: Ingo Molnar <mingo@...e.hu>
To: Mathieu Desnoyers <compudj@...stal.dyndns.org>
Cc: Jason Baron <jbaron@...hat.com>, rostedt@...dmis.org,
linux-kernel@...r.kernel.org, acme@...stprotocols.net,
fweisbec@...il.com, fche@...hat.com, peterz@...radead.org
Subject: Re: [Patch 2/2] tracepoints for softirq entry/exit - tracepoints
* Mathieu Desnoyers <compudj@...stal.dyndns.org> wrote:
> * Jason Baron (jbaron@...hat.com) wrote:
> >
> > introduce softirq entry/exit tracepoints. These are useful for
> > augmenting existing tracers, and to figure out softirq frequencies and
> > timings.
> >
> > Signed-off-by: Jason Baron <jbaron@...hat.com>
> >
> > ---
> >
> > include/trace/irq_event_types.h | 12 ++++++++++++
> > kernel/softirq.c | 7 ++++++-
> > 2 files changed, 18 insertions(+), 1 deletions(-)
> >
> >
> > diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h
> > index 214bb92..38b4bdd 100644
> > --- a/include/trace/irq_event_types.h
> > +++ b/include/trace/irq_event_types.h
> > @@ -40,4 +40,16 @@ TRACE_EVENT(irq_handler_exit,
> > __entry->irq, __entry->ret ? "handled" : "unhandled")
> > );
> >
> > +TRACE_FORMAT(irq_softirq_entry,
> > + TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
> > + TP_ARGS(h, vec),
> > + TP_FMT("softirq=%d action=%s", h - vec, softirq_to_name[h-vec])
> > + );
> > +
> > +TRACE_FORMAT(irq_softirq_exit,
> > + TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
> > + TP_ARGS(h, vec),
> > + TP_FMT("softirq=%d action=%s", h - vec, softirq_to_name[h-vec])
>
> The softirq tracepoints are a good idea indeed (I have similar
> ones in the LTTng tree). My main concern is about the fact
> that you output the softirq name in plain text to the trace
> buffers. I would rather prefer to save only the softirq
> (h-vec) into the trace and dump the mapping (h-vec) to name
> only once, so we can save precious trace bytes.
The right solution is to change this tracepoint to TRACE_EVENT()
format. Jason, do you have time to do that?
Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists