Messages in this thread | | | Date | Mon, 28 Jan 2008 07:15:50 -0500 (EST) | From | Steven Rostedt <> | Subject | Re: [PATCH 06/20 -v5] add notrace annotations for NMI routines |
| |
On Mon, 28 Jan 2008, Jan Kiszka wrote: > Steven Rostedt wrote: > > On Wed, 23 Jan 2008, Mathieu Desnoyers wrote: > > > >> * Steven Rostedt (rostedt@goodmis.org) wrote: > >>> This annotates NMI functions with notrace. Some tracers may be able > >>> to live with this, but some cannot. So we turn off NMI tracing. > >>> > >>> One solution might be to make a notrace_nmi which would only turn > >>> off NMI tracing if a trace utility needed it off. > >>> > >> Is this still needed with the atomic clocksource read ? > >> > > > > Before you ask again, I've still included this in -v6, simply because I > > didn't get a chance to test it without this patch. I'll try to remember to > > do that on Monday. > > Only in case you finally have to keep the annotations for the posted > tracer: Then please make it a Kconfig selectable restriction, because > there are use cases of the mcount hook where you are interested in NMI > invocations.
I've thought about adding a notrace_nmi which would do precisely that. This week I'll take this patch out and turn on a bunch of nmi profiling and see how it holds up.
Thanks,
-- Steve
| |