Re: [PATCH] perf sched replay: fix event lookup

[Arnaldo Carvalho de Melo <acme@ghostprotocols.net>]

Em Wed, Jun 27, 2012 at 01:18:17PM +0400, Dmitry Antipov escreveu:
> On 06/26/2012 03:20 AM, Arnaldo Carvalho de Melo wrote:
> >
> >>Fair enough. The method should be a simple wrapper to libtraceevent APIs
> >>like this patch.
> >
> >The pevent thing is per perf.data file, so I made it stop being static
> >and become a perf_session member, so tools processing perf.data files
> >use perf_session and _there_ we read the event into session->pevent and
> >then have to change everywhere to stop using that single global pevent
> >variable and use the per session one.
> >
> >Dmitry, can you test the attached patch to check if it solves the
> >problems you reported?
> 
> This looks good and works for my x86 <-> ARM tests.

Thanks, adding your Tested-by: Dmitry, ok?
 
> >Note that it _doesn't_ fall backs to trace__event_id, as we're not
> >interested at all in what is present in the
> >/sys/kernel/debug/tracing/events in the workstation doing the analysis,
> >just in what is in the perf.data file.
> 
> Agree.
> 
> Dmitry