Re: [PATCH 2/2] perf-report: add --max-stack option to limit callchainstack scan

[Waiman Long]

On 10/16/2013 11:01 PM, David Ahern wrote:
> On 10/16/13 1:59 PM, Waiman Long wrote:
> > This patch adds a new --max-stack option to perf-report to limit the
> > depth of callchain stack data to look at to reduce the time it takes
> > for perf-report to finish its processing. It trades the presence of
> > trailing stack information with faster speed.
>
> I like the patch. I have a similar option in my perf-sched-timehist 
> command, and I have a patch somewhere for perf-script.
>
> It would be even better to pass this arg kernel side and limit the 
> stack depth at data collection time.

That will require option a similar option on the record side. However, 
the overhead of collecting more stack ip address isn't as high as that 
in the report side.

> ---8<---
>
> > diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
> > index 72eae74..d90d04a 100644
> > --- a/tools/perf/builtin-report.c
> > +++ b/tools/perf/builtin-report.c
> > @@ -37,6 +37,12 @@
> >
> >   #include <linux/bitmap.h>
> >
> > +/*
> > + * 2-level stringification macro to enable stringification of macro 
> > value
> > + * */
> > +#define    __to_string(x)    #x
> > +#define    STRINGIFY(x)    __to_string(x)
>
> These 2 lines should be somewhere else -- like util/util.h

I will move that to a common header file.

> ---8<---
>
> > diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
> > index 2122141..2725aca 100644
> > --- a/tools/perf/builtin-top.c
> > +++ b/tools/perf/builtin-top.c
> > @@ -771,7 +771,8 @@ static void perf_event__process_sample(struct 
> > perf_tool *tool,
> >               sample->callchain) {
> >               err = machine__resolve_callchain(machine, evsel,
> >                                al.thread, sample,
> > - &parent, &al);
> > + &parent, &al,
> > +                             PERF_MAX_STACK_DEPTH);
> >               if (err)
> >                   return;
> >           }
>
> Why not add the option to perf-top as well? copy-paste.

I had thought about it, but I decided to wait for feedback before doing 
it. I will make that change in the next version.

-Longman

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/