The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Namhyung Kim <namhyung@kernel.org>
To: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>,
	Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	LKML <linux-kernel@vger.kernel.org>,
	Brendan Gregg <brendan.d.gregg@gmail.com>,
	David Ahern <dsahern@gmail.com>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	Andi Kleen <andi@firstfloor.org>, Kan Liang <kan.liang@intel.com>
Subject: Re: [PATCH v3 2/4] perf callchain: Abstract callchain print function
Date: Tue, 3 Nov 2015 19:31:13 +0900	[thread overview]
Message-ID: <20151103103113.GA5733@danjae.kornet> (raw)
In-Reply-To: <20151103084055.GH23878@krava.brq.redhat.com>

Hi Jiri,

On Tue, Nov 03, 2015 at 09:40:55AM +0100, Jiri Olsa wrote:
> On Tue, Nov 03, 2015 at 04:18:29PM +0900, Namhyung Kim wrote:
> 
> SNIP
> 
> >  	while (rb_node) {
> > -		double percent;
> > -
> >  		chain = rb_entry(rb_node, struct callchain_node, rb_node);
> > -		percent = chain->hit * 100.0 / total_samples;
> >  
> > -		ret = percent_color_fprintf(fp, "           %6.2f%%\n", percent);
> > +		ret += fprintf(fp, "           ");
> > +		ret += callchain_node__fprintf_value(chain, fp, total_samples);
> > +		ret += fprintf(fp, "\n");
> >  		ret += __callchain__fprintf_flat(fp, chain, total_samples);
> >  		ret += fprintf(fp, "\n");
> >  		if (++entries_printed == callchain_param.print_limit)
> > @@ -294,12 +294,11 @@ static size_t callchain__fprintf_folded(FILE *fp, struct rb_root *tree,
> >  	struct rb_node *rb_node = rb_first(tree);
> >  
> >  	while (rb_node) {
> > -		double percent;
> >  
> >  		chain = rb_entry(rb_node, struct callchain_node, rb_node);
> > -		percent = chain->hit * 100.0 / total_samples;
> >  
> > -		ret += fprintf(fp, "%.2f%% ", percent);
> > +		ret += callchain_node__fprintf_value(chain, fp, total_samples);
> > +		ret += fprintf(fp, " ");
> 
> hum, the callchain_node__fprintf_value gets hits as callchain_cumul_hits(node)
> which is 'node->hit + node->children_hit'
> 
> while the replaced code took only 'chain->hit'
> 
> not sure now which one we actualy want here..

Right, this is somewhat confusing..

AFAICS cumul_hits is used for other output mode, but for folded output
we should use hit without children_hit.

I added the check to use count in patch 4/4 but missed to use hit.
Will update.

Thanks,
Namhyung



> 
> >  		ret += __callchain__fprintf_folded(fp, chain);
> >  		ret += fprintf(fp, "\n");
> >  		if (++entries_printed == callchain_param.print_limit)
> > diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
> > index 08cb220ba5ea..44184d198855 100644
> > --- a/tools/perf/util/callchain.c
> > +++ b/tools/perf/util/callchain.c
> > @@ -805,6 +805,31 @@ char *callchain_list__sym_name(struct callchain_list *cl,
> >  	return bf;
> >  }
> >  
> > +char *callchain_node__sprintf_value(struct callchain_node *node,
> > +				    char *bf, size_t bfsize, u64 total)
> > +{
> > +	double percent = 0.0;
> > +	u64 cumul = callchain_cumul_hits(node);
> > +
> > +	if (total)
> > +		percent = cumul * 100.0 / total;
> > +
> > +	scnprintf(bf, bfsize, "%6.2f%%", percent);
> > +	return bf;
> > +}
> > +
> > +int callchain_node__fprintf_value(struct callchain_node *node,
> > +				 FILE *fp, u64 total)
> > +{
> > +	double percent = 0.0;
> > +	u64 cumul = callchain_cumul_hits(node);
> > +
> > +	if (total)
> > +		percent = cumul * 100.0 / total;
> > +
> > +	return percent_color_fprintf(fp, "%.2f%%", percent);
> > +}
> 
> SNIP

  reply	other threads:[~2015-11-03 10:31 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-03  7:18 [PATCH 0/4] perf report: Support folded callchain output (v3) Namhyung Kim
2015-11-03  7:18 ` [PATCH v3 1/4] perf report: Support folded callchain mode on --stdio Namhyung Kim
2015-11-03  8:21   ` Jiri Olsa
2015-11-03  7:18 ` [PATCH v3 2/4] perf callchain: Abstract callchain print function Namhyung Kim
2015-11-03  8:40   ` Jiri Olsa
2015-11-03 10:31     ` Namhyung Kim [this message]
2015-11-03  7:18 ` [PATCH v3 3/4] perf callchain: Add count fields to struct callchain_node Namhyung Kim
2015-11-03  9:03   ` Jiri Olsa
2015-11-03  7:18 ` [PATCH v3 4/4] perf report: Add callchain value option Namhyung Kim
2015-11-03  9:04   ` Jiri Olsa
2015-11-03  9:06   ` Jiri Olsa
2015-11-03 10:53     ` Namhyung Kim
2015-11-03 11:19       ` Jiri Olsa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20151103103113.GA5733@danjae.kornet \
    --to=namhyung@kernel.org \
    --cc=a.p.zijlstra@chello.nl \
    --cc=acme@kernel.org \
    --cc=andi@firstfloor.org \
    --cc=brendan.d.gregg@gmail.com \
    --cc=dsahern@gmail.com \
    --cc=fweisbec@gmail.com \
    --cc=jolsa@redhat.com \
    --cc=kan.liang@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox