mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Jiri Olsa <jolsa@redhat.com>
To: Andi Kleen <andi@firstfloor.org>
Cc: jolsa@kernel.org, acme@kernel.org, mingo@kernel.org,
	linux-kernel@vger.kernel.org, Andi Kleen <ak@linux.intel.com>
Subject: Re: [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing
Date: Wed, 4 Nov 2015 09:34:56 +0100	[thread overview]
Message-ID: <20151104083456.GE29671@krava.brq.redhat.com> (raw)
In-Reply-To: <1446515428-7450-4-git-send-email-andi@firstfloor.org>

On Mon, Nov 02, 2015 at 05:50:22PM -0800, Andi Kleen wrote:

SNIP

> @@ -307,119 +302,145 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
>  		total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
>  		if (total) {
>  			ratio = avg / total;
> -			fprintf(out, " #   %5.2f  insns per cycle        ", ratio);
> +			print_metric(ctxp, NULL, "%7.2f ",
> +					"insn per cycle", ratio);
>  		} else {
> -			fprintf(out, "                                   ");
> +			print_metric(ctxp, NULL, NULL, "insn per cycle", 0);
>  		}
>  		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
>  		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
>  
> +		out->new_line(ctxp);

I think this needs to be in the condition below (check patch below)
otherwise you'll get empty new line in case there's no stalled-cycles events

>  		if (total && avg) {
>  			ratio = total / avg;
> -			fprintf(out, "\n");
> -			if (aggr == AGGR_NONE)
> -				fprintf(out, "        ");
> -			fprintf(out, "                                                  #   %5.2f  stalled cycles per insn", ratio);
> +			print_metric(ctxp, NULL, "%7.2f ",
> +					"stalled cycles per insn",
> +					ratio);
> +		} else {
> +			print_metric(ctxp, NULL, NULL,
> +				     "stalled cycles per insn", 0);
>  		}

also I dont understand the reason for the else case in here

jirka

> -
> -	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
> -			runtime_branches_stats[ctx][cpu].n != 0) {
> -		print_branch_misses(out, cpu, evsel, avg);


---
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 4d8f18581b9b..367e220e93d5 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -310,8 +310,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 		total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
 		total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
 
-		out->new_line(ctxp);
 		if (total && avg) {
+			out->new_line(ctxp);
 			ratio = total / avg;
 			print_metric(ctxp, NULL, "%7.2f ",
 					"stalled cycles per insn",

  reply	other threads:[~2015-11-04  8:35 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-11-03  1:50 perf, tools: Refactor and support interval and CSV metrics v6 Andi Kleen
2015-11-03  1:50 ` [PATCH 1/9] perf, tools, stat: Move sw clock metrics printout to stat-shadow Andi Kleen
2015-11-04  8:15   ` Jiri Olsa
2015-11-08  7:28   ` [tip:perf/urgent] perf " tip-bot for Andi Kleen
2015-11-03  1:50 ` [PATCH 2/9] tools, perf, stat: Use common printout faction to avoid duplicated code Andi Kleen
2015-11-04  8:15   ` Jiri Olsa
2015-11-08  7:28   ` [tip:perf/urgent] perf stat: Use common printout function " tip-bot for Andi Kleen
2015-11-03  1:50 ` [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing Andi Kleen
2015-11-04  8:34   ` Jiri Olsa [this message]
2015-11-04  8:42   ` Jiri Olsa
2015-11-05  2:43     ` Andi Kleen
2015-11-05  6:52       ` Jiri Olsa
2015-11-05 15:20         ` Andi Kleen
2015-11-03  1:50 ` [PATCH 4/9] perf, tools, stat: Add support for metrics in interval mode Andi Kleen
2015-11-03  1:50 ` [PATCH 5/9] perf, tools, stat: Move noise/running printing into printout Andi Kleen
2015-11-04  8:48   ` Jiri Olsa
2015-11-03  1:50 ` [PATCH 6/9] perf, tools, stat: Implement CSV metrics output Andi Kleen
2015-11-03  1:50 ` [PATCH 7/9] perf, tools, stat: Move non counting counter printing to printout Andi Kleen
2015-11-03  1:50 ` [PATCH 8/9] perf, tools: Support metrics in --per-core/socket mode Andi Kleen
2015-11-03  1:50 ` [PATCH 9/9] perf, tools, stat: Document CSV format in manpage Andi Kleen
2015-11-03  7:46 ` perf, tools: Refactor and support interval and CSV metrics v6 Jiri Olsa
2015-11-05  2:43   ` Andi Kleen
  -- strict thread matches above, loose matches on Subject: below --
2015-10-23 23:59 perf, tools: Refactor and support interval and CSV metrics v5 Andi Kleen
2015-10-23 23:59 ` [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing Andi Kleen
2015-09-21 23:49 perf, tools: Refactor and support interval and CSV metrics v4 Andi Kleen
2015-09-21 23:49 ` [PATCH 3/9] perf, tools, stat: Abstract stat metrics printing Andi Kleen

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=20151104083456.GE29671@krava.brq.redhat.com \
    --to=jolsa@redhat.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=andi@firstfloor.org \
    --cc=jolsa@kernel.org \
    --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

all inboxes | Powered by JetHome®