[Patch] perf stat: always separate stalled cycles per insn

[Patch] perf stat: always separate stalled cycles per insn

[Cong Wang]

The "stalled cycles per insn" is appended to "instructions" when
the CPU has this hardware counter directly. We should always make it
a separate line, which also aligns to the output when we hit the
"if (total && avg)" branch.

Before:
$ sudo perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
4565048704,,instructions,64114578096,100.00,1.34,insn per cycle,,
3396325133,,cycles,64146628546,100.00,,

After:
$ sudo ./tools/perf/perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
6721924,,instructions,24026790339,100.00,0.22,insn per cycle
,,,,,0.00,stalled cycles per insn
30939953,,cycles,24025512526,100.00,,

Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
---
 tools/perf/util/stat-shadow.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 83d8094be4fe..5c5e012e99c4 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -800,7 +800,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(config, ctxp, NULL, NULL,
+			out->new_line(config, ctxp);
+			print_metric(config, ctxp, NULL, "%7.2f ",
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
-- 
2.21.0

Re: [Patch] perf stat: always separate stalled cycles per insn

[Jiri Olsa]

On Fri, May 17, 2019 at 03:10:39PM -0700, Cong Wang wrote:
> The "stalled cycles per insn" is appended to "instructions" when
> the CPU has this hardware counter directly. We should always make it
> a separate line, which also aligns to the output when we hit the
> "if (total && avg)" branch.
> 
> Before:
> $ sudo perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
> 4565048704,,instructions,64114578096,100.00,1.34,insn per cycle,,
> 3396325133,,cycles,64146628546,100.00,,
> 
> After:
> $ sudo ./tools/perf/perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
> 6721924,,instructions,24026790339,100.00,0.22,insn per cycle
> ,,,,,0.00,stalled cycles per insn
> 30939953,,cycles,24025512526,100.00,,
> 
> Cc: Andi Kleen <ak@linux.intel.com>
> Cc: Jiri Olsa <jolsa@kernel.org>
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>

Acked-by: Jiri Olsa <jolsa@kernel.org>

thanks,
jirka

> ---
>  tools/perf/util/stat-shadow.c | 3 ++-
>  1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
> index 83d8094be4fe..5c5e012e99c4 100644
> --- a/tools/perf/util/stat-shadow.c
> +++ b/tools/perf/util/stat-shadow.c
> @@ -800,7 +800,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
>  					"stalled cycles per insn",
>  					ratio);
>  		} else if (have_frontend_stalled) {
> -			print_metric(config, ctxp, NULL, NULL,
> +			out->new_line(config, ctxp);
> +			print_metric(config, ctxp, NULL, "%7.2f ",
>  				     "stalled cycles per insn", 0);
>  		}
>  	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
> -- 
> 2.21.0
> 

Re: [Patch] perf stat: always separate stalled cycles per insn

[Cong Wang]

On Sun, May 19, 2019 at 11:59 PM Jiri Olsa <jolsa@redhat.com> wrote:
>
> On Fri, May 17, 2019 at 03:10:39PM -0700, Cong Wang wrote:
> > The "stalled cycles per insn" is appended to "instructions" when
> > the CPU has this hardware counter directly. We should always make it
> > a separate line, which also aligns to the output when we hit the
> > "if (total && avg)" branch.
> >
> > Before:
> > $ sudo perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
> > 4565048704,,instructions,64114578096,100.00,1.34,insn per cycle,,
> > 3396325133,,cycles,64146628546,100.00,,
> >
> > After:
> > $ sudo ./tools/perf/perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
> > 6721924,,instructions,24026790339,100.00,0.22,insn per cycle
> > ,,,,,0.00,stalled cycles per insn
> > 30939953,,cycles,24025512526,100.00,,
> >
> > Cc: Andi Kleen <ak@linux.intel.com>
> > Cc: Jiri Olsa <jolsa@kernel.org>
> > Cc: Ingo Molnar <mingo@redhat.com>
> > Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> > Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
>
> Acked-by: Jiri Olsa <jolsa@kernel.org>

Thanks for reviewing it. Is there anyone takes this patch?

Re: [Patch] perf stat: always separate stalled cycles per insn

[Arnaldo Carvalho de Melo]

Em Tue, May 28, 2019 at 11:21:38AM -0700, Cong Wang escreveu:
> On Sun, May 19, 2019 at 11:59 PM Jiri Olsa <jolsa@redhat.com> wrote:
> >
> > On Fri, May 17, 2019 at 03:10:39PM -0700, Cong Wang wrote:
> > > The "stalled cycles per insn" is appended to "instructions" when
> > > the CPU has this hardware counter directly. We should always make it
> > > a separate line, which also aligns to the output when we hit the
> > > "if (total && avg)" branch.
> > >
> > > Before:
> > > $ sudo perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
> > > 4565048704,,instructions,64114578096,100.00,1.34,insn per cycle,,
> > > 3396325133,,cycles,64146628546,100.00,,
> > >
> > > After:
> > > $ sudo ./tools/perf/perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
> > > 6721924,,instructions,24026790339,100.00,0.22,insn per cycle
> > > ,,,,,0.00,stalled cycles per insn
> > > 30939953,,cycles,24025512526,100.00,,
> > >
> > > Cc: Andi Kleen <ak@linux.intel.com>
> > > Cc: Jiri Olsa <jolsa@kernel.org>
> > > Cc: Ingo Molnar <mingo@redhat.com>
> > > Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> > > Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
> >
> > Acked-by: Jiri Olsa <jolsa@kernel.org>
> 
> Thanks for reviewing it. Is there anyone takes this patch?

Enough time, acked already, picking it.

- Arnaldo

Re: [Patch] perf stat: always separate stalled cycles per insn

[Cong Wang]

Hi, Arnaldo

On Tue, May 28, 2019 at 12:11 PM Arnaldo Carvalho de Melo
<arnaldo.melo@gmail.com> wrote:
>
> Em Tue, May 28, 2019 at 11:21:38AM -0700, Cong Wang escreveu:
> > Thanks for reviewing it. Is there anyone takes this patch?
>
> Enough time, acked already, picking it.

Where is this patch landed? I don't see it in Linus tree. I guess you
are still holding it somewhere?

Thanks.

Re: [Patch] perf stat: always separate stalled cycles per insn

[Arnaldo Carvalho de Melo]

Em Tue, Jul 16, 2019 at 12:24:41PM -0700, Cong Wang escreveu:
> Hi, Arnaldo
> 
> On Tue, May 28, 2019 at 12:11 PM Arnaldo Carvalho de Melo
> <arnaldo.melo@gmail.com> wrote:
> >
> > Em Tue, May 28, 2019 at 11:21:38AM -0700, Cong Wang escreveu:
> > > Thanks for reviewing it. Is there anyone takes this patch?
> >
> > Enough time, acked already, picking it.
> 
> Where is this patch landed? I don't see it in Linus tree. I guess you
> are still holding it somewhere?

Got it now, will push upstream in the next batch, sorry for the delay.

- Arnaldo

Re: [Patch] perf stat: always separate stalled cycles per insn

[Andi Kleen]

On Tue, Jul 16, 2019 at 05:43:24PM -0300, Arnaldo Carvalho de Melo wrote:
> Em Tue, Jul 16, 2019 at 12:24:41PM -0700, Cong Wang escreveu:
> > Hi, Arnaldo
> > 
> > On Tue, May 28, 2019 at 12:11 PM Arnaldo Carvalho de Melo
> > <arnaldo.melo@gmail.com> wrote:
> > >
> > > Em Tue, May 28, 2019 at 11:21:38AM -0700, Cong Wang escreveu:
> > > > Thanks for reviewing it. Is there anyone takes this patch?
> > >
> > > Enough time, acked already, picking it.
> > 
> > Where is this patch landed? I don't see it in Linus tree. I guess you
> > are still holding it somewhere?
> 
> Got it now, will push upstream in the next batch, sorry for the delay.

FWIW i would prefer to deprecate the stalled cycles metrics. They 
are confusing and misleading. --topdown FrontendBound is a much
better metric.

-Andi

[tip:perf/urgent] perf stat: Always separate stalled cycles per insn

[tip-bot for Cong Wang]

Commit-ID:  146540fb545b8464ba1be298e3392daca0d183a2
Gitweb:     https://git.kernel.org/tip/146540fb545b8464ba1be298e3392daca0d183a2
Author:     Cong Wang <xiyou.wangcong@gmail.com>
AuthorDate: Fri, 17 May 2019 15:10:39 -0700
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 23 Jul 2019 09:03:46 -0300

perf stat: Always separate stalled cycles per insn

The "stalled cycles per insn" is appended to "instructions" when the CPU
has this hardware counter directly. We should always make it a separate
line, which also aligns to the output when we hit the "if (total &&
avg)" branch.

Before:

  $ sudo perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
  4565048704,,instructions,64114578096,100.00,1.34,insn per cycle,,
  3396325133,,cycles,64146628546,100.00,,

After:

  $ sudo ./tools/perf/perf stat --all-cpus --field-separator , --log-fd 1 -einstructions,cycles -- sleep 1
  6721924,,instructions,24026790339,100.00,0.22,insn per cycle
  ,,,,,0.00,stalled cycles per insn
  30939953,,cycles,24025512526,100.00,,

Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/20190517221039.8975-1-xiyou.wangcong@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/stat-shadow.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 656065af4971..accb1bf1cfd8 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -819,7 +819,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					"stalled cycles per insn",
 					ratio);
 		} else if (have_frontend_stalled) {
-			print_metric(config, ctxp, NULL, NULL,
+			out->new_line(config, ctxp);
+			print_metric(config, ctxp, NULL, "%7.2f ",
 				     "stalled cycles per insn", 0);
 		}
 	} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {