perf, tools: Refactor and support interval and CSV metrics v2
[v2: Addressed (near) all review feedback. No manpage updates so far.
Add support for --per-core metrics. Various cleanups.]
Currently perf stat does not support printing computed metrics for interval (-I xxx) or CSV (-x,) mode. For example IPC or TSX metrics over time are quite useful to know.
This patch implements them. The main obstacle was that the
metrics printing was all open coded all over the metrics computation code. The second patch refactors the metrics printing to work through call backs that can be more easily changed. This also cleans up the metrics printing significantly. The indentation is now handled through printf, no more need to manually count spaces.
Then based on that it implements metrics printing for CSV and interval mode.
Example output:
% perf stat -I1000 -a sleep 1
# time counts unit events metric multiplex
1.001301370 12020.049593 task-clock (msec) (100.00%)
1.001301370 3,952 context-switches # 0.329 K/sec (100.00%)
1.001301370 69 cpu-migrations # 0.006 K/sec (100.00%)
1.001301370 76 page-faults # 0.006 K/sec
1.001301370 386,582,789 cycles # 0.032 GHz (100.00%)
1.001301370 716,441,544 stalled-cycles-frontend # 185.33% frontend cycles idle (100.00%)
1.001301370 <not supported> stalled-cycles-backend
1.001301370 101,751,678 instructions # 0.26 insn per cycle
1.001301370 # 7.04 stalled cycles per insn (100.00%)
1.001301370 20,914,692 branches # 1.740 M/sec (100.00%)
1.001301370 1,943,630 branch-misses # 9.29% of all branches CSV mode
% perf stat -x, -I1000 -a sleep 1
1.000852081,12016.143006,,task-clock
1.000852081,4457,,context-switches,12015168277,100.00,0.371,K/sec
1.000852081,50,,cpu-migrations,12014024424,100.00,0.004,K/sec
1.000852081,76,,page-faults,12013076716,100.00,0.006,K/sec
1.000852081,515854373,,cycles,12011235336,100.00,0.043,GHz
1.000852081,1030742150,,stalled-cycles-frontend,12010984057,100.00,199.81,frontend cycles idle
1.000852081,<not supported>,,stalled-cycles-backend,0,100.00
1.000852081,116782495,,instructions,12011130729,100.00,0.23,insn per cycle
1.000852081,,,,12011130729,100.00,8.83,stalled cycles per insn
1.000852081,23748237,,branches,12010745125,100.00,1.976,M/sec
1.000852081,1976560,,branch-misses,12010501884,100.00,8.32,of all branchesAvailable ingit://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-misc perf/stat-metrics-2
PATCH 1/8 perf, tools: Remove trail argument to color vsprintf
From: Jiri Olsa <[email protected]>
Seems like it's always '\n' through color_fprintf_ln, which is not used at all, removing.. ;-)
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/util/color.c | 16 ++-------------- tools/perf/util/color.h | 1 - 2 files changed, 2 insertions(+), 15 deletions(-)
tools/perf/util/color.c +2 -14
@@ -68,7 +68,7 @@ static int __color_vsnprintf(char *bf, size_t size, const char *color, }static int __color_vfprintf (FILE *fp,const char *color,const char *fmt, -va_list args,const char *trail) +va_list args) {int r =0 ;
@@ -87,8 +87,6 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, r +=vfprintf (fp, fmt, args);if (perf_use_color_default && *color) r +=fprintf (fp,"%s" ,PERF_COLOR_RESET ); -if (trail) - r +=fprintf (fp,"%s" , trail);return r; }
@@ -100,7 +98,7 @@ int color_vsnprintf(char *bf, size_t size, const char *color,int color_vfprintf (FILE *fp,const char *color,const char *fmt,va_list args) { -return __color_vfprintf (fp, color, fmt, args,NULL ); +return __color_vfprintf (fp, color, fmt, args); } int color_snprintf(char *bf, size_t size, const char *color,
@@ -126,16 +124,6 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...)return r; } -int color_fprintf_ln (FILE *fp,const char *color,const char *fmt, ...) -{ -va_list args; -int r; -va_start (args, fmt); - r =__color_vfprintf (fp, color, fmt, args,"\n" ); -va_end (args); -return r; -} -/* * This function splits the buffer by newlines and colors the lines individually. *
tools/perf/util/color.h +0 -1
@@ -35,7 +35,6 @@ int color_vsnprintf(char *bf, size_t size, const char *color,int color_vfprintf (FILE *fp,const char *color,const char *fmt,va_list args);int color_fprintf (FILE *fp,const char *color,const char *fmt, ...);int color_snprintf (char *bf,size_t size,const char *color,const char *fmt, ...); -int color_fprintf_ln (FILE *fp,const char *color,const char *fmt, ...);int color_fwrite_lines (FILE *fp,const char *color,size_t count,const char *buf);int value_color_snprintf (char *bf,size_t size,const char *fmt,double value);int percent_color_snprintf (char *bf,size_t size,const char *fmt, ...);
Signature · 1 line
2.4.3
tip-bot for Jiri Olsa
merge bot[tip:perf/core] perf tools: Remove trail argument to color vsprintf
perf tools: Remove trail argument to color vsprintf
Commit-ID: 8011de7ab3b10c5352f3f0708f517de2722b0957 Gitweb: http://git.kernel.org/tip/8011de7ab3b10c5352f3f0708f517de2722b0957 Author: Jiri Olsa <[email protected]> AuthorDate: Mon, 3 Aug 2015 17:50:01 -0700 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitDate: Wed, 5 Aug 2015 16:44:02 -0300
perf tools: Remove trail argument to color vsprintf
Seems like it's always '\n' through color_fprintf_ln, which is not used at all, removing.. ;-)
Signed-off-by Jiri Olsa <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Stephane Eranian <[email protected]>
Signed-off-by Andi Kleen <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/color.c | 16 ++-------------- tools/perf/util/color.h | 1 - 2 files changed, 2 insertions(+), 15 deletions(-)
tools/perf/util/color.c +2 -14
@@ -68,7 +68,7 @@ static int __color_vsnprintf(char *bf, size_t size, const char *color, }static int __color_vfprintf (FILE *fp,const char *color,const char *fmt, -va_list args,const char *trail) +va_list args) {int r =0 ;
@@ -87,8 +87,6 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, r +=vfprintf (fp, fmt, args);if (perf_use_color_default && *color) r +=fprintf (fp,"%s" ,PERF_COLOR_RESET ); -if (trail) - r +=fprintf (fp,"%s" , trail);return r; }
@@ -100,7 +98,7 @@ int color_vsnprintf(char *bf, size_t size, const char *color,int color_vfprintf (FILE *fp,const char *color,const char *fmt,va_list args) { -return __color_vfprintf (fp, color, fmt, args,NULL ); +return __color_vfprintf (fp, color, fmt, args); } int color_snprintf(char *bf, size_t size, const char *color,
@@ -126,16 +124,6 @@ int color_fprintf(FILE *fp, const char *color, const char *fmt, ...)return r; } -int color_fprintf_ln (FILE *fp,const char *color,const char *fmt, ...) -{ -va_list args; -int r; -va_start (args, fmt); - r =__color_vfprintf (fp, color, fmt, args,"\n" ); -va_end (args); -return r; -} -/* * This function splits the buffer by newlines and colors the lines individually. *
tools/perf/util/color.h +0 -1
@@ -35,7 +35,6 @@ int color_vsnprintf(char *bf, size_t size, const char *color,int color_vfprintf (FILE *fp,const char *color,const char *fmt,va_list args);int color_fprintf (FILE *fp,const char *color,const char *fmt, ...);int color_snprintf (char *bf,size_t size,const char *color,const char *fmt, ...); -int color_fprintf_ln (FILE *fp,const char *color,const char *fmt, ...);int color_fwrite_lines (FILE *fp,const char *color,size_t count,const char *buf);int value_color_snprintf (char *bf,size_t size,const char *fmt,double value);int percent_color_snprintf (char *bf,size_t size,const char *fmt, ...);
PATCH 2/8 perf, tools: Do not include escape sequences in color_vfprintf return
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
color_vprintf was including the length of the invisible escape sequences in its return argument. Don't include them to make the return value usable for indentation calculations.
v2: Add comment, rebase
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/util/color.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
tools/perf/util/color.c +3 -2
@@ -67,6 +67,7 @@ static int __color_vsnprintf(char *bf, size_t size, const char *color,return r; } +/* Colors are not included in return value */ static int __color_vfprintf (FILE *fp,const char *color,const char *fmt,va_list args) {
@@ -83,10 +84,10 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, }if (perf_use_color_default && *color) - r +=fprintf (fp,"%s" , color); +fprintf (fp,"%s" , color); r +=vfprintf (fp, fmt, args);if (perf_use_color_default && *color) - r +=fprintf (fp,"%s" ,PERF_COLOR_RESET ); +fprintf (fp,"%s" ,PERF_COLOR_RESET );return r; }
Signature · 1 line
2.4.3
tip-bot for Andi Kleen
merge bot[tip:perf/core] perf tools: Do not include escape sequences in color_vfprintf return
perf tools: Do not include escape sequences in color_vfprintf return
Commit-ID: b7a001d2067830a98e65d1bbbf99a6d435d70616 Gitweb: http://git.kernel.org/tip/b7a001d2067830a98e65d1bbbf99a6d435d70616 Author: Andi Kleen <[email protected]> AuthorDate: Mon, 3 Aug 2015 17:50:02 -0700 Committer: Arnaldo Carvalho de Melo <[email protected]> CommitDate: Wed, 5 Aug 2015 16:46:06 -0300
perf tools: Do not include escape sequences in color_vfprintf return
color_vprintf was including the length of the invisible escape sequences in its return argument. Don't include them to make the return value usable for indentation calculations.
v2: Add comment, rebase
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Stephane Eranian <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/color.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
tools/perf/util/color.c +3 -2
@@ -67,6 +67,7 @@ static int __color_vsnprintf(char *bf, size_t size, const char *color,return r; } +/* Colors are not included in return value */ static int __color_vfprintf (FILE *fp,const char *color,const char *fmt,va_list args) {
@@ -83,10 +84,10 @@ static int __color_vfprintf(FILE *fp, const char *color, const char *fmt, }if (perf_use_color_default && *color) - r +=fprintf (fp,"%s" , color); +fprintf (fp,"%s" , color); r +=vfprintf (fp, fmt, args);if (perf_use_color_default && *color) - r +=fprintf (fp,"%s" ,PERF_COLOR_RESET ); +fprintf (fp,"%s" ,PERF_COLOR_RESET );return r; }
PATCH 3/8 perf, tools, stat: Move sw clock metrics printout to stat-shadow
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
The sw clock metrics printing was missed in the earlier move to stat-shadow of all the other metric printouts. Move it too.
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/builtin-stat.c | 9 --------- tools/perf/util/stat-shadow.c | 4 ++++ 2 files changed, 4 insertions(+), 9 deletions(-)
tools/perf/builtin-stat.c +0 -9
@@ -642,15 +642,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)if (evsel->cgrp)fprintf (output,"%s%s" , csv_sep, evsel->cgrp->name); - -if (csv_output || interval) -return ; - -if (perf_evsel__match (evsel,SOFTWARE ,SW_TASK_CLOCK )) -fprintf (output," # %8.3f CPUs utilized " , - avg /avg_stats (&walltime_nsecs_stats)); -else -fprintf (output," " ); }static void abs_printout (int id,int nr,struct perf_evsel *evsel,double avg)
tools/perf/util/stat-shadow.c +4 -0
@@ -415,6 +415,10 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, ratio = total / avg;fprintf (out," # %8.0f cycles / elision " , ratio); + }else if (perf_evsel__match (evsel,SOFTWARE ,SW_TASK_CLOCK ) && + (ratio =avg_stats (&walltime_nsecs_stats)) !=0 ) { +fprintf (output," # %8.3f CPUs utilized " , + avg / ratio); }else if (runtime_nsecs_stats[cpu].n !=0 ) {char unit ='M' ;
Signature · 1 line
2.4.3
PATCH 4/8 perf, tools, stat: Abstract stat metrics printing
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Abstract the printing of shadow metrics. Instead of every metric calling fprintf directly and taking care of indentation, use two call backs: one to print metrics and another to start a new line.
This will allow adding metrics to CSV mode and also using them for other purposes.
The computation of padding is now done in the central callback, instead of every metric doing it manually. This makes it easier to add new metrics.
v2: Refactor functions, printout now does more. Move shadow printing.
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/builtin-stat.c | 96 +++++++++++++++++-------- tools/perf/util/stat-shadow.c | 158 ++++++++++++++++++++++-------------------- tools/perf/util/stat.h | 10 ++- 3 files changed, 158 insertions(+), 106 deletions(-)
tools/perf/builtin-stat.c +68 -28
@@ -617,6 +617,47 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr) } } +struct outstate { +FILE *fh; +}; + +#define BASE_INDENT 41 +#define AGGR_INDENT 8 +#define METRIC_LEN 35 +#define NA_INDENT 16 + +static void new_line_no_aggr_std (void *ctx) +{ +struct outstate *os = ctx; +fprintf (os->fh,"\n%*s" ,BASE_INDENT +NA_INDENT ,"" ); +} + +static void new_line_std (void *ctx) +{ +struct outstate *os = ctx; +fprintf (os->fh,"\n%-*s" ,BASE_INDENT +AGGR_INDENT ,"" ); +} + +static void print_metric_std (void *ctx,const char *color,const char *fmt, +const char *unit,double val) +{ +struct outstate *os = ctx; +FILE *out = os->fh; +int n; + +if (unit ==NULL ) { +fprintf (out,"%-*s" ,METRIC_LEN ,"" ); +return ; + } + + n =fprintf (out," # " ); +if (color) + n +=color_fprintf (out, color, fmt, val); +else + n +=fprintf (out, fmt, val); +fprintf (out," %-*s" ,METRIC_LEN - n -1 , unit); +} +static void nsec_printout (int id,int nr,struct perf_evsel *evsel,double avg) {double msecs = avg /1e6 ;
@@ -648,7 +689,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) {double sc = evsel->scale;const char *fmt; -int cpu =cpu_map__id_to_cpu (id);if (csv_output) { fmt = sc !=1.0 ?"%.2f%s" :"%.0f%s" ;
@@ -661,9 +701,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)aggr_printout (evsel, id, nr); -if (aggr_mode ==AGGR_GLOBAL ) - cpu =0 ; -fprintf (output, fmt, avg, csv_sep);if (evsel->unit)
@@ -676,10 +713,30 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)if (evsel->cgrp)fprintf (output,"%s%s" , csv_sep, evsel->cgrp->name); -if (csv_output || interval) -return ; +} -perf_stat__print_shadow_stats (output, evsel, avg, cpu, aggr_mode); +static void printout (int id,int nr,struct perf_evsel *counter,double uval) +{ +struct outstate os = { .fh = output }; +print_metric_t pm = print_metric_std; +void (*nl)(void *); + +if (aggr_mode ==AGGR_NONE ) + nl = new_line_no_aggr_std; +else + nl = new_line_std; + +if (nsec_counter (counter)) +nsec_printout (id, nr, counter, uval); +else +abs_printout (id, nr, counter, uval); + +perf_stat__print_shadow_stats (counter, uval, + aggr_mode ==AGGR_GLOBAL ?0 : +cpu_map__id_to_cpu (id), + pm, + nl, + &os); }static void print_aggr (char *prefix)
@@ -735,12 +792,7 @@ static void print_aggr(char *prefix)continue ; } uval = val * counter->scale; - -if (nsec_counter (counter)) -nsec_printout (id, nr, counter, uval); -else -abs_printout (id, nr, counter, uval); - +printout (id, nr, counter, uval);if (!csv_output)print_noise (counter,1.0 );
@@ -770,11 +822,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)fprintf (output,"%s" , prefix); uval = val * counter->scale; - -if (nsec_counter (counter)) -nsec_printout (thread,0 , counter, uval); -else -abs_printout (thread,0 , counter, uval); +printout (thread,0 , counter, uval);if (!csv_output)print_noise (counter,1.0 );
@@ -823,11 +871,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) } uval = avg * counter->scale; - -if (nsec_counter (counter)) -nsec_printout (-1 ,0 , counter, uval); -else -abs_printout (-1 ,0 , counter, uval); +printout (-1 ,0 , counter, uval);print_noise (counter, avg);
@@ -879,11 +923,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix) } uval = val * counter->scale; - -if (nsec_counter (counter)) -nsec_printout (cpu,0 , counter, uval); -else -abs_printout (cpu,0 , counter, uval); +printout (cpu,0 , counter, uval);if (!csv_output)print_noise (counter,1.0 );
tools/perf/util/stat-shadow.c +82 -76
330 lines not on this page · raw message
tools/perf/util/stat.h +8 -2
@@ -83,11 +83,17 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel);extern struct stats walltime_nsecs_stats; +typedef void (*print_metric_t )(void *ctx,const char *color,const char *unit, +const char *fmt,double val); +void perf_stat__reset_shadow_stats (void );void perf_stat__update_shadow_stats (struct perf_evsel *counter,u64 *count,int cpu); -void perf_stat__print_shadow_stats (FILE *out,struct perf_evsel *evsel, -double avg,int cpu,enum aggr_mode aggr); +void perf_stat__print_shadow_stats (struct perf_evsel *evsel, +double avg,int cpu, +print_metric_t print_metric, +void (*new_line)(void *ctx), +void *ctx);struct perf_counts *perf_counts__new (int ncpus,int nthreads);void perf_counts__delete (struct perf_counts *counts);
Signature · 1 line
2.4.3
PATCH 5/8 perf, tools, stat: Add support for metrics in interval mode
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Now that we can modify the metrics printout functions easily, it's straight forward to support metric printing for interval mode. All that is needed is to print the time stamp on every new line. Pass the prefix into the context and print it out.
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/builtin-stat.c | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-)
tools/perf/builtin-stat.c +15 -9
@@ -619,6 +619,9 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr)struct outstate {FILE *fh; +const char *prefix; +int nfields; +u64 run, ena; };#define BASE_INDENT 41
@@ -629,13 +632,13 @@ struct outstate {static void new_line_no_aggr_std (void *ctx) {struct outstate *os = ctx; -fprintf (os->fh,"\n%*s" ,BASE_INDENT +NA_INDENT ,"" ); +fprintf (os->fh,"\n%s%-*s" , os->prefix,BASE_INDENT +NA_INDENT ,"" ); }static void new_line_std (void *ctx) {struct outstate *os = ctx; -fprintf (os->fh,"\n%-*s" ,BASE_INDENT +AGGR_INDENT ,"" ); +fprintf (os->fh,"\n%s%-*s" , os->prefix,BASE_INDENT +AGGR_INDENT ,"" ); } static void print_metric_std(void *ctx, const char *color, const char *fmt,
@@ -712,12 +715,15 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)if (evsel->cgrp)fprintf (output,"%s%s" , csv_sep, evsel->cgrp->name); - } -static void printout (int id,int nr,struct perf_evsel *counter,double uval) +static void printout (int id,int nr,struct perf_evsel *counter,double uval, +char *prefix) { -struct outstate os = { .fh = output }; +struct outstate os = { + .fh = output, + .prefix = prefix ? prefix :"" + };print_metric_t pm = print_metric_std;void (*nl)(void *);
@@ -792,7 +798,7 @@ static void print_aggr(char *prefix)continue ; } uval = val * counter->scale; -printout (id, nr, counter, uval); +printout (id, nr, counter, uval, prefix);if (!csv_output)print_noise (counter,1.0 );
@@ -822,7 +828,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)fprintf (output,"%s" , prefix); uval = val * counter->scale; -printout (thread,0 , counter, uval); +printout (thread,0 , counter, uval, prefix);if (!csv_output)print_noise (counter,1.0 );
@@ -871,7 +877,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) } uval = avg * counter->scale; -printout (-1 ,0 , counter, uval); +printout (-1 ,0 , counter, uval, prefix);print_noise (counter, avg);
@@ -923,7 +929,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix) } uval = val * counter->scale; -printout (cpu,0 , counter, uval); +printout (cpu,0 , counter, uval, prefix);if (!csv_output)print_noise (counter,1.0 );
Signature · 1 line
2.4.3
PATCH 6/8 perf, tools, stat: Move noise/running printing into printout
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Move the running/noise printing into printout to avoid duplicated code in the callers.
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/builtin-stat.c | 33 +++++++++++---------------------- 1 file changed, 11 insertions(+), 22 deletions(-)
tools/perf/builtin-stat.c +11 -22
@@ -718,7 +718,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) }static void printout (int id,int nr,struct perf_evsel *counter,double uval, -char *prefix) +char *prefix,u64 run,u64 ena,double noise) {struct outstate os = { .fh = output,
@@ -743,6 +743,12 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, pm, nl, &os); + +if (!csv_output) { +print_noise (counter, noise); +if (run != ena) +fprintf (output," (%.2f%%)" ,100.0 * run / ena); + } }static void print_aggr (char *prefix)
@@ -798,11 +804,7 @@ static void print_aggr(char *prefix)continue ; } uval = val * counter->scale; -printout (id, nr, counter, uval, prefix); -if (!csv_output) -print_noise (counter,1.0 ); - -print_running (run, ena); +printout (id, nr, counter, uval, prefix, run, ena,1.0 );fputc ('\n' , output); } }
@@ -828,12 +830,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix)fprintf (output,"%s" , prefix); uval = val * counter->scale; -printout (thread,0 , counter, uval, prefix); - -if (!csv_output) -print_noise (counter,1.0 ); - -print_running (run, ena); +printout (thread,0 , counter, uval, prefix, run, ena,1.0 );fputc ('\n' , output); } }
@@ -877,11 +874,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) } uval = avg * counter->scale; -printout (-1 ,0 , counter, uval, prefix); - -print_noise (counter, avg); - -print_running (avg_running, avg_enabled); +printout (-1 ,0 , counter, uval, prefix, avg_running, avg_enabled, avg);fprintf (output,"\n" ); }
@@ -929,11 +922,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix) } uval = val * counter->scale; -printout (cpu,0 , counter, uval, prefix); - -if (!csv_output) -print_noise (counter,1.0 ); -print_running (run, ena); +printout (cpu,0 , counter, uval, prefix, run, ena,1.0 );fputc ('\n' , output); }
Signature · 1 line
2.4.3
PATCH 7/8 perf, tools, stat: Implement CSV metrics output
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Now support CSV output for metrics. With the new output callbacks this is relatively straight forward by creating new callbacks.
The new line callback needs to know the number of fields to skip them correctly
v2: Split out function argument changes
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/builtin-stat.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+)
tools/perf/builtin-stat.c +62 -0
@@ -661,6 +661,49 @@ static void print_metric_std(void *ctx, const char *color, const char *fmt,fprintf (out," %-*s" ,METRIC_LEN - n -1 , unit); } +static void new_line_csv (void *ctx) +{ +struct outstate *os = ctx; +int i; + +fputc ('\n' , os->fh); +if (os->prefix) +fprintf (os->fh,"%s%s" , os->prefix, csv_sep); +for (i =0 ; i < os->nfields; i++) +fputs (csv_sep, os->fh); +} + +static void print_metric_csv (void *ctx, +const char *color__maybe_unused , +const char *fmt,const char *unit,double val) +{ +struct outstate *os = ctx; +FILE *out = os->fh; +char buf[64 ], *vals, *ends; + +if (unit ==NULL ) { +fprintf (out,"%s%s%s%s" , csv_sep, csv_sep, csv_sep, csv_sep); +return ; + } +fprintf (out,"%s%" PRIu64"%s%.2f%s" , + csv_sep, + os->run, + csv_sep, + os->ena ?100.0 * os->run / os->ena :100.0 , + csv_sep); +snprintf (buf,sizeof (buf), fmt, val); + vals = buf; +while (isspace (*vals)) + vals++; + ends = vals; +while (isdigit (*ends) || *ends =='.' ) + ends++; + *ends =0 ; +while (isspace (*unit)) + unit++; +fprintf (out,"%s%s%s" , vals, csv_sep, unit); +} +static void nsec_printout (int id,int nr,struct perf_evsel *evsel,double avg) {double msecs = avg /1e6 ;
@@ -732,6 +775,25 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,else nl = new_line_std; +if (csv_output) { +static int aggr_fields[] = { + [AGGR_GLOBAL ] =0 , + [AGGR_THREAD ] =1 , + [AGGR_NONE ] =1 , + [AGGR_SOCKET ] =2 , + [AGGR_CORE ] =2 , + }; + + pm = print_metric_csv; + nl = new_line_csv; + os.nfields =1 ; + os.nfields += aggr_fields[aggr_mode]; +if (counter->cgrp) + os.nfields++; + os.run = run; + os.ena = ena; + } +if (nsec_counter (counter))nsec_printout (id, nr, counter, uval);else
Signature · 1 line
2.4.3
PATCH 8/8 perf, tools: Support metrics in --per-core/socket mode
In reply to Andi KleenFrom: Andi Kleen <[email protected]>
Enable metrics printing in --per-core / --per-socket mode. We need to save the shadow metrics in a unique place. Always use the first CPU in the aggregation. Then use the same CPU to retrieve the shadow value later.
Example output:
% perf stat --per-core -a ./BC1s
Performance counter stats for 'system wide':
S0-C0 2 2966.020381 task-clock (msec) # 2.004 CPUs utilized (100.00%) S0-C0 2 49 context-switches # 0.017 K/sec (100.00%) S0-C0 2 4 cpu-migrations # 0.001 K/sec (100.00%) S0-C0 2 467 page-faults # 0.157 K/sec S0-C0 2 4,599,061,773 cycles # 1.551 GHz (100.00%) S0-C0 2 9,755,886,883 instructions # 2.12 insn per cycle (100.00%) S0-C0 2 1,906,272,125 branches # 642.704 M/sec (100.00%) S0-C0 2 81,180,867 branch-misses # 4.26% of all branches S0-C1 2 2965.995373 task-clock (msec) # 2.003 CPUs utilized (100.00%) S0-C1 2 62 context-switches # 0.021 K/sec (100.00%) S0-C1 2 8 cpu-migrations # 0.003 K/sec (100.00%) S0-C1 2 281 page-faults # 0.095 K/sec S0-C1 2 6,347,290 cycles # 0.002 GHz (100.00%) S0-C1 2 4,654,156 instructions # 0.73 insn per cycle (100.00%) S0-C1 2 947,121 branches # 0.319 M/sec (100.00%) S0-C1 2 37,322 branch-misses # 3.94% of all branches
1.480409747 seconds time elapsed
Signed-off-by Andi Kleen <[email protected]>
--- tools/perf/builtin-stat.c | 45 +++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 43 insertions(+), 2 deletions(-)
tools/perf/builtin-stat.c +43 -2
@@ -731,6 +731,22 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)fprintf (output,"%s%s" , csv_sep, evsel->cgrp->name); } +static int first_shadow_cpu (struct perf_evsel *evsel,int id) +{ +int i; + +if (aggr_get_id ==NULL ) +return 0 ; + +for (i =0 ; i <perf_evsel__nr_cpus (evsel); i++) { +int cpu2 =perf_evsel__cpus (evsel)->map[i]; + +if (aggr_get_id (evsel_list->cpus, cpu2) == id) +return cpu2; + } +return 0 ; +} +static void abs_printout (int id,int nr,struct perf_evsel *evsel,double avg) {double sc = evsel->scale;
@@ -800,8 +816,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,abs_printout (id, nr, counter, uval);perf_stat__print_shadow_stats (counter, uval, - aggr_mode ==AGGR_GLOBAL ?0 : -cpu_map__id_to_cpu (id), +first_shadow_cpu (counter, id), pm, nl, &os);
@@ -813,6 +828,30 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval, } } +static void aggr_update_shadow (void ) +{ +int cpu, cpu2, s2, id, s; +u64 val; +struct perf_evsel *counter; + +for (s =0 ; s < aggr_map->nr; s++) { + id = aggr_map->map[s]; +evlist__for_each (evsel_list, counter) { + val =0 ; +for (cpu =0 ; cpu <perf_evsel__nr_cpus (counter); cpu++) { + cpu2 =perf_evsel__cpus (counter)->map[cpu]; + s2 =aggr_get_id (evsel_list->cpus, cpu2); +if (s2 != id) +continue ; + val +=perf_counts (counter->counts, cpu,0 )->val; + } + val =scale_val (counter, val); +perf_stat__update_shadow_stats (counter, &val, +first_shadow_cpu (counter, id)); + } + } +} +static void print_aggr (char *prefix) {struct perf_evsel *counter;
@@ -823,6 +862,8 @@ static void print_aggr(char *prefix)if (!(aggr_map || aggr_get_id))return ; +aggr_update_shadow (); +for (s =0 ; s < aggr_map->nr; s++) { id = aggr_map->map[s];evlist__for_each (evsel_list, counter) {
Signature · 1 line
2.4.3
Quoted 46 lines · Andi Kleen
[v2: Addressed (near) all review feedback. No manpage updates so far.
Add support for --per-core metrics. Various cleanups.]Currently perf stat does not support printing computed metrics for interval (-I xxx) or CSV (-x,) mode. For example IPC or TSX metrics over time are quite useful to know.
This patch implements them. The main obstacle was that the
metrics printing was all open coded all over the metrics computation code. The second patch refactors the metrics printing to work through call backs that can be more easily changed. This also cleans up the metrics printing significantly. The indentation is now handled through printf, no more need to manually count spaces.Then based on that it implements metrics printing for CSV and interval mode.
Example output:
% perf stat -I1000 -a sleep 1
# time counts unit events metric multiplex 1.001301370 12020.049593 task-clock (msec) (100.00%) 1.001301370 3,952 context-switches # 0.329 K/sec (100.00%) 1.001301370 69 cpu-migrations # 0.006 K/sec (100.00%) 1.001301370 76 page-faults # 0.006 K/sec 1.001301370 386,582,789 cycles # 0.032 GHz (100.00%) 1.001301370 716,441,544 stalled-cycles-frontend # 185.33% frontend cycles idle (100.00%) 1.001301370 <not supported> stalled-cycles-backend 1.001301370 101,751,678 instructions # 0.26 insn per cycle 1.001301370 # 7.04 stalled cycles per insn (100.00%) 1.001301370 20,914,692 branches # 1.740 M/sec (100.00%) 1.001301370 1,943,630 branch-misses # 9.29% of all branchesCSV mode
% perf stat -x, -I1000 -a sleep 1
1.000852081,12016.143006,,task-clock 1.000852081,4457,,context-switches,12015168277,100.00,0.371,K/sec 1.000852081,50,,cpu-migrations,12014024424,100.00,0.004,K/sec 1.000852081,76,,page-faults,12013076716,100.00,0.006,K/sec 1.000852081,515854373,,cycles,12011235336,100.00,0.043,GHz 1.000852081,1030742150,,stalled-cycles-frontend,12010984057,100.00,199.81,frontend cycles idle 1.000852081,<not supported>,,stalled-cycles-backend,0,100.00 1.000852081,116782495,,instructions,12011130729,100.00,0.23,insn per cycle 1.000852081,,,,12011130729,100.00,8.83,stalled cycles per insn 1.000852081,23748237,,branches,12010745125,100.00,1.976,M/sec 1.000852081,1976560,,branch-misses,12010501884,100.00,8.32,of all branches
Quoted 2 lines
Available in
git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-miscperf/stat-metrics-2
got build failure:
CC builtin-stat.obuiltin-stat.c: In function ‘aggr_update_shadow’:
builtin-stat.c:848:10: error: implicit declaration of function ‘scale_val’ [-Werror=implicit-function-declaration]
val = scale_val(counter, val);
^
builtin-stat.c:848:4: error: nested extern declaration of ‘scale_val’ [-Werror=nested-externs]
val = scale_val(counter, val);
^cc1: all warnings being treated as errors /home/jolsa/kernel/linux-perf/tools/build/Makefile.build:68: recipe for target 'builtin-stat.o' failed make[2]: *** [builtin-stat.o] Error 1
Makefile.perf:296: recipe for target 'perf-in.o' failed
make[1]: *** [perf-in.o] Error 2
Makefile:68: recipe for target 'all' failed
make: *** [all] Error 2
jirka
Quoted 2 lines
^cc1: all warnings being treated as errors
Sorry mistake in refactoring. I also forgot to include one patch.
I'll fix this and repost (and also add the man page)
-Andi