perf, tools: Support spark lines in perf stat v2
PATCH 1/1 perf, tools: Support spark lines in perf stat v2
From: Andi Kleen <[email protected]>
perf stat -rX prints the stddev for multiple measurements. Just looking at the stddev for judging the quality of the data is a bit dangerous The simplest sanity check is to just look at a simple plot. This patchs add a sparkline to the end of the measurements to make it simple to judge the data.
The sparkline only uses UTF-8, so should be readable in all modern tools and terminals.
The sparkline is between the minimum and maximum of the data, so it's mainly a indicator of variance. To keep the code simple and make the output not too wide only the first 8 values are printed. If more values are there it adds '..'
The code is inspired by Zach Holman's spark shell script.
Example output (view in non-proportial font):
Performance counter stats for 'true' (10 runs):
0.175672 task-clock (msec) # 0.555 CPUs utilized ( +- 1.77% ) █▄▁▁▁▁▁▁..
0 context-switches # 0.000 K/sec
0 cpu-migrations # 0.000 K/sec
114 page-faults # 0.647 M/sec ( +- 0.14% ) ▁█▁▁████..
520,798 cycles # 2.965 GHz ( +- 1.75% ) █▄▁▁▁▁▁▁..
433,525 instructions # 0.83 insns per cycle ( +- 0.28% ) ▅▇▅▄▇█▁▆..
83,012 branches # 472.537 M/sec ( +- 0.31% ) ▅▇▆▄▇█▁▆..
3,157 branch-misses # 3.80% of all branches ( +- 2.55% ) ▇█▃▅▁▃▁▂..0.000316660 seconds time elapsed ( +- 1.78% ) █▅▁▁▁▁▁▁..
As you can see even in the most simple run there are quite interesting patterns. The time sparkline suggests it would be also useful to have an option to throw the first measurement away.
Known issues:
- Makes the perf stat output wider. Could be adjust by shrinking some white space. Not done so far.
- No output for -A/--per-socket/--per-core with -rX. This code is missing the basic noise detection code. Once it's added there sparklines could be shown too.
v2: Address review feedback. Use all_zero() and remove len. Remove test code. Rebased to perf/core
--- tools/perf/Makefile.perf | 1 + tools/perf/builtin-stat.c | 12 ++++++++++++ tools/perf/util/spark.c | 29 +++++++++++++++++++++++++++++ tools/perf/util/spark.h | 3 +++ tools/perf/util/stat.c | 33 +++++++++++++++++++++++++++++++++ tools/perf/util/stat.h | 10 ++++++++++ 6 files changed, 88 insertions(+) create mode 100644 tools/perf/util/spark.c create mode 100644 tools/perf/util/spark.h
tools/perf/Makefile.perf +1 -0
@@ -359,6 +359,7 @@ LIB_OBJS += $(OUTPUT)util/trace-event-scripting.o LIB_OBJS += $(OUTPUT)util/trace-event.o LIB_OBJS += $(OUTPUT)util/svghelper.o LIB_OBJS += $(OUTPUT)util/sort.o +LIB_OBJS += $(OUTPUT)util/spark.o LIB_OBJS += $(OUTPUT)util/hist.o LIB_OBJS += $(OUTPUT)util/probe-event.o LIB_OBJS += $(OUTPUT)util/util.o
tools/perf/builtin-stat.c +12 -0
@@ -1176,6 +1176,9 @@ static void print_aggr(char *prefix)if (run != ena)fprintf (output," (%.2f%%)" ,100.0 * run / ena); + +fputc (' ' , output); +print_stat_spark (output, counter->priv); }fputc ('\n' , output); }
@@ -1224,6 +1227,9 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix)print_noise (counter, avg); +fputc (' ' , output); +print_stat_spark (output, counter->priv); +if (csv_output) {fputc ('\n' , output);return ;
@@ -1295,6 +1301,9 @@ static void print_counter(struct perf_evsel *counter, char *prefix)if (run != ena)fprintf (output," (%.2f%%)" ,100.0 * run / ena); + +fputc (' ' , output); +print_stat_spark (output, counter->priv); }fputc ('\n' , output); }
@@ -1355,6 +1364,9 @@ static void print_stat(int argc, const char **argv)fprintf (output," " );print_noise_pct (stddev_stats (&walltime_nsecs_stats),avg_stats (&walltime_nsecs_stats)); + +fputc (' ' , output); +print_stat_spark (output, &walltime_nsecs_stats); }fprintf (output,"\n\n" ); }
tools/perf/util/spark.c new file +29 -0
@@ -0,0 +1,29 @@ +#include <stdio.h> +#include <limits.h> +#include "spark.h" + +#define NUM_SPARKS 8 +#define SPARK_SHIFT 8 + +/* Print spark lines on outf for numval values in val. */ +void print_spark (FILE *outf,unsigned long *val,int numval) +{ +static const char *ticks[NUM_SPARKS ] = { +"▁" ,"▂" ,"▃" ,"▄" ,"▅" ,"▆" ,"▇" ,"█" + }; +int i; +unsigned long min =LONG_MAX , max =0 , f; + +for (i =0 ; i < numval; i++) { +if (val[i] < min) + min = val[i]; +if (val[i] > max) + max = val[i]; + } + f = ((max - min) <<SPARK_SHIFT ) / (NUM_SPARKS -1 ); +if (f <1 ) + f =1 ; +for (i =0 ; i < numval; i++) { +fputs (ticks[((val[i] - min) <<SPARK_SHIFT ) / f], outf); + } +}
tools/perf/util/spark.h new file +3 -0
@@ -0,0 +1,3 @@ +#pragma once +void print_spark (FILE *outf,unsigned long *val,int numval); +
tools/perf/util/stat.c +33 -0
@@ -1,10 +1,16 @@#include <math.h> +#include <stdio.h> #include "stat.h" +#include "spark.h" void update_stats (struct stats *stats,u64 val) {double delta; +int n = stats->n; + +if (n <NUM_SPARK_VALS ) + stats->svals[n] = val; stats->n++; delta = val - stats->mean;
@@ -61,3 +67,30 @@ double rel_stddev_stats(double stddev, double avg)return pct; } + +static int all_zero (unsigned long *vals,int len) +{ +int i; + +for (i =0 ; i < len; i++) +if (vals[i] !=0 ) +return 0 ; +return 1 ; +} + +void print_stat_spark (FILE *f,struct stats *stat) +{ +int n = stat->n; + +if (n <=1 ) +return ; + +if (n >NUM_SPARK_VALS ) + n =NUM_SPARK_VALS ; +if (all_zero (stat->svals, n)) +return ; + +print_spark (f, stat->svals, n); +if (stat->n >NUM_SPARK_VALS ) +fputs (".." , f); +}
tools/perf/util/stat.h +10 -0
@@ -2,11 +2,15 @@#define __PERF_STATS_H#include <linux/types.h> +#include <stdio.h> + +#define NUM_SPARK_VALS 8/* support spark line on first N items */ struct stats {double n, mean, M2;u64 max, min; +unsigned long svals[NUM_SPARK_VALS ]; };void update_stats (struct stats *stats,u64 val);
@@ -14,12 +18,18 @@ double avg_stats(struct stats *stats);double stddev_stats (struct stats *stats);double rel_stddev_stats (double stddev,double avg); +void print_stat_spark (FILE *f,struct stats *stat); +static inline void init_stats (struct stats *stats) { +int i; + stats->n =0.0 ; stats->mean =0.0 ; stats->M2 =0.0 ; stats->min = (u64) -1 ; stats->max =0 ; +for (i =0 ; i <NUM_SPARK_VALS ; i++) + stats->svals[i] =0 ; }#endif
Signature · 1 line
1.9.0
Peter Zijlstra
maintainerQuoted 31 lines · Andi Kleen
From: Andi Kleen <[email protected]>
perf stat -rX prints the stddev for multiple measurements. Just looking at the stddev for judging the quality of the data is a bit dangerous The simplest sanity check is to just look at a simple plot. This patchs add a sparkline to the end of the measurements to make it simple to judge the data.
The sparkline only uses UTF-8, so should be readable in all modern tools and terminals.
The sparkline is between the minimum and maximum of the data, so it's mainly a indicator of variance. To keep the code simple and make the output not too wide only the first 8 values are printed. If more values are there it adds '..'
The code is inspired by Zach Holman's spark shell script.
Example output (view in non-proportial font):
Performance counter stats for 'true' (10 runs):
0.175672 task-clock (msec) # 0.555 CPUs utilized ( +- 1.77% ) █▄▁▁▁▁▁▁.. 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 114 page-faults # 0.647 M/sec ( +- 0.14% ) ▁█▁▁████.. 520,798 cycles # 2.965 GHz ( +- 1.75% ) █▄▁▁▁▁▁▁.. 433,525 instructions # 0.83 insns per cycle ( +- 0.28% ) ▅▇▅▄▇█▁▆.. 83,012 branches # 472.537 M/sec ( +- 0.31% ) ▅▇▆▄▇█▁▆.. 3,157 branch-misses # 3.80% of all branches ( +- 2.55% ) ▇█▃▅▁▃▁▂..
Quoted 5 lines
0.000316660 seconds time elapsed ( +- 1.78% ) █▅▁▁▁▁▁▁..
As you can see even in the most simple run there are quite interesting patterns. The time sparkline suggests it would be also useful to have an option to throw the first measurement away.
Hmm, my first looking at the spark thingies interpreted them as a histogram. But they're not really.
Would it be possible to make it a histogram of -2sigma,2sigma around the avg value? That way you can plot all data and get a good idea of the distribution. I'd suggest using 9 buckets for it.
Quoted 3 lines · Peter Zijlstra
Hmm, my first looking at the spark thingies interpreted them as a histogram. But they're not really.
It's a histogram of variance.
Quoted 3 lines
Would it be possible to make it a histogram of -2sigma,2sigma around the avg value? That way you can plot all data and get a good idea of the distribution. I'd suggest using 9 buckets for it.
I doubt that would work well with only ~8 values. This would need multiple lines or a real plotter, otherwise you would have all kinds of odd corner cases.
Sparklines are much better for limited space.
-Andi
Signature · 1 line
[email protected] -- Speaking for myself only
Quoted 37 lines · Andi Kleen
From: Andi Kleen <[email protected]>
perf stat -rX prints the stddev for multiple measurements. Just looking at the stddev for judging the quality of the data is a bit dangerous The simplest sanity check is to just look at a simple plot. This patchs add a sparkline to the end of the measurements to make it simple to judge the data.
The sparkline only uses UTF-8, so should be readable in all modern tools and terminals.
The sparkline is between the minimum and maximum of the data, so it's mainly a indicator of variance. To keep the code simple and make the output not too wide only the first 8 values are printed. If more values are there it adds '..'
The code is inspired by Zach Holman's spark shell script.
Example output (view in non-proportial font):
Performance counter stats for 'true' (10 runs):
0.175672 task-clock (msec) # 0.555 CPUs utilized ( +- 1.77% ) █▄▁▁▁▁▁▁.. 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 114 page-faults # 0.647 M/sec ( +- 0.14% ) ▁█▁▁████.. 520,798 cycles # 2.965 GHz ( +- 1.75% ) █▄▁▁▁▁▁▁.. 433,525 instructions # 0.83 insns per cycle ( +- 0.28% ) ▅▇▅▄▇█▁▆.. 83,012 branches # 472.537 M/sec ( +- 0.31% ) ▅▇▆▄▇█▁▆.. 3,157 branch-misses # 3.80% of all branches ( +- 2.55% ) ▇█▃▅▁▃▁▂..0.000316660 seconds time elapsed ( +- 1.78% ) █▅▁▁▁▁▁▁..
As you can see even in the most simple run there are quite interesting patterns. The time sparkline suggests it would be also useful to have an option to throw the first measurement away.
Quoted 8 lines
Known issues:
- Makes the perf stat output wider. Could be adjust by shrinking some white space. Not done so far.
- No output for -A/--per-socket/--per-core with -rX. This code is missing the basic noise detection code. Once it's added there sparklines could be shown too.v2: Address review feedback. Use
all_zero()and remove len.
ok.. confusing.. so this v2 has changes which are missing in v3 patch:
http://marc.info/?l=linux-kernel&m=139767371027557&w=2
jirka
Quoted 3 lines
ok.. confusing.. so this v2 has changes which are missing in v3 patch:
http://marc.info/?l=linux-kernel&m=139767371027557&w=2
What do you think is missing? I removed some code Namhyung didn't like in v3
-Andi