linux-sg2042/tools/perf/builtin-stat.c

1247 lines
32 KiB
C
Raw Normal View History

/*
* builtin-stat.c
*
* Builtin stat command: Give a precise performance counters summary
* overview about any workload, CPU or specific PID.
*
* Sample output:
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
$ perf stat ./hackbench 10
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
Time: 0.118
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
Performance counter stats for './hackbench 10':
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
1708.761321 task-clock # 11.037 CPUs utilized
41,190 context-switches # 0.024 M/sec
6,735 CPU-migrations # 0.004 M/sec
17,318 page-faults # 0.010 M/sec
5,205,202,243 cycles # 3.046 GHz
3,856,436,920 stalled-cycles-frontend # 74.09% frontend cycles idle
1,600,790,871 stalled-cycles-backend # 30.75% backend cycles idle
2,603,501,247 instructions # 0.50 insns per cycle
# 1.48 stalled cycles per insn
484,357,498 branches # 283.455 M/sec
6,388,934 branch-misses # 1.32% of all branches
0.154822978 seconds time elapsed
*
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
* Copyright (C) 2008-2011, Red Hat Inc, Ingo Molnar <mingo@redhat.com>
*
* Improvements and fixes by:
*
* Arjan van de Ven <arjan@linux.intel.com>
* Yanmin Zhang <yanmin.zhang@intel.com>
* Wu Fengguang <fengguang.wu@intel.com>
* Mike Galbraith <efault@gmx.de>
* Paul Mackerras <paulus@samba.org>
* Jaswinder Singh Rajput <jaswinder@kernel.org>
*
* Released under the GPL v2. (and only v2, not any later version)
*/
#include "perf.h"
#include "builtin.h"
#include "util/util.h"
#include "util/parse-options.h"
#include "util/parse-events.h"
#include "util/event.h"
#include "util/evlist.h"
#include "util/evsel.h"
#include "util/debug.h"
#include "util/color.h"
#include "util/header.h"
perf tools: Fix sparse CPU numbering related bugs At present, the perf subcommands that do system-wide monitoring (perf stat, perf record and perf top) don't work properly unless the online cpus are numbered 0, 1, ..., N-1. These tools ask for the number of online cpus with sysconf(_SC_NPROCESSORS_ONLN) and then try to create events for cpus 0, 1, ..., N-1. This creates problems for systems where the online cpus are numbered sparsely. For example, a POWER6 system in single-threaded mode (i.e. only running 1 hardware thread per core) will have only even-numbered cpus online. This fixes the problem by reading the /sys/devices/system/cpu/online file to find out which cpus are online. The code that does that is in tools/perf/util/cpumap.[ch], and consists of a read_cpu_map() function that sets up a cpumap[] array and returns the number of online cpus. If /sys/devices/system/cpu/online can't be read or can't be parsed successfully, it falls back to using sysconf to ask how many cpus are online and sets up an identity map in cpumap[]. The perf record, perf stat and perf top code then calls read_cpu_map() in the system-wide monitoring case (instead of sysconf) and uses cpumap[] to get the cpu numbers to pass to perf_event_open. Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> LKML-Reference: <20100310093609.GA3959@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 17:36:09 +08:00
#include "util/cpumap.h"
#include "util/thread.h"
#include "util/thread_map.h"
#include <sys/prctl.h>
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
#include <math.h>
perf stat: add perf stat -B to pretty print large numbers It is hard to read very large numbers so provide an option to perf stat to separate thousands using a separator. The patch leverages the locale support of stdio. You need to set your LC_NUMERIC appropriately, for instance LC_NUMERIC=en_US.UTF8. You need to pass -B to activate this feature. This way existing scripts parsing the output do not need to be changed. Here is an example. $ perf stat noploop 2 noploop for 2 seconds Performance counter stats for 'noploop 2': 1998.347031 task-clock-msecs # 0.998 CPUs 61 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 118 page-faults # 0.000 M/sec 4,138,410,900 cycles # 2070.917 M/sec (scaled from 70.01%) 2,062,650,268 instructions # 0.498 IPC (scaled from 70.01%) 2,057,653,466 branches # 1029.678 M/sec (scaled from 70.01%) 40,267 branch-misses # 0.002 % (scaled from 30.04%) 2,055,961,348 cache-references # 1028.831 M/sec (scaled from 30.03%) 53,725 cache-misses # 0.027 M/sec (scaled from 30.02%) 2.001393933 seconds time elapsed $ perf stat -B noploop 2 noploop for 2 seconds Performance counter stats for 'noploop 2': 1998.297883 task-clock-msecs # 0.998 CPUs 59 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 119 page-faults # 0.000 M/sec 4,131,380,160 cycles # 2067.450 M/sec (scaled from 70.01%) 2,059,096,507 instructions # 0.498 IPC (scaled from 70.01%) 2,054,681,303 branches # 1028.216 M/sec (scaled from 70.01%) 25,650 branch-misses # 0.001 % (scaled from 30.05%) 2,056,283,014 cache-references # 1029.017 M/sec (scaled from 30.03%) 47,097 cache-misses # 0.024 M/sec (scaled from 30.02%) 2.001391016 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <4bf28fe8.914ed80a.01ca.fffff5f5@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-05-18 21:00:01 +08:00
#include <locale.h>
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
#define DEFAULT_SEPARATOR " "
perf stat: clarify unsupported events from uncounted events perf stat continues running even if the event list contains counters that are not supported. The resulting output then contains <not counted> for those events which gets confusing as to which events are supported, but not counted and which are not supported. Before: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 0.571283 task-clock # 0.001 CPUs utilized 1 context-switches # 0.002 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.275 M/sec 1,037,707 cycles # 1.816 GHz <not counted> stalled-cycles-frontend <not counted> stalled-cycles-backend 654,499 instructions # 0.63 insns per cycle 136,129 branches # 238.286 M/sec <not counted> branch-misses <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not counted> L1-dcache-prefetch-misses 1.001004836 seconds time elapsed After: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 1.350326 task-clock # 0.001 CPUs utilized 2 context-switches # 0.001 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.116 M/sec 11,986 cycles # 0.009 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 496,986 instructions # 41.46 insns per cycle 138,065 branches # 102.246 M/sec 7,245 branch-misses # 5.25% of all branches <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not supported> L1-dcache-prefetch-misses 1.002397333 seconds time elapsed v1->v2: changed supported type from int to bool v2->v3 fixed vertical alignment of new struct element Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1306767359-13221-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-30 22:55:59 +08:00
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
perf: Do the big rename: Performance Counters -> Performance Events Bye-bye Performance Counters, welcome Performance Events! In the past few months the perfcounters subsystem has grown out its initial role of counting hardware events, and has become (and is becoming) a much broader generic event enumeration, reporting, logging, monitoring, analysis facility. Naming its core object 'perf_counter' and naming the subsystem 'perfcounters' has become more and more of a misnomer. With pending code like hw-breakpoints support the 'counter' name is less and less appropriate. All in one, we've decided to rename the subsystem to 'performance events' and to propagate this rename through all fields, variables and API names. (in an ABI compatible fashion) The word 'event' is also a bit shorter than 'counter' - which makes it slightly more convenient to write/handle as well. Thanks goes to Stephane Eranian who first observed this misnomer and suggested a rename. User-space tooling and ABI compatibility is not affected - this patch should be function-invariant. (Also, defconfigs were not touched to keep the size down.) This patch has been generated via the following script: FILES=$(find * -type f | grep -vE 'oprofile|[^K]config') sed -i \ -e 's/PERF_EVENT_/PERF_RECORD_/g' \ -e 's/PERF_COUNTER/PERF_EVENT/g' \ -e 's/perf_counter/perf_event/g' \ -e 's/nb_counters/nb_events/g' \ -e 's/swcounter/swevent/g' \ -e 's/tpcounter_event/tp_event/g' \ $FILES for N in $(find . -name perf_counter.[ch]); do M=$(echo $N | sed 's/perf_counter/perf_event/g') mv $N $M done FILES=$(find . -name perf_event.*) sed -i \ -e 's/COUNTER_MASK/REG_MASK/g' \ -e 's/COUNTER/EVENT/g' \ -e 's/\<event\>/event_id/g' \ -e 's/counter/event/g' \ -e 's/Counter/Event/g' \ $FILES ... to keep it as correct as possible. This script can also be used by anyone who has pending perfcounters patches - it converts a Linux kernel tree over to the new naming. We tried to time this change to the point in time where the amount of pending patches is the smallest: the end of the merge window. Namespace clashes were fixed up in a preparatory patch - and some stylistic fallout will be fixed up in a subsequent patch. ( NOTE: 'counters' are still the proper terminology when we deal with hardware registers - and these sed scripts are a bit over-eager in renaming them. I've undone some of that, but in case there's something left where 'counter' would be better than 'event' we can undo that on an individual basis instead of touching an otherwise nicely automated patch. ) Suggested-by: Stephane Eranian <eranian@google.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Paul Mackerras <paulus@samba.org> Reviewed-by: Arjan van de Ven <arjan@linux.intel.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Howells <dhowells@redhat.com> Cc: Kyle McMartin <kyle@mcmartin.ca> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: <linux-arch@vger.kernel.org> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-09-21 18:02:48 +08:00
static struct perf_event_attr default_attrs[] = {
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_TASK_CLOCK },
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CONTEXT_SWITCHES },
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_CPU_MIGRATIONS },
{ .type = PERF_TYPE_SOFTWARE, .config = PERF_COUNT_SW_PAGE_FAULTS },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_CPU_CYCLES },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_FRONTEND },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_STALLED_CYCLES_BACKEND },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_INSTRUCTIONS },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
{ .type = PERF_TYPE_HARDWARE, .config = PERF_COUNT_HW_BRANCH_MISSES },
};
2011-04-27 19:50:47 +08:00
/*
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
* Detailed stats (-d), covering the L1 and last level data caches:
2011-04-27 19:50:47 +08:00
*/
static struct perf_event_attr detailed_attrs[] = {
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1D << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1D << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_LL << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_LL << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
/*
* Very detailed stats (-d -d), covering the instruction cache and the TLB caches:
*/
static struct perf_event_attr very_detailed_attrs[] = {
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1I << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1I << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_DTLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_DTLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_ITLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_ITLB << 0 |
(PERF_COUNT_HW_CACHE_OP_READ << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
/*
* Very, very detailed stats (-d -d -d), adding prefetch events:
*/
static struct perf_event_attr very_very_detailed_attrs[] = {
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1D << 0 |
(PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) |
(PERF_COUNT_HW_CACHE_RESULT_ACCESS << 16) },
{ .type = PERF_TYPE_HW_CACHE,
.config =
PERF_COUNT_HW_CACHE_L1D << 0 |
(PERF_COUNT_HW_CACHE_OP_PREFETCH << 8) |
(PERF_COUNT_HW_CACHE_RESULT_MISS << 16) },
};
struct perf_evlist *evsel_list;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
static bool system_wide = false;
static int run_idx = 0;
static int run_count = 1;
static bool no_inherit = false;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
static bool scale = true;
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
static bool no_aggr = false;
static pid_t target_pid = -1;
static pid_t target_tid = -1;
static pid_t child_pid = -1;
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
static bool null_run = false;
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
static int detailed_run = 0;
static bool sync_run = false;
static bool big_num = true;
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
static int big_num_opt = -1;
static const char *cpu_list;
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
static const char *csv_sep = NULL;
static bool csv_output = false;
static bool group = false;
perf stat: add perf stat -B to pretty print large numbers It is hard to read very large numbers so provide an option to perf stat to separate thousands using a separator. The patch leverages the locale support of stdio. You need to set your LC_NUMERIC appropriately, for instance LC_NUMERIC=en_US.UTF8. You need to pass -B to activate this feature. This way existing scripts parsing the output do not need to be changed. Here is an example. $ perf stat noploop 2 noploop for 2 seconds Performance counter stats for 'noploop 2': 1998.347031 task-clock-msecs # 0.998 CPUs 61 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 118 page-faults # 0.000 M/sec 4,138,410,900 cycles # 2070.917 M/sec (scaled from 70.01%) 2,062,650,268 instructions # 0.498 IPC (scaled from 70.01%) 2,057,653,466 branches # 1029.678 M/sec (scaled from 70.01%) 40,267 branch-misses # 0.002 % (scaled from 30.04%) 2,055,961,348 cache-references # 1028.831 M/sec (scaled from 30.03%) 53,725 cache-misses # 0.027 M/sec (scaled from 30.02%) 2.001393933 seconds time elapsed $ perf stat -B noploop 2 noploop for 2 seconds Performance counter stats for 'noploop 2': 1998.297883 task-clock-msecs # 0.998 CPUs 59 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 119 page-faults # 0.000 M/sec 4,131,380,160 cycles # 2067.450 M/sec (scaled from 70.01%) 2,059,096,507 instructions # 0.498 IPC (scaled from 70.01%) 2,054,681,303 branches # 1028.216 M/sec (scaled from 70.01%) 25,650 branch-misses # 0.001 % (scaled from 30.05%) 2,056,283,014 cache-references # 1029.017 M/sec (scaled from 30.03%) 47,097 cache-misses # 0.024 M/sec (scaled from 30.02%) 2.001391016 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <4bf28fe8.914ed80a.01ca.fffff5f5@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-05-18 21:00:01 +08:00
static volatile int done = 0;
struct stats
{
double n, mean, M2;
};
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
struct perf_stat {
struct stats res_stats[3];
};
static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel)
{
evsel->priv = zalloc(sizeof(struct perf_stat));
return evsel->priv == NULL ? -ENOMEM : 0;
}
static void perf_evsel__free_stat_priv(struct perf_evsel *evsel)
{
free(evsel->priv);
evsel->priv = NULL;
}
static void update_stats(struct stats *stats, u64 val)
{
double delta;
stats->n++;
delta = val - stats->mean;
stats->mean += delta / stats->n;
stats->M2 += delta*(val - stats->mean);
}
static double avg_stats(struct stats *stats)
{
return stats->mean;
}
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
/*
* http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance
*
* (\Sum n_i^2) - ((\Sum n_i)^2)/n
* s^2 = -------------------------------
* n - 1
*
* http://en.wikipedia.org/wiki/Stddev
*
* The std dev of the mean is related to the std dev by:
*
* s
* s_mean = -------
* sqrt(n)
*
*/
static double stddev_stats(struct stats *stats)
{
double variance = stats->M2 / (stats->n - 1);
double variance_mean = variance / stats->n;
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
return sqrt(variance_mean);
}
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
struct stats runtime_nsecs_stats[MAX_NR_CPUS];
struct stats runtime_cycles_stats[MAX_NR_CPUS];
struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS];
struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS];
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
struct stats runtime_branches_stats[MAX_NR_CPUS];
struct stats runtime_cacherefs_stats[MAX_NR_CPUS];
struct stats runtime_l1_dcache_stats[MAX_NR_CPUS];
struct stats runtime_l1_icache_stats[MAX_NR_CPUS];
struct stats runtime_ll_cache_stats[MAX_NR_CPUS];
struct stats runtime_itlb_cache_stats[MAX_NR_CPUS];
struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS];
struct stats walltime_nsecs_stats;
perf_counter tools: Also display time-normalized stat results Add new column that normalizes counter results by 'nanoseconds spent running' unit. Before: Performance counter stats for '/home/mingo/hackbench': 10469.403605 task clock ticks (msecs) 75502 context switches (events) 9501 CPU migrations (events) 36158 pagefaults (events) 31975676185 CPU cycles (events) 26257738659 instructions (events) 108740581 cache references (events) 54606088 cache misses (events) Wall-clock time elapsed: 810.514504 msecs After: Performance counter stats for '/home/mingo/hackbench': 10469.403605 task clock ticks (msecs) 75502 context switches # 0.007 M/sec 9501 CPU migrations # 0.001 M/sec 36158 pagefaults # 0.003 M/sec 31975676185 CPU cycles # 3054.202 M/sec 26257738659 instructions # 2508.045 M/sec 108740581 cache references # 10.387 M/sec 54606088 cache misses # 5.216 M/sec Wall-clock time elapsed: 810.514504 msecs The advantage of that column is that it is characteristic of the execution workflow, regardless of runtime. Hence 'hackbench 10' will look similar to 'hackbench 15' - while the absolute counter values are very different. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-29 15:10:54 +08:00
static int create_perf_stat_counter(struct perf_evsel *evsel)
{
struct perf_event_attr *attr = &evsel->attr;
if (scale)
attr->read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
PERF_FORMAT_TOTAL_TIME_RUNNING;
attr->inherit = !no_inherit;
if (system_wide)
return perf_evsel__open_per_cpu(evsel, evsel_list->cpus, group);
if (target_pid == -1 && target_tid == -1) {
attr->disabled = 1;
attr->enable_on_exec = 1;
}
return perf_evsel__open_per_thread(evsel, evsel_list->threads, group);
}
/*
* Does the counter have nsecs as a unit?
*/
static inline int nsec_counter(struct perf_evsel *evsel)
{
if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
return 1;
return 0;
}
/*
* Update various tracking values we maintain to print
* more semantic information such as miss/hit ratios,
* instruction rates, etc:
*/
static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
{
if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
update_stats(&runtime_nsecs_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
update_stats(&runtime_cycles_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_stats(&runtime_stalled_cycles_front_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
update_stats(&runtime_stalled_cycles_back_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
update_stats(&runtime_branches_stats[0], count[0]);
else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
update_stats(&runtime_cacherefs_stats[0], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
update_stats(&runtime_l1_dcache_stats[0], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
update_stats(&runtime_l1_icache_stats[0], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
update_stats(&runtime_ll_cache_stats[0], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
update_stats(&runtime_dtlb_cache_stats[0], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
update_stats(&runtime_itlb_cache_stats[0], count[0]);
}
/*
* Read out the results of a single counter:
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
* aggregate counts across CPUs in system-wide mode
*/
static int read_counter_aggr(struct perf_evsel *counter)
{
struct perf_stat *ps = counter->priv;
u64 *count = counter->counts->aggr.values;
int i;
if (__perf_evsel__read(counter, evsel_list->cpus->nr,
evsel_list->threads->nr, scale) < 0)
return -1;
for (i = 0; i < 3; i++)
update_stats(&ps->res_stats[i], count[i]);
if (verbose) {
fprintf(stderr, "%s: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
event_name(counter), count[0], count[1], count[2]);
}
perf_counter tools: Also display time-normalized stat results Add new column that normalizes counter results by 'nanoseconds spent running' unit. Before: Performance counter stats for '/home/mingo/hackbench': 10469.403605 task clock ticks (msecs) 75502 context switches (events) 9501 CPU migrations (events) 36158 pagefaults (events) 31975676185 CPU cycles (events) 26257738659 instructions (events) 108740581 cache references (events) 54606088 cache misses (events) Wall-clock time elapsed: 810.514504 msecs After: Performance counter stats for '/home/mingo/hackbench': 10469.403605 task clock ticks (msecs) 75502 context switches # 0.007 M/sec 9501 CPU migrations # 0.001 M/sec 36158 pagefaults # 0.003 M/sec 31975676185 CPU cycles # 3054.202 M/sec 26257738659 instructions # 2508.045 M/sec 108740581 cache references # 10.387 M/sec 54606088 cache misses # 5.216 M/sec Wall-clock time elapsed: 810.514504 msecs The advantage of that column is that it is characteristic of the execution workflow, regardless of runtime. Hence 'hackbench 10' will look similar to 'hackbench 15' - while the absolute counter values are very different. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: John Kacur <jkacur@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-05-29 15:10:54 +08:00
/*
* Save the full runtime - to allow normalization during printout:
*/
update_shadow_stats(counter, count);
return 0;
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
}
/*
* Read out the results of a single counter:
* do not aggregate counts across CPUs in system-wide mode
*/
static int read_counter(struct perf_evsel *counter)
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
{
u64 *count;
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
int cpu;
for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
return -1;
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
count = counter->counts->cpu[cpu].values;
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
update_shadow_stats(counter, count);
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
}
return 0;
}
static int run_perf_stat(int argc __used, const char **argv)
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
{
unsigned long long t0, t1;
struct perf_evsel *counter;
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
int status = 0;
perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver <vince@deater.net> Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 19:13:21 +08:00
int child_ready_pipe[2], go_pipe[2];
const bool forks = (argc > 0);
perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver <vince@deater.net> Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 19:13:21 +08:00
char buf;
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
if (forks && (pipe(child_ready_pipe) < 0 || pipe(go_pipe) < 0)) {
perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver <vince@deater.net> Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 19:13:21 +08:00
perror("failed to create pipes");
exit(1);
}
if (forks) {
if ((child_pid = fork()) < 0)
perror("failed to fork");
if (!child_pid) {
close(child_ready_pipe[0]);
close(go_pipe[1]);
fcntl(go_pipe[0], F_SETFD, FD_CLOEXEC);
/*
* Do a dummy execvp to get the PLT entry resolved,
* so we avoid the resolver overhead on the real
* execvp call.
*/
execvp("", (char **)argv);
/*
* Tell the parent we're ready to go
*/
close(child_ready_pipe[1]);
/*
* Wait until the parent tells us to go.
*/
if (read(go_pipe[0], &buf, 1) == -1)
perror("unable to read pipe");
execvp(argv[0], (char **)argv);
perror(argv[0]);
exit(-1);
}
perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver <vince@deater.net> Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 19:13:21 +08:00
if (target_tid == -1 && target_pid == -1 && !system_wide)
evsel_list->threads->map[0] = child_pid;
perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver <vince@deater.net> Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 19:13:21 +08:00
/*
* Wait for the child to be ready to exec.
perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver <vince@deater.net> Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 19:13:21 +08:00
*/
close(child_ready_pipe[1]);
close(go_pipe[0]);
if (read(child_ready_pipe[0], &buf, 1) == -1)
perror("unable to read pipe");
close(child_ready_pipe[0]);
perf_counter tools: Reduce perf stat measurement overhead/skew Vince Weaver reported a 'perf stat' measurement overhead in the count of retired instructions, which can amount to a +6000 instructions inflated count in the reported count. At present, perf stat creates its counters on the perf process. Thus the counters count the fork and various other activity in both the parent and child, such as the resolver overhead for resolving PLT entries for any libc functions that haven't been called before, such as execvp. This reduces the overhead by creating the counters on the child process after the fork, using a couple of pipes to synchronize so that the child process waits until the parent has created the counters before doing the exec. To eliminate the PLT resolution overhead on calling execvp, this does a dummy execvp first which will always fail. With this, the overhead of executing a program goes down from over 4800 instructions to about 90 instructions on powerpc (32-bit). This was measured with a statically-linked program written in assembler which only does the 3 instructions needed to call _exit(0). Before: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 4858 instructions 0.001274523 seconds time elapsed After: $ perf stat -e 0:1:u ./three Performance counter stats for './three': 92 instructions 0.000468153 seconds time elapsed Reported-by: Vince Weaver <vince@deater.net> Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <19016.41425.814043.870352@cargo.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-29 19:13:21 +08:00
}
list_for_each_entry(counter, &evsel_list->entries, node) {
if (create_perf_stat_counter(counter) < 0) {
if (errno == EINVAL || errno == ENOSYS || errno == ENOENT) {
if (verbose)
ui__warning("%s event is not supported by the kernel.\n",
event_name(counter));
perf stat: clarify unsupported events from uncounted events perf stat continues running even if the event list contains counters that are not supported. The resulting output then contains <not counted> for those events which gets confusing as to which events are supported, but not counted and which are not supported. Before: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 0.571283 task-clock # 0.001 CPUs utilized 1 context-switches # 0.002 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.275 M/sec 1,037,707 cycles # 1.816 GHz <not counted> stalled-cycles-frontend <not counted> stalled-cycles-backend 654,499 instructions # 0.63 insns per cycle 136,129 branches # 238.286 M/sec <not counted> branch-misses <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not counted> L1-dcache-prefetch-misses 1.001004836 seconds time elapsed After: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 1.350326 task-clock # 0.001 CPUs utilized 2 context-switches # 0.001 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.116 M/sec 11,986 cycles # 0.009 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 496,986 instructions # 41.46 insns per cycle 138,065 branches # 102.246 M/sec 7,245 branch-misses # 5.25% of all branches <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not supported> L1-dcache-prefetch-misses 1.002397333 seconds time elapsed v1->v2: changed supported type from int to bool v2->v3 fixed vertical alignment of new struct element Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1306767359-13221-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-30 22:55:59 +08:00
counter->supported = false;
continue;
}
if (errno == EPERM || errno == EACCES) {
error("You may not have permission to collect %sstats.\n"
"\t Consider tweaking"
" /proc/sys/kernel/perf_event_paranoid or running as root.",
system_wide ? "system-wide " : "");
} else {
error("open_counter returned with %d (%s). "
"/bin/dmesg may provide additional information.\n",
errno, strerror(errno));
}
if (child_pid != -1)
kill(child_pid, SIGTERM);
die("Not all events could be opened.\n");
return -1;
}
perf stat: clarify unsupported events from uncounted events perf stat continues running even if the event list contains counters that are not supported. The resulting output then contains <not counted> for those events which gets confusing as to which events are supported, but not counted and which are not supported. Before: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 0.571283 task-clock # 0.001 CPUs utilized 1 context-switches # 0.002 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.275 M/sec 1,037,707 cycles # 1.816 GHz <not counted> stalled-cycles-frontend <not counted> stalled-cycles-backend 654,499 instructions # 0.63 insns per cycle 136,129 branches # 238.286 M/sec <not counted> branch-misses <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not counted> L1-dcache-prefetch-misses 1.001004836 seconds time elapsed After: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 1.350326 task-clock # 0.001 CPUs utilized 2 context-switches # 0.001 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.116 M/sec 11,986 cycles # 0.009 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 496,986 instructions # 41.46 insns per cycle 138,065 branches # 102.246 M/sec 7,245 branch-misses # 5.25% of all branches <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not supported> L1-dcache-prefetch-misses 1.002397333 seconds time elapsed v1->v2: changed supported type from int to bool v2->v3 fixed vertical alignment of new struct element Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1306767359-13221-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-30 22:55:59 +08:00
counter->supported = true;
}
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
if (perf_evlist__set_filters(evsel_list)) {
error("failed to set filter with %d (%s)\n", errno,
strerror(errno));
return -1;
}
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
/*
* Enable counters and exec the command:
*/
t0 = rdclock();
if (forks) {
close(go_pipe[1]);
wait(&status);
} else {
while(!done) sleep(1);
}
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
t1 = rdclock();
update_stats(&walltime_nsecs_stats, t1 - t0);
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
if (no_aggr) {
list_for_each_entry(counter, &evsel_list->entries, node) {
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
read_counter(counter);
perf_evsel__close_fd(counter, evsel_list->cpus->nr, 1);
}
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
} else {
list_for_each_entry(counter, &evsel_list->entries, node) {
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
read_counter_aggr(counter);
perf_evsel__close_fd(counter, evsel_list->cpus->nr,
evsel_list->threads->nr);
}
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
}
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
return WEXITSTATUS(status);
}
static void print_noise_pct(double total, double avg)
{
double pct = 0.0;
if (avg)
pct = 100.0*total/avg;
if (csv_output)
fprintf(stderr, "%s%.2f%%", csv_sep, pct);
else
fprintf(stderr, " ( +-%6.2f%% )", pct);
}
static void print_noise(struct perf_evsel *evsel, double avg)
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
{
struct perf_stat *ps;
if (run_count == 1)
return;
ps = evsel->priv;
print_noise_pct(stddev_stats(&ps->res_stats[0]), avg);
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
}
static void nsec_printout(int cpu, struct perf_evsel *evsel, double avg)
{
double msecs = avg / 1e6;
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
char cpustr[16] = { '\0', };
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
const char *fmt = csv_output ? "%s%.6f%s%s" : "%s%18.6f%s%-25s";
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
if (no_aggr)
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
sprintf(cpustr, "CPU%*d%s",
csv_output ? 0 : -4,
evsel_list->cpus->map[cpu], csv_sep);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
fprintf(stderr, fmt, cpustr, msecs, csv_sep, event_name(evsel));
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (evsel->cgrp)
fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (csv_output)
return;
if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
fprintf(stderr, " # %8.3f CPUs utilized ", avg / avg_stats(&walltime_nsecs_stats));
}
static void print_stalled_cycles_frontend(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_cycles_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 50.0)
color = PERF_COLOR_RED;
else if (ratio > 30.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 10.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " frontend cycles idle ");
}
static void print_stalled_cycles_backend(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_cycles_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 75.0)
color = PERF_COLOR_RED;
else if (ratio > 50.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 20.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " backend cycles idle ");
}
static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_branches_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 20.0)
color = PERF_COLOR_RED;
else if (ratio > 10.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 5.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " of all branches ");
}
static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_l1_dcache_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 20.0)
color = PERF_COLOR_RED;
else if (ratio > 10.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 5.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " of all L1-dcache hits ");
}
static void print_l1_icache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_l1_icache_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 20.0)
color = PERF_COLOR_RED;
else if (ratio > 10.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 5.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " of all L1-icache hits ");
}
static void print_dtlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_dtlb_cache_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 20.0)
color = PERF_COLOR_RED;
else if (ratio > 10.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 5.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " of all dTLB cache hits ");
}
static void print_itlb_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_itlb_cache_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 20.0)
color = PERF_COLOR_RED;
else if (ratio > 10.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 5.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " of all iTLB cache hits ");
}
static void print_ll_cache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
{
double total, ratio = 0.0;
const char *color;
total = avg_stats(&runtime_ll_cache_stats[cpu]);
if (total)
ratio = avg / total * 100.0;
color = PERF_COLOR_NORMAL;
if (ratio > 20.0)
color = PERF_COLOR_RED;
else if (ratio > 10.0)
color = PERF_COLOR_MAGENTA;
else if (ratio > 5.0)
color = PERF_COLOR_YELLOW;
fprintf(stderr, " # ");
color_fprintf(stderr, color, "%6.2f%%", ratio);
fprintf(stderr, " of all LL-cache hits ");
}
static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
{
double total, ratio = 0.0;
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
char cpustr[16] = { '\0', };
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
const char *fmt;
if (csv_output)
fmt = "%s%.0f%s%s";
else if (big_num)
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
fmt = "%s%'18.0f%s%-25s";
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
else
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
fmt = "%s%18.0f%s%-25s";
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
if (no_aggr)
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
sprintf(cpustr, "CPU%*d%s",
csv_output ? 0 : -4,
evsel_list->cpus->map[cpu], csv_sep);
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
else
cpu = 0;
fprintf(stderr, fmt, cpustr, avg, csv_sep, event_name(evsel));
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (evsel->cgrp)
fprintf(stderr, "%s%s", csv_sep, evsel->cgrp->name);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (csv_output)
return;
if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
total = avg_stats(&runtime_cycles_stats[cpu]);
if (total)
ratio = avg / total;
fprintf(stderr, " # %5.2f insns per cycle ", ratio);
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]);
total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu]));
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
if (total && avg) {
ratio = total / avg;
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
fprintf(stderr, "\n # %5.2f stalled cycles per insn", ratio);
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
}
} else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
runtime_branches_stats[cpu].n != 0) {
print_branch_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
2011-04-27 19:50:47 +08:00
runtime_l1_dcache_stats[cpu].n != 0) {
print_l1_dcache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_l1_icache_stats[cpu].n != 0) {
print_l1_icache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_dtlb_cache_stats[cpu].n != 0) {
print_dtlb_cache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_itlb_cache_stats[cpu].n != 0) {
print_itlb_cache_misses(cpu, evsel, avg);
} else if (
evsel->attr.type == PERF_TYPE_HW_CACHE &&
evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
runtime_ll_cache_stats[cpu].n != 0) {
print_ll_cache_misses(cpu, evsel, avg);
} else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
runtime_cacherefs_stats[cpu].n != 0) {
total = avg_stats(&runtime_cacherefs_stats[cpu]);
if (total)
ratio = avg * 100 / total;
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
fprintf(stderr, " # %8.3f %% of all cache refs ", ratio);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
print_stalled_cycles_frontend(cpu, evsel, avg);
} else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
print_stalled_cycles_backend(cpu, evsel, avg);
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
} else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
total = avg_stats(&runtime_nsecs_stats[cpu]);
if (total)
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
ratio = 1.0 * avg / total;
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
fprintf(stderr, " # %8.3f GHz ", ratio);
} else if (runtime_nsecs_stats[cpu].n != 0) {
total = avg_stats(&runtime_nsecs_stats[cpu]);
if (total)
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
ratio = 1000.0 * avg / total;
perf stat: Add stalled cycles accounting, prettify the resulting output Add stalled cycles accounting and use it to print the "cycles stalled per instruction" value. Also change the unit of the cycles output from M/sec to GHz - this is more intuitive. Prettify the output to: Performance counter stats for './loop_1b_instructions': 239.775036 task-clock # 0.997 CPUs utilized 761,903,912 cycles # 3.178 GHz 356,620,620 stalled-cycles # 46.81% of all cycles are idle 1,001,578,351 instructions # 1.31 insns per cycle # 0.36 stalled cycles per insn 14,782 cache-references # 0.062 M/sec 5,694 cache-misses # 38.520 % of all cache refs 0.240493656 seconds time elapsed Also adjust the --repeat output to make the percentages align vertically: Performance counter stats for './loop_1b_instructions' (10 runs): 236.096793 task-clock # 0.997 CPUs utilized ( +- 0.011% ) 756,553,086 cycles # 3.204 GHz ( +- 0.002% ) 354,942,692 stalled-cycles # 46.92% of all cycles are idle ( +- 0.008% ) 1,001,389,700 instructions # 1.32 insns per cycle # 0.35 stalled cycles per insn ( +- 0.000% ) 10,166 cache-references # 0.043 M/sec ( +- 0.742% ) 468 cache-misses # 4.608 % of all cache refs ( +- 13.385% ) 0.236874136 seconds time elapsed ( +- 0.01% ) Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Link: http://lkml.kernel.org/n/tip-uapziqny39601apdmmhoz7hk@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-04-27 10:34:16 +08:00
fprintf(stderr, " # %8.3f M/sec ", ratio);
} else {
fprintf(stderr, " ");
}
}
/*
* Print out the results of a single counter:
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
* aggregated counts in system-wide mode
*/
static void print_counter_aggr(struct perf_evsel *counter)
{
struct perf_stat *ps = counter->priv;
double avg = avg_stats(&ps->res_stats[0]);
int scaled = counter->counts->scaled;
if (scaled == -1) {
fprintf(stderr, "%*s%s%*s",
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
csv_output ? 0 : 18,
perf stat: clarify unsupported events from uncounted events perf stat continues running even if the event list contains counters that are not supported. The resulting output then contains <not counted> for those events which gets confusing as to which events are supported, but not counted and which are not supported. Before: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 0.571283 task-clock # 0.001 CPUs utilized 1 context-switches # 0.002 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.275 M/sec 1,037,707 cycles # 1.816 GHz <not counted> stalled-cycles-frontend <not counted> stalled-cycles-backend 654,499 instructions # 0.63 insns per cycle 136,129 branches # 238.286 M/sec <not counted> branch-misses <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not counted> L1-dcache-prefetch-misses 1.001004836 seconds time elapsed After: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 1.350326 task-clock # 0.001 CPUs utilized 2 context-switches # 0.001 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.116 M/sec 11,986 cycles # 0.009 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 496,986 instructions # 41.46 insns per cycle 138,065 branches # 102.246 M/sec 7,245 branch-misses # 5.25% of all branches <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not supported> L1-dcache-prefetch-misses 1.002397333 seconds time elapsed v1->v2: changed supported type from int to bool v2->v3 fixed vertical alignment of new struct element Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1306767359-13221-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-30 22:55:59 +08:00
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
csv_sep,
csv_output ? 0 : -24,
event_name(counter));
if (counter->cgrp)
fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
fputc('\n', stderr);
return;
}
if (nsec_counter(counter))
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
nsec_printout(-1, counter, avg);
else
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
abs_printout(-1, counter, avg);
print_noise(counter, avg);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (csv_output) {
fputc('\n', stderr);
return;
}
if (scaled) {
double avg_enabled, avg_running;
avg_enabled = avg_stats(&ps->res_stats[1]);
avg_running = avg_stats(&ps->res_stats[2]);
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
fprintf(stderr, " [%5.2f%%]", 100 * avg_running / avg_enabled);
}
fprintf(stderr, "\n");
}
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
/*
* Print out the results of a single counter:
* does not use aggregated count in system-wide
*/
static void print_counter(struct perf_evsel *counter)
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
{
u64 ena, run, val;
int cpu;
for (cpu = 0; cpu < evsel_list->cpus->nr; cpu++) {
val = counter->counts->cpu[cpu].val;
ena = counter->counts->cpu[cpu].ena;
run = counter->counts->cpu[cpu].run;
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
if (run == 0 || ena == 0) {
fprintf(stderr, "CPU%*d%s%*s%s%*s",
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
csv_output ? 0 : -4,
evsel_list->cpus->map[cpu], csv_sep,
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
csv_output ? 0 : 18,
perf stat: clarify unsupported events from uncounted events perf stat continues running even if the event list contains counters that are not supported. The resulting output then contains <not counted> for those events which gets confusing as to which events are supported, but not counted and which are not supported. Before: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 0.571283 task-clock # 0.001 CPUs utilized 1 context-switches # 0.002 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.275 M/sec 1,037,707 cycles # 1.816 GHz <not counted> stalled-cycles-frontend <not counted> stalled-cycles-backend 654,499 instructions # 0.63 insns per cycle 136,129 branches # 238.286 M/sec <not counted> branch-misses <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not counted> L1-dcache-prefetch-misses 1.001004836 seconds time elapsed After: perf stat -ddd -- sleep 1 Performance counter stats for 'sleep 1': 1.350326 task-clock # 0.001 CPUs utilized 2 context-switches # 0.001 M/sec 0 CPU-migrations # 0.000 M/sec 157 page-faults # 0.116 M/sec 11,986 cycles # 0.009 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 496,986 instructions # 41.46 insns per cycle 138,065 branches # 102.246 M/sec 7,245 branch-misses # 5.25% of all branches <not counted> L1-dcache-loads <not counted> L1-dcache-load-misses <not counted> LLC-loads <not counted> LLC-load-misses <not counted> L1-icache-loads <not counted> L1-icache-load-misses <not counted> dTLB-loads <not counted> dTLB-load-misses <not counted> iTLB-loads <not counted> iTLB-load-misses <not counted> L1-dcache-prefetches <not supported> L1-dcache-prefetch-misses 1.002397333 seconds time elapsed v1->v2: changed supported type from int to bool v2->v3 fixed vertical alignment of new struct element Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Link: http://lkml.kernel.org/r/1306767359-13221-1-git-send-email-dsahern@gmail.com Signed-off-by: David Ahern <dsahern@gmail.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-05-30 22:55:59 +08:00
counter->supported ? CNTR_NOT_COUNTED : CNTR_NOT_SUPPORTED,
csv_sep,
csv_output ? 0 : -24,
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
event_name(counter));
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
if (counter->cgrp)
fprintf(stderr, "%s%s", csv_sep, counter->cgrp->name);
fputc('\n', stderr);
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
continue;
}
if (nsec_counter(counter))
nsec_printout(cpu, counter, val);
else
abs_printout(cpu, counter, val);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (!csv_output) {
print_noise(counter, 1.0);
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
2011-04-27 19:50:47 +08:00
if (run != ena)
fprintf(stderr, " (%.2f%%)", 100.0 * run / ena);
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
}
fputc('\n', stderr);
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
}
}
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
static void print_stat(int argc, const char **argv)
{
struct perf_evsel *counter;
int i;
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
fflush(stdout);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (!csv_output) {
fprintf(stderr, "\n");
fprintf(stderr, " Performance counter stats for ");
if(target_pid == -1 && target_tid == -1) {
fprintf(stderr, "\'%s", argv[0]);
for (i = 1; i < argc; i++)
fprintf(stderr, " %s", argv[i]);
} else if (target_pid != -1)
fprintf(stderr, "process id \'%d", target_pid);
else
fprintf(stderr, "thread id \'%d", target_tid);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
fprintf(stderr, "\'");
if (run_count > 1)
fprintf(stderr, " (%d runs)", run_count);
fprintf(stderr, ":\n\n");
}
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
if (no_aggr) {
list_for_each_entry(counter, &evsel_list->entries, node)
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
print_counter(counter);
} else {
list_for_each_entry(counter, &evsel_list->entries, node)
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
print_counter_aggr(counter);
}
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (!csv_output) {
if (!null_run)
fprintf(stderr, "\n");
fprintf(stderr, " %17.9f seconds time elapsed",
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
avg_stats(&walltime_nsecs_stats)/1e9);
if (run_count > 1) {
fprintf(stderr, " ");
print_noise_pct(stddev_stats(&walltime_nsecs_stats),
avg_stats(&walltime_nsecs_stats));
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
}
fprintf(stderr, "\n\n");
}
}
static volatile int signr = -1;
static void skip_signal(int signo)
{
if(child_pid == -1)
done = 1;
signr = signo;
}
static void sig_atexit(void)
{
if (child_pid != -1)
kill(child_pid, SIGTERM);
if (signr == -1)
return;
signal(signr, SIG_DFL);
kill(getpid(), signr);
}
static const char * const stat_usage[] = {
"perf stat [<options>] [<command>]",
NULL
};
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
static int stat__set_big_num(const struct option *opt __used,
const char *s __used, int unset)
{
big_num_opt = unset ? 0 : 1;
return 0;
}
static const struct option options[] = {
OPT_CALLBACK('e', "event", &evsel_list, "event",
"event selector. use 'perf list' to list available events",
parse_events_option),
OPT_CALLBACK(0, "filter", &evsel_list, "filter",
"event filter", parse_filter),
OPT_BOOLEAN('i', "no-inherit", &no_inherit,
"child tasks do not inherit counters"),
OPT_INTEGER('p', "pid", &target_pid,
"stat events on existing process id"),
OPT_INTEGER('t', "tid", &target_tid,
"stat events on existing thread id"),
OPT_BOOLEAN('a', "all-cpus", &system_wide,
"system-wide collection from all CPUs"),
OPT_BOOLEAN('g', "group", &group,
"put the counters into a counter group"),
OPT_BOOLEAN('c', "scale", &scale,
"scale/normalize counters"),
perf: Fix endianness argument compatibility with OPT_BOOLEAN() and introduce OPT_INCR() Parsing an option from the command line with OPT_BOOLEAN on a bool data type would not work on a big-endian machine due to the manner in which the boolean was being cast into an int and incremented. For example, running 'perf probe --list' on a PowerPC machine would fail to properly set the list_events bool and would therefore print out the usage information and terminate. This patch makes OPT_BOOLEAN work as expected with a bool datatype. For cases where the original OPT_BOOLEAN was intentionally being used to increment an int each time it was passed in on the command line, this patch introduces OPT_INCR with the old behaviour of OPT_BOOLEAN (the verbose variable is currently the only such example of this). I have reviewed every use of OPT_BOOLEAN to verify that a true C99 bool was passed. Where integers were used, I verified that they were only being used for boolean logic and changed them to bools to ensure that they would not be mistakenly used as ints. The major exception was the verbose variable which now uses OPT_INCR instead of OPT_BOOLEAN. Signed-off-by: Ian Munsie <imunsie@au.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: <stable@kernel.org> # NOTE: wont apply to .3[34].x cleanly, please backport Cc: Git development list <git@vger.kernel.org> Cc: Ian Munsie <imunsie@au1.ibm.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Eric B Munson <ebmunson@us.ibm.com> Cc: Valdis.Kletnieks@vt.edu Cc: WANG Cong <amwang@redhat.com> Cc: Thiago Farina <tfransosi@gmail.com> Cc: Masami Hiramatsu <mhiramat@redhat.com> Cc: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com> Cc: Jaswinder Singh Rajput <jaswinderrajput@gmail.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Cc: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> Cc: Mike Galbraith <efault@gmx.de> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Anton Blanchard <anton@samba.org> Cc: John Kacur <jkacur@redhat.com> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> LKML-Reference: <1271147857-11604-1-git-send-email-imunsie@au.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-04-13 16:37:33 +08:00
OPT_INCR('v', "verbose", &verbose,
"be more verbose (show counter open errors, etc)"),
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
OPT_INTEGER('r', "repeat", &run_count,
"repeat command and print average + stddev (max: 100)"),
OPT_BOOLEAN('n', "null", &null_run,
"null run - dont start any counters"),
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
OPT_INCR('d', "detailed", &detailed_run,
2011-04-27 19:50:47 +08:00
"detailed run - start a lot of events"),
OPT_BOOLEAN('S', "sync", &sync_run,
"call sync() before starting a run"),
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL,
"print large numbers with thousands\' separators",
stat__set_big_num),
OPT_STRING('C', "cpu", &cpu_list, "cpu",
"list of cpus to monitor in system-wide"),
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
OPT_BOOLEAN('A', "no-aggr", &no_aggr,
"disable CPU count aggregation"),
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
OPT_STRING('x', "field-separator", &csv_sep, "separator",
"print counts with custom separator"),
OPT_CALLBACK('G', "cgroup", &evsel_list, "name",
"monitor event in cgroup name only",
parse_cgroups),
OPT_END()
};
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
/*
* Add default attributes, if there were no attributes specified or
* if -d/--detailed, -d -d or -d -d -d is used:
*/
static int add_default_attributes(void)
{
struct perf_evsel *pos;
size_t attr_nr = 0;
size_t c;
/* Set attrs if no event is selected and !null_run: */
if (null_run)
return 0;
if (!evsel_list->nr_entries) {
for (c = 0; c < ARRAY_SIZE(default_attrs); c++) {
pos = perf_evsel__new(default_attrs + c, c + attr_nr);
if (pos == NULL)
return -1;
perf_evlist__add(evsel_list, pos);
}
attr_nr += c;
}
/* Detailed events get appended to the event list: */
if (detailed_run < 1)
return 0;
/* Append detailed run extra attributes: */
for (c = 0; c < ARRAY_SIZE(detailed_attrs); c++) {
pos = perf_evsel__new(detailed_attrs + c, c + attr_nr);
if (pos == NULL)
return -1;
perf_evlist__add(evsel_list, pos);
}
attr_nr += c;
if (detailed_run < 2)
return 0;
/* Append very detailed run extra attributes: */
for (c = 0; c < ARRAY_SIZE(very_detailed_attrs); c++) {
pos = perf_evsel__new(very_detailed_attrs + c, c + attr_nr);
if (pos == NULL)
return -1;
perf_evlist__add(evsel_list, pos);
}
if (detailed_run < 3)
return 0;
/* Append very, very detailed run extra attributes: */
for (c = 0; c < ARRAY_SIZE(very_very_detailed_attrs); c++) {
pos = perf_evsel__new(very_very_detailed_attrs + c, c + attr_nr);
if (pos == NULL)
return -1;
perf_evlist__add(evsel_list, pos);
}
return 0;
}
int cmd_stat(int argc, const char **argv, const char *prefix __used)
{
struct perf_evsel *pos;
int status = -ENOMEM;
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
perf stat: add perf stat -B to pretty print large numbers It is hard to read very large numbers so provide an option to perf stat to separate thousands using a separator. The patch leverages the locale support of stdio. You need to set your LC_NUMERIC appropriately, for instance LC_NUMERIC=en_US.UTF8. You need to pass -B to activate this feature. This way existing scripts parsing the output do not need to be changed. Here is an example. $ perf stat noploop 2 noploop for 2 seconds Performance counter stats for 'noploop 2': 1998.347031 task-clock-msecs # 0.998 CPUs 61 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 118 page-faults # 0.000 M/sec 4,138,410,900 cycles # 2070.917 M/sec (scaled from 70.01%) 2,062,650,268 instructions # 0.498 IPC (scaled from 70.01%) 2,057,653,466 branches # 1029.678 M/sec (scaled from 70.01%) 40,267 branch-misses # 0.002 % (scaled from 30.04%) 2,055,961,348 cache-references # 1028.831 M/sec (scaled from 30.03%) 53,725 cache-misses # 0.027 M/sec (scaled from 30.02%) 2.001393933 seconds time elapsed $ perf stat -B noploop 2 noploop for 2 seconds Performance counter stats for 'noploop 2': 1998.297883 task-clock-msecs # 0.998 CPUs 59 context-switches # 0.000 M/sec 0 CPU-migrations # 0.000 M/sec 119 page-faults # 0.000 M/sec 4,131,380,160 cycles # 2067.450 M/sec (scaled from 70.01%) 2,059,096,507 instructions # 0.498 IPC (scaled from 70.01%) 2,054,681,303 branches # 1028.216 M/sec (scaled from 70.01%) 25,650 branch-misses # 0.001 % (scaled from 30.05%) 2,056,283,014 cache-references # 1029.017 M/sec (scaled from 30.03%) 47,097 cache-misses # 0.024 M/sec (scaled from 30.02%) 2.001391016 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frédéric Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tom Zanussi <tzanussi@gmail.com> LKML-Reference: <4bf28fe8.914ed80a.01ca.fffff5f5@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-05-18 21:00:01 +08:00
setlocale(LC_ALL, "");
evsel_list = perf_evlist__new(NULL, NULL);
if (evsel_list == NULL)
return -ENOMEM;
argc = parse_options(argc, argv, options, stat_usage,
PARSE_OPT_STOP_AT_NON_OPTION);
perf stat: Add csv-style output This patch adds an option (-x/--field-separator) to print counts using a CSV-style output. The user can pass a custom separator. This makes it very easy to import counts directly into your favorite spreadsheet without having to write scripts. Example: $ perf stat --field-separator=, -a -- sleep 1 4009.961740,task-clock-msecs 13,context-switches 2,CPU-migrations 189,page-faults 9596385684,cycles 3493659441,instructions 872897069,branches 41562,branch-misses 22424,cache-references 1289,cache-misses Works also in non-aggregated mode: $ perf stat -x , -a -A -- sleep 1 CPU0,1002.526168,task-clock-msecs CPU1,1002.528365,task-clock-msecs CPU2,1002.523360,task-clock-msecs CPU3,1002.519878,task-clock-msecs CPU0,1,context-switches CPU1,5,context-switches CPU2,5,context-switches CPU3,6,context-switches CPU0,0,CPU-migrations CPU1,1,CPU-migrations CPU2,0,CPU-migrations CPU3,1,CPU-migrations CPU0,2,page-faults CPU1,6,page-faults CPU2,9,page-faults CPU3,174,page-faults CPU0,2399439771,cycles CPU1,2380369063,cycles CPU2,2399142710,cycles CPU3,2373161192,cycles CPU0,872900618,instructions CPU1,873030960,instructions CPU2,872714525,instructions CPU3,874460580,instructions CPU0,221556839,branches CPU1,218134342,branches CPU2,218161730,branches CPU3,218284093,branches CPU0,18556,branch-misses CPU1,1449,branch-misses CPU2,3447,branch-misses CPU3,12714,branch-misses CPU0,8330,cache-references CPU1,313844,cache-references CPU2,47993728,cache-references CPU3,826481,cache-references CPU0,272,cache-misses CPU1,5360,cache-misses CPU2,1342193,cache-misses CPU3,13992,cache-misses This second version adds the ability to name a separator and uses field-separator as the long option to be consistent with perf report. Commiter note: Since we enabled --big-num by default in 201e0b0 and -x can't be used with it, we need to notice if the user explicitely enabled or disabled -B, add code to disable big_num if the user didn't explicitely set --big_num when -x is used. Cc: David S. Miller <davem@davemloft.net> Cc: Frederik Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: paulus@samba.org Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4cf68aa7.0fedd80a.5294.1203@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-12-02 00:49:05 +08:00
if (csv_sep)
csv_output = true;
else
csv_sep = DEFAULT_SEPARATOR;
/*
* let the spreadsheet do the pretty-printing
*/
if (csv_output) {
/* User explicitely passed -B? */
if (big_num_opt == 1) {
fprintf(stderr, "-B option not supported with -x\n");
usage_with_options(stat_usage, options);
} else /* Nope, so disable big number formatting */
big_num = false;
} else if (big_num_opt == 0) /* User passed --no-big-num */
big_num = false;
if (!argc && target_pid == -1 && target_tid == -1)
usage_with_options(stat_usage, options);
if (run_count <= 0)
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
usage_with_options(stat_usage, options);
/* no_aggr, cgroup are for system-wide only */
if ((no_aggr || nr_cgroups) && !system_wide) {
fprintf(stderr, "both cgroup and no-aggregation "
"modes only available in system-wide mode\n");
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
usage_with_options(stat_usage, options);
}
perf stat: Add no-aggregation mode to -a This patch adds a new -A option to perf stat. If specified then perf stat does not aggregate counts across all monitored CPUs in system-wide mode, i.e., when using -a. This option is not supported in per-thread mode. Being able to get a per-cpu breakdown is useful to detect imbalances between CPUs when running a uniform workload than spans all monitored CPUs. The second version corrects the missing cpumap[] support, so that it works when the -C option is used. The third version fixes a missing cpumap[] in print_counter() and removes a stray patch in builtin-trace.c. Examples on a 4-way system: # perf stat -a -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': 9592808135 cycles 3490380006 instructions # 0.364 IPC 1.001584632 seconds time elapsed # perf stat -a -A -e cycles,instructions -- sleep 1 Performance counter stats for 'sleep 1': CPU0 2398163767 cycles CPU1 2398180817 cycles CPU2 2398217115 cycles CPU3 2398247483 cycles CPU0 872282046 instructions # 0.364 IPC CPU1 873481776 instructions # 0.364 IPC CPU2 872638127 instructions # 0.364 IPC CPU3 872437789 instructions # 0.364 IPC 1.001556052 seconds time elapsed Cc: David S. Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> LKML-Reference: <4ce257b5.1e07e30a.7b6b.3aa9@mx.google.com> Signed-off-by: Stephane Eranian <eranian@google.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-11-16 17:05:01 +08:00
perf stat: Add -d -d and -d -d -d options to show more CPU events Print even more detailed statistics if requested via perf stat -d: -d: detailed events, L1 and LLC data cache -d -d: more detailed events, dTLB and iTLB events -d -d -d: very detailed events, adding prefetch events Full output looks like this now: Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1703.674707 task-clock # 8.709 CPUs utilized ( +- 4.19% ) 49,068 context-switches # 0.029 M/sec ( +- 16.66% ) 8,303 CPU-migrations # 0.005 M/sec ( +- 24.90% ) 17,397 page-faults # 0.010 M/sec ( +- 0.46% ) 2,345,389,239 cycles # 1.377 GHz ( +- 4.61% ) [55.90%] 1,884,503,527 stalled-cycles-frontend # 80.35% frontend cycles idle ( +- 5.67% ) [50.39%] 743,919,737 stalled-cycles-backend # 31.72% backend cycles idle ( +- 8.75% ) [49.91%] 1,314,416,379 instructions # 0.56 insns per cycle # 1.43 stalled cycles per insn ( +- 2.53% ) [60.87%] 272,592,567 branches # 160.003 M/sec ( +- 1.74% ) [56.56%] 3,794,846 branch-misses # 1.39% of all branches ( +- 6.59% ) [58.50%] 449,982,778 L1-dcache-loads # 264.125 M/sec ( +- 2.47% ) [49.88%] 22,404,961 L1-dcache-load-misses # 4.98% of all L1-dcache hits ( +- 6.08% ) [55.05%] 6,204,750 LLC-loads # 3.642 M/sec ( +- 8.91% ) [43.75%] 1,837,411 LLC-load-misses # 1.078 M/sec ( +- 7.27% ) [12.07%] 411,440,421 L1-icache-loads # 241.502 M/sec ( +- 5.60% ) [36.52%] 27,556,832 L1-icache-load-misses # 16.175 M/sec ( +- 7.46% ) [46.72%] 464,067,627 dTLB-loads # 272.392 M/sec ( +- 4.46% ) [54.17%] 10,765,648 dTLB-load-misses # 6.319 M/sec ( +- 3.18% ) [48.68%] 1,273,080,386 iTLB-loads # 747.256 M/sec ( +- 3.38% ) [47.53%] 117,481 iTLB-load-misses # 0.069 M/sec ( +- 14.99% ) [47.01%] 4,590,653 L1-dcache-prefetches # 2.695 M/sec ( +- 4.49% ) [46.19%] 1,712,660 L1-dcache-prefetch-misses # 1.005 M/sec ( +- 3.75% ) [44.82%] 0.195622057 seconds time elapsed ( +- 6.84% ) Also clean up the attribute construction code to be appending, and factor it out into add_default_attributes(). Tweak the coverage percentage printout a bit, so that it's easier to view it alongside the +- sttddev colum. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/n/tip-to3kgu04449s64062val8b62@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu>
2011-05-19 19:30:56 +08:00
if (add_default_attributes())
goto out;
if (target_pid != -1)
target_tid = target_pid;
evsel_list->threads = thread_map__new(target_pid, target_tid);
if (evsel_list->threads == NULL) {
pr_err("Problems finding threads of monitor\n");
usage_with_options(stat_usage, options);
}
perf tools: Fix sparse CPU numbering related bugs At present, the perf subcommands that do system-wide monitoring (perf stat, perf record and perf top) don't work properly unless the online cpus are numbered 0, 1, ..., N-1. These tools ask for the number of online cpus with sysconf(_SC_NPROCESSORS_ONLN) and then try to create events for cpus 0, 1, ..., N-1. This creates problems for systems where the online cpus are numbered sparsely. For example, a POWER6 system in single-threaded mode (i.e. only running 1 hardware thread per core) will have only even-numbered cpus online. This fixes the problem by reading the /sys/devices/system/cpu/online file to find out which cpus are online. The code that does that is in tools/perf/util/cpumap.[ch], and consists of a read_cpu_map() function that sets up a cpumap[] array and returns the number of online cpus. If /sys/devices/system/cpu/online can't be read or can't be parsed successfully, it falls back to using sysconf to ask how many cpus are online and sets up an identity map in cpumap[]. The perf record, perf stat and perf top code then calls read_cpu_map() in the system-wide monitoring case (instead of sysconf) and uses cpumap[] to get the cpu numbers to pass to perf_event_open. Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> LKML-Reference: <20100310093609.GA3959@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 17:36:09 +08:00
if (system_wide)
evsel_list->cpus = cpu_map__new(cpu_list);
perf tools: Fix sparse CPU numbering related bugs At present, the perf subcommands that do system-wide monitoring (perf stat, perf record and perf top) don't work properly unless the online cpus are numbered 0, 1, ..., N-1. These tools ask for the number of online cpus with sysconf(_SC_NPROCESSORS_ONLN) and then try to create events for cpus 0, 1, ..., N-1. This creates problems for systems where the online cpus are numbered sparsely. For example, a POWER6 system in single-threaded mode (i.e. only running 1 hardware thread per core) will have only even-numbered cpus online. This fixes the problem by reading the /sys/devices/system/cpu/online file to find out which cpus are online. The code that does that is in tools/perf/util/cpumap.[ch], and consists of a read_cpu_map() function that sets up a cpumap[] array and returns the number of online cpus. If /sys/devices/system/cpu/online can't be read or can't be parsed successfully, it falls back to using sysconf to ask how many cpus are online and sets up an identity map in cpumap[]. The perf record, perf stat and perf top code then calls read_cpu_map() in the system-wide monitoring case (instead of sysconf) and uses cpumap[] to get the cpu numbers to pass to perf_event_open. Signed-off-by: Paul Mackerras <paulus@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Arnaldo Carvalho de Melo <acme@infradead.org> LKML-Reference: <20100310093609.GA3959@brick.ozlabs.ibm.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-03-10 17:36:09 +08:00
else
evsel_list->cpus = cpu_map__dummy_new();
if (evsel_list->cpus == NULL) {
perror("failed to parse CPUs map");
usage_with_options(stat_usage, options);
return -1;
}
list_for_each_entry(pos, &evsel_list->entries, node) {
if (perf_evsel__alloc_stat_priv(pos) < 0 ||
perf_evsel__alloc_counts(pos, evsel_list->cpus->nr) < 0 ||
perf_evsel__alloc_fd(pos, evsel_list->cpus->nr, evsel_list->threads->nr) < 0)
goto out_free_fd;
}
/*
* We dont want to block the signals - that would cause
* child tasks to inherit that and Ctrl-C would not work.
* What we want is for Ctrl-C to work in the exec()-ed
* task, but being ignored by perf stat itself:
*/
atexit(sig_atexit);
signal(SIGINT, skip_signal);
signal(SIGALRM, skip_signal);
signal(SIGABRT, skip_signal);
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
status = 0;
for (run_idx = 0; run_idx < run_count; run_idx++) {
if (run_count != 1 && verbose)
fprintf(stderr, "[ perf stat: executing run #%d ... ]\n", run_idx + 1);
if (sync_run)
sync();
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
status = run_perf_stat(argc, argv);
}
if (status != -1)
print_stat(argc, argv);
out_free_fd:
list_for_each_entry(pos, &evsel_list->entries, node)
perf_evsel__free_stat_priv(pos);
perf_evlist__delete_maps(evsel_list);
out:
perf_evlist__delete(evsel_list);
perf stat: Add feature to run and measure a command multiple times Add the --repeat <n> feature to perf stat, which repeats a given command up to a 100 times, collects the stats and calculates an average and a stddev. For example, the following oneliner 'perf stat' command runs hackbench 5 times and prints a tabulated result of all metrics, with averages and noise levels (in percentage) printed: aldebaran:~/linux/linux/tools/perf> ./perf stat --repeat 5 ~/hackbench 10 Time: 0.117 Time: 0.108 Time: 0.089 Time: 0.088 Time: 0.100 Performance counter stats for '/home/mingo/hackbench 10' (5 runs): 1243.989586 task-clock-msecs # 10.460 CPUs ( +- 4.720% ) 47706 context-switches # 0.038 M/sec ( +- 19.706% ) 387 CPU-migrations # 0.000 M/sec ( +- 3.608% ) 17793 page-faults # 0.014 M/sec ( +- 0.354% ) 3770941606 cycles # 3031.329 M/sec ( +- 4.621% ) 1566372416 instructions # 0.415 IPC ( +- 2.703% ) 16783421 cache-references # 13.492 M/sec ( +- 5.202% ) 7128590 cache-misses # 5.730 M/sec ( +- 7.420% ) 0.118924455 seconds time elapsed. The goal of this feature is to allow the reliance on these accurate statistics and to know how many times a command has to be repeated for the noise to go down to an acceptable level. (The -v option can be used to see a line printed out as each run progresses.) Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> LKML-Reference: <new-submission> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-13 20:57:28 +08:00
return status;
}