diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-15 09:36:24 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-11-15 09:36:24 -0800 |
commit | 0ca9b67606f0ce984b5811b0830cfd7d143f6077 (patch) | |
tree | 0352af98e9760edd8bbd1712cd0c79f77156217a /tools/perf/builtin-stat.c | |
parent | 051b29f2798b5f1a95e745613117eeb367ab4bce (diff) | |
parent | 41ac18ebfc429ce3f4d369ef07447d652999a0cd (diff) |
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates from Thomas Gleixner:
"Mostly updates to the perf tool plus two fixes to the kernel core code:
- Handle tracepoint filters correctly for inherited events (Peter
Zijlstra)
- Prevent a deadlock in perf_lock_task_context (Paul McKenney)
- Add missing newlines to some pr_err() calls (Arnaldo Carvalho de
Melo)
- Print full source file paths when using 'perf annotate --print-line
--full-paths' (Michael Petlan)
- Fix 'perf probe -d' when just one out of uprobes and kprobes is
enabled (Wang Nan)
- Add compiler.h to list.h to fix 'make perf-tar-src-pkg' generated
tarballs, i.e. out of tree building (Arnaldo Carvalho de Melo)
- Add the llvm-src-base.c and llvm-src-kbuild.c files, generated by
the 'perf test' LLVM entries, when running it in-tree, to
.gitignore (Yunlong Song)
- libbpf error reporting improvements, using a strerror interface to
more precisely tell the user about problems with the provided
scriptlet, be it in C or as a ready made object file (Wang Nan)
- Do not be case sensitive when searching for matching 'perf test'
entries (Arnaldo Carvalho de Melo)
- Inform the user about objdump failures in 'perf annotate' (Andi
Kleen)
- Improve the LLVM 'perf test' entry, introduce a new ones for BPF
and kbuild tests to check the environment used by clang to compile
.c scriptlets (Wang Nan)"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
perf/x86/intel/rapl: Remove the unused RAPL_EVENT_DESC() macro
tools include: Add compiler.h to list.h
perf probe: Verify parameters in two functions
perf session: Add missing newlines to some pr_err() calls
perf annotate: Support full source file paths for srcline fix
perf test: Add llvm-src-base.c and llvm-src-kbuild.c to .gitignore
perf: Fix inherited events vs. tracepoint filters
perf: Disable IRQs across RCU RS CS that acquires scheduler lock
perf test: Do not be case sensitive when searching for matching tests
perf test: Add 'perf test BPF'
perf test: Enhance the LLVM tests: add kbuild test
perf test: Enhance the LLVM test: update basic BPF test program
perf bpf: Improve BPF related error messages
perf tools: Make fetch_kernel_version() publicly available
bpf tools: Add new API bpf_object__get_kversion()
bpf tools: Improve libbpf error reporting
perf probe: Cleanup find_perf_probe_point_from_map to reduce redundancy
perf annotate: Inform the user about objdump failures in --stdio
perf stat: Make stat options global
perf sched latency: Fix thread pid reuse issue
...
Diffstat (limited to 'tools/perf/builtin-stat.c')
-rw-r--r-- | tools/perf/builtin-stat.c | 222 |
1 files changed, 102 insertions, 120 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 2f438f76cceb..e77880b5094d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -122,6 +122,9 @@ static bool forever = false; static struct timespec ref_time; static struct cpu_map *aggr_map; static aggr_get_id_t aggr_get_id; +static bool append_file; +static const char *output_name; +static int output_fd; static volatile int done = 0; @@ -513,15 +516,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); - - if (csv_output || stat_config.interval) - return; - - if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK)) - fprintf(output, " # %8.3f CPUs utilized ", - avg / avg_stats(&walltime_nsecs_stats)); - else - fprintf(output, " "); } static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) @@ -529,7 +523,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) FILE *output = stat_config.output; double sc = evsel->scale; const char *fmt; - int cpu = cpu_map__id_to_cpu(id); if (csv_output) { fmt = sc != 1.0 ? "%.2f%s" : "%.0f%s"; @@ -542,9 +535,6 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) aggr_printout(evsel, id, nr); - if (stat_config.aggr_mode == AGGR_GLOBAL) - cpu = 0; - fprintf(output, fmt, avg, csv_sep); if (evsel->unit) @@ -556,12 +546,24 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) if (evsel->cgrp) fprintf(output, "%s%s", csv_sep, evsel->cgrp->name); +} - if (csv_output || stat_config.interval) - return; +static void printout(int id, int nr, struct perf_evsel *counter, double uval) +{ + int cpu = cpu_map__id_to_cpu(id); + + if (stat_config.aggr_mode == AGGR_GLOBAL) + cpu = 0; - perf_stat__print_shadow_stats(output, evsel, avg, cpu, - stat_config.aggr_mode); + if (nsec_counter(counter)) + nsec_printout(id, nr, counter, uval); + else + abs_printout(id, nr, counter, uval); + + if (!csv_output && !stat_config.interval) + perf_stat__print_shadow_stats(stat_config.output, counter, + uval, cpu, + stat_config.aggr_mode); } static void print_aggr(char *prefix) @@ -617,12 +619,7 @@ static void print_aggr(char *prefix) continue; } uval = val * counter->scale; - - if (nsec_counter(counter)) - nsec_printout(id, nr, counter, uval); - else - abs_printout(id, nr, counter, uval); - + printout(id, nr, counter, uval); if (!csv_output) print_noise(counter, 1.0); @@ -653,11 +650,7 @@ static void print_aggr_thread(struct perf_evsel *counter, char *prefix) fprintf(output, "%s", prefix); uval = val * counter->scale; - - if (nsec_counter(counter)) - nsec_printout(thread, 0, counter, uval); - else - abs_printout(thread, 0, counter, uval); + printout(thread, 0, counter, uval); if (!csv_output) print_noise(counter, 1.0); @@ -707,11 +700,7 @@ static void print_counter_aggr(struct perf_evsel *counter, char *prefix) } uval = avg * counter->scale; - - if (nsec_counter(counter)) - nsec_printout(-1, 0, counter, uval); - else - abs_printout(-1, 0, counter, uval); + printout(-1, 0, counter, uval); print_noise(counter, avg); @@ -764,12 +753,7 @@ static void print_counter(struct perf_evsel *counter, char *prefix) } uval = val * counter->scale; - - if (nsec_counter(counter)) - nsec_printout(cpu, 0, counter, uval); - else - abs_printout(cpu, 0, counter, uval); - + printout(cpu, 0, counter, uval); if (!csv_output) print_noise(counter, 1.0); print_running(run, ena); @@ -946,6 +930,67 @@ static int stat__set_big_num(const struct option *opt __maybe_unused, return 0; } +static const struct option stat_options[] = { + OPT_BOOLEAN('T', "transaction", &transaction_run, + "hardware transaction statistics"), + 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_STRING('p', "pid", &target.pid, "pid", + "stat events on existing process id"), + OPT_STRING('t', "tid", &target.tid, "tid", + "stat events on existing thread id"), + OPT_BOOLEAN('a', "all-cpus", &target.system_wide, + "system-wide collection from all CPUs"), + OPT_BOOLEAN('g', "group", &group, + "put the counters into a counter group"), + OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"), + OPT_INCR('v', "verbose", &verbose, + "be more verbose (show counter open errors, etc)"), + OPT_INTEGER('r', "repeat", &run_count, + "repeat command and print average + stddev (max: 100, forever: 0)"), + OPT_BOOLEAN('n', "null", &null_run, + "null run - dont start any counters"), + OPT_INCR('d', "detailed", &detailed_run, + "detailed run - start a lot of events"), + OPT_BOOLEAN('S', "sync", &sync_run, + "call sync() before starting a run"), + OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, + "print large numbers with thousands\' separators", + stat__set_big_num), + OPT_STRING('C', "cpu", &target.cpu_list, "cpu", + "list of cpus to monitor in system-wide"), + OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode, + "disable CPU count aggregation", AGGR_NONE), + 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_STRING('o', "output", &output_name, "file", "output file name"), + OPT_BOOLEAN(0, "append", &append_file, "append to the output file"), + OPT_INTEGER(0, "log-fd", &output_fd, + "log output to fd, instead of stderr"), + OPT_STRING(0, "pre", &pre_cmd, "command", + "command to run prior to the measured command"), + OPT_STRING(0, "post", &post_cmd, "command", + "command to run after to the measured command"), + OPT_UINTEGER('I', "interval-print", &stat_config.interval, + "print counts at regular interval in ms (>= 10)"), + OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode, + "aggregate counts per processor socket", AGGR_SOCKET), + OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode, + "aggregate counts per physical processor core", AGGR_CORE), + OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode, + "aggregate counts per thread", AGGR_THREAD), + OPT_UINTEGER('D', "delay", &initial_delay, + "ms to wait before starting measurement after program start"), + OPT_END() +}; + static int perf_stat__get_socket(struct cpu_map *map, int cpu) { return cpu_map__get_socket(map, cpu, NULL); @@ -1193,69 +1238,6 @@ static int add_default_attributes(void) int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) { - bool append_file = false; - int output_fd = 0; - const char *output_name = NULL; - const struct option options[] = { - OPT_BOOLEAN('T', "transaction", &transaction_run, - "hardware transaction statistics"), - 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_STRING('p', "pid", &target.pid, "pid", - "stat events on existing process id"), - OPT_STRING('t', "tid", &target.tid, "tid", - "stat events on existing thread id"), - OPT_BOOLEAN('a', "all-cpus", &target.system_wide, - "system-wide collection from all CPUs"), - OPT_BOOLEAN('g', "group", &group, - "put the counters into a counter group"), - OPT_BOOLEAN('c', "scale", &stat_config.scale, "scale/normalize counters"), - OPT_INCR('v', "verbose", &verbose, - "be more verbose (show counter open errors, etc)"), - OPT_INTEGER('r', "repeat", &run_count, - "repeat command and print average + stddev (max: 100, forever: 0)"), - OPT_BOOLEAN('n', "null", &null_run, - "null run - dont start any counters"), - OPT_INCR('d', "detailed", &detailed_run, - "detailed run - start a lot of events"), - OPT_BOOLEAN('S', "sync", &sync_run, - "call sync() before starting a run"), - OPT_CALLBACK_NOOPT('B', "big-num", NULL, NULL, - "print large numbers with thousands\' separators", - stat__set_big_num), - OPT_STRING('C', "cpu", &target.cpu_list, "cpu", - "list of cpus to monitor in system-wide"), - OPT_SET_UINT('A', "no-aggr", &stat_config.aggr_mode, - "disable CPU count aggregation", AGGR_NONE), - 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_STRING('o', "output", &output_name, "file", "output file name"), - OPT_BOOLEAN(0, "append", &append_file, "append to the output file"), - OPT_INTEGER(0, "log-fd", &output_fd, - "log output to fd, instead of stderr"), - OPT_STRING(0, "pre", &pre_cmd, "command", - "command to run prior to the measured command"), - OPT_STRING(0, "post", &post_cmd, "command", - "command to run after to the measured command"), - OPT_UINTEGER('I', "interval-print", &stat_config.interval, - "print counts at regular interval in ms (>= 10)"), - OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode, - "aggregate counts per processor socket", AGGR_SOCKET), - OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode, - "aggregate counts per physical processor core", AGGR_CORE), - OPT_SET_UINT(0, "per-thread", &stat_config.aggr_mode, - "aggregate counts per thread", AGGR_THREAD), - OPT_UINTEGER('D', "delay", &initial_delay, - "ms to wait before starting measurement after program start"), - OPT_END() - }; const char * const stat_usage[] = { "perf stat [<options>] [<command>]", NULL @@ -1271,7 +1253,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (evsel_list == NULL) return -ENOMEM; - argc = parse_options(argc, argv, options, stat_usage, + argc = parse_options(argc, argv, stat_options, stat_usage, PARSE_OPT_STOP_AT_NON_OPTION); interval = stat_config.interval; @@ -1281,14 +1263,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (output_name && output_fd) { fprintf(stderr, "cannot use both --output and --log-fd\n"); - parse_options_usage(stat_usage, options, "o", 1); - parse_options_usage(NULL, options, "log-fd", 0); + parse_options_usage(stat_usage, stat_options, "o", 1); + parse_options_usage(NULL, stat_options, "log-fd", 0); goto out; } if (output_fd < 0) { fprintf(stderr, "argument to --log-fd must be a > 0\n"); - parse_options_usage(stat_usage, options, "log-fd", 0); + parse_options_usage(stat_usage, stat_options, "log-fd", 0); goto out; } @@ -1328,8 +1310,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) /* User explicitly passed -B? */ if (big_num_opt == 1) { fprintf(stderr, "-B option not supported with -x\n"); - parse_options_usage(stat_usage, options, "B", 1); - parse_options_usage(NULL, options, "x", 1); + parse_options_usage(stat_usage, stat_options, "B", 1); + parse_options_usage(NULL, stat_options, "x", 1); goto out; } else /* Nope, so disable big number formatting */ big_num = false; @@ -1337,11 +1319,11 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) big_num = false; if (!argc && target__none(&target)) - usage_with_options(stat_usage, options); + usage_with_options(stat_usage, stat_options); if (run_count < 0) { pr_err("Run count must be a positive number\n"); - parse_options_usage(stat_usage, options, "r", 1); + parse_options_usage(stat_usage, stat_options, "r", 1); goto out; } else if (run_count == 0) { forever = true; @@ -1351,8 +1333,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if ((stat_config.aggr_mode == AGGR_THREAD) && !target__has_task(&target)) { fprintf(stderr, "The --per-thread option is only available " "when monitoring via -p -t options.\n"); - parse_options_usage(NULL, options, "p", 1); - parse_options_usage(NULL, options, "t", 1); + parse_options_usage(NULL, stat_options, "p", 1); + parse_options_usage(NULL, stat_options, "t", 1); goto out; } @@ -1366,9 +1348,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) fprintf(stderr, "both cgroup and no-aggregation " "modes only available in system-wide mode\n"); - parse_options_usage(stat_usage, options, "G", 1); - parse_options_usage(NULL, options, "A", 1); - parse_options_usage(NULL, options, "a", 1); + parse_options_usage(stat_usage, stat_options, "G", 1); + parse_options_usage(NULL, stat_options, "A", 1); + parse_options_usage(NULL, stat_options, "a", 1); goto out; } @@ -1380,12 +1362,12 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (perf_evlist__create_maps(evsel_list, &target) < 0) { if (target__has_task(&target)) { pr_err("Problems finding threads of monitor\n"); - parse_options_usage(stat_usage, options, "p", 1); - parse_options_usage(NULL, options, "t", 1); + parse_options_usage(stat_usage, stat_options, "p", 1); + parse_options_usage(NULL, stat_options, "t", 1); } else if (target__has_cpu(&target)) { perror("failed to parse CPUs map"); - parse_options_usage(stat_usage, options, "C", 1); - parse_options_usage(NULL, options, "a", 1); + parse_options_usage(stat_usage, stat_options, "C", 1); + parse_options_usage(NULL, stat_options, "a", 1); } goto out; } @@ -1400,7 +1382,7 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) if (interval && interval < 100) { if (interval < 10) { pr_err("print interval must be >= 10ms\n"); - parse_options_usage(stat_usage, options, "I", 1); + parse_options_usage(stat_usage, stat_options, "I", 1); goto out; } else pr_warning("print interval < 100ms. " |