diff options
Diffstat (limited to 'tools/perf/builtin-stat.c')
-rw-r--r-- | tools/perf/builtin-stat.c | 884 |
1 files changed, 222 insertions, 662 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index f7b821878..d99d850e1 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -67,14 +67,11 @@ #define CNTR_NOT_SUPPORTED "<not supported>" #define CNTR_NOT_COUNTED "<not counted>" -static void print_stat(int argc, const char **argv); -static void print_counter_aggr(struct perf_evsel *counter, char *prefix); -static void print_counter(struct perf_evsel *counter, char *prefix); -static void print_aggr(char *prefix); +static void print_counters(struct timespec *ts, int argc, const char **argv); /* Default events used for perf stat -T */ -static const char * const transaction_attrs[] = { - "task-clock", +static const char *transaction_attrs = { + "task-clock," "{" "instructions," "cycles," @@ -86,8 +83,8 @@ static const char * const transaction_attrs[] = { }; /* More limited version when the CPU does not have all events. */ -static const char * const transaction_limited_attrs[] = { - "task-clock", +static const char * transaction_limited_attrs = { + "task-clock," "{" "instructions," "cycles," @@ -96,30 +93,12 @@ static const char * const transaction_limited_attrs[] = { "}" }; -/* must match transaction_attrs and the beginning limited_attrs */ -enum { - T_TASK_CLOCK, - T_INSTRUCTIONS, - T_CYCLES, - T_CYCLES_IN_TX, - T_TRANSACTION_START, - T_ELISION_START, - T_CYCLES_IN_TX_CP, -}; - static struct perf_evlist *evsel_list; static struct target target = { .uid = UINT_MAX, }; -enum aggr_mode { - AGGR_NONE, - AGGR_GLOBAL, - AGGR_SOCKET, - AGGR_CORE, -}; - static int run_count = 1; static bool no_inherit = false; static bool scale = true; @@ -147,10 +126,6 @@ static int (*aggr_get_id)(struct cpu_map *m, int cpu); static volatile int done = 0; -struct perf_stat { - struct stats res_stats[3]; -}; - static inline void diff_timespec(struct timespec *r, struct timespec *a, struct timespec *b) { @@ -163,132 +138,10 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a, } } -static inline struct cpu_map *perf_evsel__cpus(struct perf_evsel *evsel) -{ - return (evsel->cpus && !target.cpu_list) ? evsel->cpus : evsel_list->cpus; -} - -static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) -{ - return perf_evsel__cpus(evsel)->nr; -} - -static void perf_evsel__reset_stat_priv(struct perf_evsel *evsel) -{ - int i; - struct perf_stat *ps = evsel->priv; - - for (i = 0; i < 3; i++) - init_stats(&ps->res_stats[i]); -} - -static int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel) -{ - evsel->priv = zalloc(sizeof(struct perf_stat)); - if (evsel->priv == NULL) - return -ENOMEM; - perf_evsel__reset_stat_priv(evsel); - return 0; -} - -static void perf_evsel__free_stat_priv(struct perf_evsel *evsel) -{ - zfree(&evsel->priv); -} - -static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel) -{ - void *addr; - size_t sz; - - sz = sizeof(*evsel->counts) + - (perf_evsel__nr_cpus(evsel) * sizeof(struct perf_counts_values)); - - addr = zalloc(sz); - if (!addr) - return -ENOMEM; - - evsel->prev_raw_counts = addr; - - return 0; -} - -static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) -{ - zfree(&evsel->prev_raw_counts); -} - -static void perf_evlist__free_stats(struct perf_evlist *evlist) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - perf_evsel__free_stat_priv(evsel); - perf_evsel__free_counts(evsel); - perf_evsel__free_prev_raw_counts(evsel); - } -} - -static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - if (perf_evsel__alloc_stat_priv(evsel) < 0 || - perf_evsel__alloc_counts(evsel, perf_evsel__nr_cpus(evsel)) < 0 || - (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel) < 0)) - goto out_free; - } - - return 0; - -out_free: - perf_evlist__free_stats(evlist); - return -1; -} - -static struct stats runtime_nsecs_stats[MAX_NR_CPUS]; -static struct stats runtime_cycles_stats[MAX_NR_CPUS]; -static struct stats runtime_stalled_cycles_front_stats[MAX_NR_CPUS]; -static struct stats runtime_stalled_cycles_back_stats[MAX_NR_CPUS]; -static struct stats runtime_branches_stats[MAX_NR_CPUS]; -static struct stats runtime_cacherefs_stats[MAX_NR_CPUS]; -static struct stats runtime_l1_dcache_stats[MAX_NR_CPUS]; -static struct stats runtime_l1_icache_stats[MAX_NR_CPUS]; -static struct stats runtime_ll_cache_stats[MAX_NR_CPUS]; -static struct stats runtime_itlb_cache_stats[MAX_NR_CPUS]; -static struct stats runtime_dtlb_cache_stats[MAX_NR_CPUS]; -static struct stats runtime_cycles_in_tx_stats[MAX_NR_CPUS]; -static struct stats walltime_nsecs_stats; -static struct stats runtime_transaction_stats[MAX_NR_CPUS]; -static struct stats runtime_elision_stats[MAX_NR_CPUS]; - -static void perf_stat__reset_stats(struct perf_evlist *evlist) +static void perf_stat__reset_stats(void) { - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - perf_evsel__reset_stat_priv(evsel); - perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel)); - } - - memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats)); - memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats)); - memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats)); - memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats)); - memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats)); - memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats)); - memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats)); - memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats)); - memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats)); - memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats)); - memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats)); - memset(runtime_cycles_in_tx_stats, 0, - sizeof(runtime_cycles_in_tx_stats)); - memset(runtime_transaction_stats, 0, - sizeof(runtime_transaction_stats)); - memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats)); - memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats)); + perf_evlist__reset_stats(evsel_list); + perf_stat__reset_shadow_stats(); } static int create_perf_stat_counter(struct perf_evsel *evsel) @@ -325,70 +178,6 @@ static inline int nsec_counter(struct perf_evsel *evsel) return 0; } -static struct perf_evsel *nth_evsel(int n) -{ - static struct perf_evsel **array; - static int array_len; - struct perf_evsel *ev; - int j; - - /* Assumes this only called when evsel_list does not change anymore. */ - if (!array) { - evlist__for_each(evsel_list, ev) - array_len++; - array = malloc(array_len * sizeof(void *)); - if (!array) - exit(ENOMEM); - j = 0; - evlist__for_each(evsel_list, ev) - array[j++] = ev; - } - if (n < array_len) - return array[n]; - return NULL; -} - -/* - * 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, - int cpu) -{ - if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK)) - update_stats(&runtime_nsecs_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES)) - update_stats(&runtime_cycles_stats[cpu], count[0]); - else if (transaction_run && - perf_evsel__cmp(counter, nth_evsel(T_CYCLES_IN_TX))) - update_stats(&runtime_cycles_in_tx_stats[cpu], count[0]); - else if (transaction_run && - perf_evsel__cmp(counter, nth_evsel(T_TRANSACTION_START))) - update_stats(&runtime_transaction_stats[cpu], count[0]); - else if (transaction_run && - perf_evsel__cmp(counter, nth_evsel(T_ELISION_START))) - update_stats(&runtime_elision_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) - update_stats(&runtime_stalled_cycles_front_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND)) - update_stats(&runtime_stalled_cycles_back_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS)) - update_stats(&runtime_branches_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES)) - update_stats(&runtime_cacherefs_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D)) - update_stats(&runtime_l1_dcache_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I)) - update_stats(&runtime_l1_icache_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL)) - update_stats(&runtime_ll_cache_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB)) - update_stats(&runtime_dtlb_cache_stats[cpu], count[0]); - else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB)) - update_stats(&runtime_itlb_cache_stats[cpu], count[0]); -} - static void zero_per_pkg(struct perf_evsel *counter) { if (counter->per_pkg_mask) @@ -425,8 +214,9 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip) return 0; } -static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, - struct perf_counts_values *count) +static int +process_counter_values(struct perf_evsel *evsel, int cpu, int thread, + struct perf_counts_values *count) { struct perf_counts_values *aggr = &evsel->counts->aggr; static struct perf_counts_values zero; @@ -441,15 +231,15 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, count = &zero; switch (aggr_mode) { + case AGGR_THREAD: case AGGR_CORE: case AGGR_SOCKET: case AGGR_NONE: if (!evsel->snapshot) - perf_evsel__compute_deltas(evsel, cpu, count); + perf_evsel__compute_deltas(evsel, cpu, thread, count); perf_counts_values__scale(count, scale, NULL); - evsel->counts->cpu[cpu] = *count; if (aggr_mode == AGGR_NONE) - update_shadow_stats(evsel, count->values, cpu); + perf_stat__update_shadow_stats(evsel, count->values, cpu); break; case AGGR_GLOBAL: aggr->val += count->val; @@ -464,26 +254,48 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, return 0; } -static int read_counter(struct perf_evsel *counter); +static int process_counter_maps(struct perf_evsel *counter) +{ + int nthreads = thread_map__nr(counter->threads); + int ncpus = perf_evsel__nr_cpus(counter); + int cpu, thread; -/* - * Read out the results of a single counter: - * aggregate counts across CPUs in system-wide mode - */ -static int read_counter_aggr(struct perf_evsel *counter) + if (counter->system_wide) + nthreads = 1; + + for (thread = 0; thread < nthreads; thread++) { + for (cpu = 0; cpu < ncpus; cpu++) { + if (process_counter_values(counter, cpu, thread, + perf_counts(counter->counts, cpu, thread))) + return -1; + } + } + + return 0; +} + +static int process_counter(struct perf_evsel *counter) { struct perf_counts_values *aggr = &counter->counts->aggr; struct perf_stat *ps = counter->priv; u64 *count = counter->counts->aggr.values; - int i; + int i, ret; aggr->val = aggr->ena = aggr->run = 0; + init_stats(ps->res_stats); - if (read_counter(counter)) - return -1; + if (counter->per_pkg) + zero_per_pkg(counter); + + ret = process_counter_maps(counter); + if (ret) + return ret; + + if (aggr_mode != AGGR_GLOBAL) + return 0; if (!counter->snapshot) - perf_evsel__compute_deltas(counter, -1, aggr); + perf_evsel__compute_deltas(counter, -1, -1, aggr); perf_counts_values__scale(aggr, scale, &counter->counts->scaled); for (i = 0; i < 3; i++) @@ -497,7 +309,7 @@ static int read_counter_aggr(struct perf_evsel *counter) /* * Save the full runtime - to allow normalization during printout: */ - update_shadow_stats(counter, count, 0); + perf_stat__update_shadow_stats(counter, count, 0); return 0; } @@ -518,12 +330,12 @@ static int read_counter(struct perf_evsel *counter) if (counter->system_wide) nthreads = 1; - if (counter->per_pkg) - zero_per_pkg(counter); - for (thread = 0; thread < nthreads; thread++) { for (cpu = 0; cpu < ncpus; cpu++) { - if (perf_evsel__read_cb(counter, cpu, thread, read_cb)) + struct perf_counts_values *count; + + count = perf_counts(counter->counts, cpu, thread); + if (perf_evsel__read(counter, cpu, thread, count)) return -1; } } @@ -531,68 +343,34 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void print_interval(void) +static void read_counters(bool close_counters) { - static int num_print_interval; struct perf_evsel *counter; - struct perf_stat *ps; - struct timespec ts, rs; - char prefix[64]; - if (aggr_mode == AGGR_GLOBAL) { - evlist__for_each(evsel_list, counter) { - ps = counter->priv; - memset(ps->res_stats, 0, sizeof(ps->res_stats)); - read_counter_aggr(counter); - } - } else { - evlist__for_each(evsel_list, counter) { - ps = counter->priv; - memset(ps->res_stats, 0, sizeof(ps->res_stats)); - read_counter(counter); - } - } + evlist__for_each(evsel_list, counter) { + if (read_counter(counter)) + pr_warning("failed to read counter %s\n", counter->name); - clock_gettime(CLOCK_MONOTONIC, &ts); - diff_timespec(&rs, &ts, &ref_time); - sprintf(prefix, "%6lu.%09lu%s", rs.tv_sec, rs.tv_nsec, csv_sep); + if (process_counter(counter)) + pr_warning("failed to process counter %s\n", counter->name); - if (num_print_interval == 0 && !csv_output) { - switch (aggr_mode) { - case AGGR_SOCKET: - fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit"); - break; - case AGGR_CORE: - fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit"); - break; - case AGGR_NONE: - fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit"); - break; - case AGGR_GLOBAL: - default: - fprintf(output, "# time counts %*s events\n", unit_width, "unit"); + if (close_counters) { + perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), + thread_map__nr(evsel_list->threads)); } } +} - if (++num_print_interval == 25) - num_print_interval = 0; +static void process_interval(void) +{ + struct timespec ts, rs; - switch (aggr_mode) { - case AGGR_CORE: - case AGGR_SOCKET: - print_aggr(prefix); - break; - case AGGR_NONE: - evlist__for_each(evsel_list, counter) - print_counter(counter, prefix); - break; - case AGGR_GLOBAL: - default: - evlist__for_each(evsel_list, counter) - print_counter_aggr(counter, prefix); - } + read_counters(false); - fflush(output); + clock_gettime(CLOCK_MONOTONIC, &ts); + diff_timespec(&rs, &ts, &ref_time); + + print_counters(&rs, 0, NULL); } static void handle_initial_delay(void) @@ -665,7 +443,10 @@ static int __run_perf_stat(int argc, const char **argv) ui__warning("%s event is not supported by the kernel.\n", perf_evsel__name(counter)); counter->supported = false; - continue; + + if ((counter->leader != counter) || + !(counter->leader->nr_members > 1)) + continue; } perf_evsel__open_strerror(counter, &target, @@ -704,7 +485,7 @@ static int __run_perf_stat(int argc, const char **argv) if (interval) { while (!waitpid(child_pid, &status, WNOHANG)) { nanosleep(&ts, NULL); - print_interval(); + process_interval(); } } wait(&status); @@ -722,7 +503,7 @@ static int __run_perf_stat(int argc, const char **argv) while (!done) { nanosleep(&ts, NULL); if (interval) - print_interval(); + process_interval(); } } @@ -730,18 +511,7 @@ static int __run_perf_stat(int argc, const char **argv) update_stats(&walltime_nsecs_stats, t1 - t0); - if (aggr_mode == AGGR_GLOBAL) { - evlist__for_each(evsel_list, counter) { - read_counter_aggr(counter); - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), - thread_map__nr(evsel_list->threads)); - } - } else { - evlist__for_each(evsel_list, counter) { - read_counter(counter); - perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), 1); - } - } + read_counters(true); return WEXITSTATUS(status); } @@ -833,6 +603,14 @@ static void aggr_printout(struct perf_evsel *evsel, int id, int nr) csv_output ? 0 : -4, perf_evsel__cpus(evsel)->map[id], csv_sep); break; + case AGGR_THREAD: + fprintf(output, "%*s-%*d%s", + csv_output ? 0 : 16, + thread_map__comm(evsel->threads, id), + csv_output ? 0 : -8, + thread_map__pid(evsel->threads, id), + csv_sep); + break; case AGGR_GLOBAL: default: break; @@ -875,188 +653,8 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg) fprintf(output, " "); } -/* used for get_ratio_color() */ -enum grc_type { - GRC_STALLED_CYCLES_FE, - GRC_STALLED_CYCLES_BE, - GRC_CACHE_MISSES, - GRC_MAX_NR -}; - -static const char *get_ratio_color(enum grc_type type, double ratio) -{ - static const double grc_table[GRC_MAX_NR][3] = { - [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 }, - [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 }, - [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 }, - }; - const char *color = PERF_COLOR_NORMAL; - - if (ratio > grc_table[type][0]) - color = PERF_COLOR_RED; - else if (ratio > grc_table[type][1]) - color = PERF_COLOR_MAGENTA; - else if (ratio > grc_table[type][2]) - color = PERF_COLOR_YELLOW; - - return color; -} - -static void print_stalled_cycles_frontend(int cpu, - struct perf_evsel *evsel - __maybe_unused, 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 = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " frontend cycles idle "); -} - -static void print_stalled_cycles_backend(int cpu, - struct perf_evsel *evsel - __maybe_unused, 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 = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " backend cycles idle "); -} - -static void print_branch_misses(int cpu, - struct perf_evsel *evsel __maybe_unused, - 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 = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " of all branches "); -} - -static void print_l1_dcache_misses(int cpu, - struct perf_evsel *evsel __maybe_unused, - 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 = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " of all L1-dcache hits "); -} - -static void print_l1_icache_misses(int cpu, - struct perf_evsel *evsel __maybe_unused, - 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 = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " of all L1-icache hits "); -} - -static void print_dtlb_cache_misses(int cpu, - struct perf_evsel *evsel __maybe_unused, - 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 = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " of all dTLB cache hits "); -} - -static void print_itlb_cache_misses(int cpu, - struct perf_evsel *evsel __maybe_unused, - 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 = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " of all iTLB cache hits "); -} - -static void print_ll_cache_misses(int cpu, - struct perf_evsel *evsel __maybe_unused, - 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 = get_ratio_color(GRC_CACHE_MISSES, ratio); - - fprintf(output, " # "); - color_fprintf(output, color, "%6.2f%%", ratio); - fprintf(output, " of all LL-cache hits "); -} - static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) { - double total, ratio = 0.0, total2; double sc = evsel->scale; const char *fmt; int cpu = cpu_map__id_to_cpu(id); @@ -1090,138 +688,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg) if (csv_output || interval) return; - if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) { - total = avg_stats(&runtime_cycles_stats[cpu]); - if (total) { - ratio = avg / total; - fprintf(output, " # %5.2f insns per cycle ", ratio); - } else { - fprintf(output, " "); - } - total = avg_stats(&runtime_stalled_cycles_front_stats[cpu]); - total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[cpu])); - - if (total && avg) { - ratio = total / avg; - fprintf(output, "\n"); - if (aggr_mode == AGGR_NONE) - fprintf(output, " "); - fprintf(output, " # %5.2f stalled cycles per insn", ratio); - } - - } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) && - 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)) && - 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; - - fprintf(output, " # %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); - } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) { - total = avg_stats(&runtime_nsecs_stats[cpu]); - - if (total) { - ratio = avg / total; - fprintf(output, " # %8.3f GHz ", ratio); - } else { - fprintf(output, " "); - } - } else if (transaction_run && - perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX))) { - total = avg_stats(&runtime_cycles_stats[cpu]); - if (total) - fprintf(output, - " # %5.2f%% transactional cycles ", - 100.0 * (avg / total)); - } else if (transaction_run && - perf_evsel__cmp(evsel, nth_evsel(T_CYCLES_IN_TX_CP))) { - total = avg_stats(&runtime_cycles_stats[cpu]); - total2 = avg_stats(&runtime_cycles_in_tx_stats[cpu]); - if (total2 < avg) - total2 = avg; - if (total) - fprintf(output, - " # %5.2f%% aborted cycles ", - 100.0 * ((total2-avg) / total)); - } else if (transaction_run && - perf_evsel__cmp(evsel, nth_evsel(T_TRANSACTION_START)) && - avg > 0 && - runtime_cycles_in_tx_stats[cpu].n != 0) { - total = avg_stats(&runtime_cycles_in_tx_stats[cpu]); - - if (total) - ratio = total / avg; - - fprintf(output, " # %8.0f cycles / transaction ", ratio); - } else if (transaction_run && - perf_evsel__cmp(evsel, nth_evsel(T_ELISION_START)) && - avg > 0 && - runtime_cycles_in_tx_stats[cpu].n != 0) { - total = avg_stats(&runtime_cycles_in_tx_stats[cpu]); - - if (total) - ratio = total / avg; - - fprintf(output, " # %8.0f cycles / elision ", ratio); - } else if (runtime_nsecs_stats[cpu].n != 0) { - char unit = 'M'; - - total = avg_stats(&runtime_nsecs_stats[cpu]); - - if (total) - ratio = 1000.0 * avg / total; - if (ratio < 0.001) { - ratio *= 1000; - unit = 'K'; - } - - fprintf(output, " # %8.3f %c/sec ", ratio, unit); - } else { - fprintf(output, " "); - } + perf_stat__print_shadow_stats(output, evsel, avg, cpu, aggr_mode); } static void print_aggr(char *prefix) @@ -1244,9 +711,9 @@ static void print_aggr(char *prefix) s2 = aggr_get_id(evsel_list->cpus, cpu2); if (s2 != id) continue; - val += counter->counts->cpu[cpu].val; - ena += counter->counts->cpu[cpu].ena; - run += counter->counts->cpu[cpu].run; + val += perf_counts(counter->counts, cpu, 0)->val; + ena += perf_counts(counter->counts, cpu, 0)->ena; + run += perf_counts(counter->counts, cpu, 0)->run; nr++; } if (prefix) @@ -1292,6 +759,40 @@ static void print_aggr(char *prefix) } } +static void print_aggr_thread(struct perf_evsel *counter, char *prefix) +{ + int nthreads = thread_map__nr(counter->threads); + int ncpus = cpu_map__nr(counter->cpus); + int cpu, thread; + double uval; + + for (thread = 0; thread < nthreads; thread++) { + u64 ena = 0, run = 0, val = 0; + + for (cpu = 0; cpu < ncpus; cpu++) { + val += perf_counts(counter->counts, cpu, thread)->val; + ena += perf_counts(counter->counts, cpu, thread)->ena; + run += perf_counts(counter->counts, cpu, thread)->run; + } + + if (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); + + if (!csv_output) + print_noise(counter, 1.0); + + print_running(run, ena); + fputc('\n', output); + } +} + /* * Print out the results of a single counter: * aggregated counts in system-wide mode @@ -1354,9 +855,9 @@ static void print_counter(struct perf_evsel *counter, char *prefix) int cpu; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - val = counter->counts->cpu[cpu].val; - ena = counter->counts->cpu[cpu].ena; - run = counter->counts->cpu[cpu].run; + val = perf_counts(counter->counts, cpu, 0)->val; + ena = perf_counts(counter->counts, cpu, 0)->ena; + run = perf_counts(counter->counts, cpu, 0)->run; if (prefix) fprintf(output, "%s", prefix); @@ -1401,9 +902,38 @@ static void print_counter(struct perf_evsel *counter, char *prefix) } } -static void print_stat(int argc, const char **argv) +static void print_interval(char *prefix, struct timespec *ts) +{ + static int num_print_interval; + + sprintf(prefix, "%6lu.%09lu%s", ts->tv_sec, ts->tv_nsec, csv_sep); + + if (num_print_interval == 0 && !csv_output) { + switch (aggr_mode) { + case AGGR_SOCKET: + fprintf(output, "# time socket cpus counts %*s events\n", unit_width, "unit"); + break; + case AGGR_CORE: + fprintf(output, "# time core cpus counts %*s events\n", unit_width, "unit"); + break; + case AGGR_NONE: + fprintf(output, "# time CPU counts %*s events\n", unit_width, "unit"); + break; + case AGGR_THREAD: + fprintf(output, "# time comm-pid counts %*s events\n", unit_width, "unit"); + break; + case AGGR_GLOBAL: + default: + fprintf(output, "# time counts %*s events\n", unit_width, "unit"); + } + } + + if (++num_print_interval == 25) + num_print_interval = 0; +} + +static void print_header(int argc, const char **argv) { - struct perf_evsel *counter; int i; fflush(stdout); @@ -1429,36 +959,57 @@ static void print_stat(int argc, const char **argv) fprintf(output, " (%d runs)", run_count); fprintf(output, ":\n\n"); } +} + +static void print_footer(void) +{ + if (!null_run) + fprintf(output, "\n"); + fprintf(output, " %17.9f seconds time elapsed", + avg_stats(&walltime_nsecs_stats)/1e9); + if (run_count > 1) { + fprintf(output, " "); + print_noise_pct(stddev_stats(&walltime_nsecs_stats), + avg_stats(&walltime_nsecs_stats)); + } + fprintf(output, "\n\n"); +} + +static void print_counters(struct timespec *ts, int argc, const char **argv) +{ + struct perf_evsel *counter; + char buf[64], *prefix = NULL; + + if (interval) + print_interval(prefix = buf, ts); + else + print_header(argc, argv); switch (aggr_mode) { case AGGR_CORE: case AGGR_SOCKET: - print_aggr(NULL); + print_aggr(prefix); + break; + case AGGR_THREAD: + evlist__for_each(evsel_list, counter) + print_aggr_thread(counter, prefix); break; case AGGR_GLOBAL: evlist__for_each(evsel_list, counter) - print_counter_aggr(counter, NULL); + print_counter_aggr(counter, prefix); break; case AGGR_NONE: evlist__for_each(evsel_list, counter) - print_counter(counter, NULL); + print_counter(counter, prefix); break; default: break; } - if (!csv_output) { - if (!null_run) - fprintf(output, "\n"); - fprintf(output, " %17.9f seconds time elapsed", - avg_stats(&walltime_nsecs_stats)/1e9); - if (run_count > 1) { - fprintf(output, " "); - print_noise_pct(stddev_stats(&walltime_nsecs_stats), - avg_stats(&walltime_nsecs_stats)); - } - fprintf(output, "\n\n"); - } + if (!interval && !csv_output) + print_footer(); + + fflush(output); } static volatile int signr = -1; @@ -1530,23 +1081,13 @@ static int perf_stat_init_aggr_mode(void) break; case AGGR_NONE: case AGGR_GLOBAL: + case AGGR_THREAD: default: break; } return 0; } -static int setup_events(const char * const *attrs, unsigned len) -{ - unsigned i; - - for (i = 0; i < len; i++) { - if (parse_events(evsel_list, attrs[i])) - return -1; - } - return 0; -} - /* * Add default attributes, if there were no attributes specified or * if -d/--detailed, -d -d or -d -d -d is used: @@ -1668,12 +1209,10 @@ static int add_default_attributes(void) int err; if (pmu_have_event("cpu", "cycles-ct") && pmu_have_event("cpu", "el-start")) - err = setup_events(transaction_attrs, - ARRAY_SIZE(transaction_attrs)); + err = parse_events(evsel_list, transaction_attrs, NULL); else - err = setup_events(transaction_limited_attrs, - ARRAY_SIZE(transaction_limited_attrs)); - if (err < 0) { + err = parse_events(evsel_list, transaction_limited_attrs, NULL); + if (err) { fprintf(stderr, "Cannot set up transaction events\n"); return -1; } @@ -1767,6 +1306,8 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) "aggregate counts per processor socket", AGGR_SOCKET), OPT_SET_UINT(0, "per-core", &aggr_mode, "aggregate counts per physical processor core", AGGR_CORE), + OPT_SET_UINT(0, "per-thread", &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() @@ -1858,8 +1399,19 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) run_count = 1; } - /* no_aggr, cgroup are for system-wide only */ - if ((aggr_mode != AGGR_GLOBAL || nr_cgroups) && + if ((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); + goto out; + } + + /* + * no_aggr, cgroup are for system-wide only + * --per-thread is aggregated per thread, we dont mix it with cpu mode + */ + if (((aggr_mode != AGGR_GLOBAL && aggr_mode != AGGR_THREAD) || nr_cgroups) && !target__has_cpu(&target)) { fprintf(stderr, "both cgroup and no-aggregation " "modes only available in system-wide mode\n"); @@ -1887,6 +1439,14 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) } goto out; } + + /* + * Initialize thread_map with comm names, + * so we could print it out on output. + */ + if (aggr_mode == AGGR_THREAD) + thread_map__read_comms(evsel_list->threads); + if (interval && interval < 100) { pr_err("print interval must be >= 100ms\n"); parse_options_usage(stat_usage, options, "I", 1); @@ -1920,13 +1480,13 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused) status = run_perf_stat(argc, argv); if (forever && status != -1) { - print_stat(argc, argv); - perf_stat__reset_stats(evsel_list); + print_counters(NULL, argc, argv); + perf_stat__reset_stats(); } } if (!forever && status != -1 && !interval) - print_stat(argc, argv); + print_counters(NULL, argc, argv); perf_evlist__free_stats(evsel_list); out: |