From a22e99cd74a31dee4b5241bd60a256c629c808da Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Tue, 23 Jun 2015 00:36:08 +0200 Subject: perf tools: Make perf_evsel__(nr_)cpus generic Because we now propagate all evlist's cpu_maps and thread_map objects through all evsels, the perf_evsel__(nr_)cpus no longer need to be specific to stat object and check evlist and target objects. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435012588-9007-8-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index fcf99bdeb19e..3e1636cae76b 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -141,16 +141,6 @@ 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; -- cgit v1.2.3 From 1ac77e1ce8654ec94ada0c508d58ba80a4647fba Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:09 +0200 Subject: perf stat: Introduce perf_counts function Introducing perf_counts function, that returns 'struct perf_counts_values' pointer for given cpu. Also moving perf_counts* structures into stat.h. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-5-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 14 +++++++------- tools/perf/tests/openat-syscall-all-cpus.c | 4 ++-- tools/perf/tests/openat-syscall.c | 2 +- tools/perf/util/evsel.c | 6 +++--- tools/perf/util/evsel.h | 18 +----------------- tools/perf/util/stat.h | 23 +++++++++++++++++++++++ 6 files changed, 37 insertions(+), 30 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 3e1636cae76b..49b90374232c 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -316,7 +316,7 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, if (!evsel->snapshot) perf_evsel__compute_deltas(evsel, cpu, count); perf_counts_values__scale(count, scale, NULL); - evsel->counts->cpu[cpu] = *count; + *perf_counts(evsel->counts, cpu) = *count; if (aggr_mode == AGGR_NONE) perf_stat__update_shadow_stats(evsel, count->values, cpu); break; @@ -805,9 +805,9 @@ 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)->val; + ena += perf_counts(counter->counts, cpu)->ena; + run += perf_counts(counter->counts, cpu)->run; nr++; } if (prefix) @@ -915,9 +915,9 @@ 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)->val; + ena = perf_counts(counter->counts, cpu)->ena; + run = perf_counts(counter->counts, cpu)->run; if (prefix) fprintf(output, "%s", prefix); diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index b8d552b13950..e8d944fe1bd0 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -98,9 +98,9 @@ int test__openat_syscall_event_on_all_cpus(void) } expected = nr_openat_calls + cpu; - if (evsel->counts->cpu[cpu].val != expected) { + if (perf_counts(evsel->counts, cpu)->val != expected) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", - expected, cpus->map[cpu], evsel->counts->cpu[cpu].val); + expected, cpus->map[cpu], perf_counts(evsel->counts, cpu)->val); err = -1; } } diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index bdfa1f446681..e86fc477a74f 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -44,7 +44,7 @@ int test__openat_syscall_event(void) goto out_close_fd; } - if (evsel->counts->cpu[0].val != nr_openat_calls) { + if (perf_counts(evsel->counts, 0)->val != nr_openat_calls) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n", nr_openat_calls, evsel->counts->cpu[0].val); goto out_close_fd; diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 1b2f480a3e82..8401b042b9d4 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -910,8 +910,8 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, tmp = evsel->prev_raw_counts->aggr; evsel->prev_raw_counts->aggr = *count; } else { - tmp = evsel->prev_raw_counts->cpu[cpu]; - evsel->prev_raw_counts->cpu[cpu] = *count; + tmp = *perf_counts(evsel->prev_raw_counts, cpu); + *perf_counts(evsel->prev_raw_counts, cpu) = *count; } count->val = count->val - tmp.val; @@ -972,7 +972,7 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, perf_evsel__compute_deltas(evsel, cpu, &count); perf_counts_values__scale(&count, scale, NULL); - evsel->counts->cpu[cpu] = count; + *perf_counts(evsel->counts, cpu) = count; return 0; } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index 4dbf32d94dfb..b420f8f5fc5d 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -9,23 +9,7 @@ #include "xyarray.h" #include "symbol.h" #include "cpumap.h" - -struct perf_counts_values { - union { - struct { - u64 val; - u64 ena; - u64 run; - }; - u64 values[3]; - }; -}; - -struct perf_counts { - s8 scaled; - struct perf_counts_values aggr; - struct perf_counts_values cpu[]; -}; +#include "stat.h" struct perf_evsel; diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 093dc3cb28dd..5e43348836a6 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -31,6 +31,29 @@ enum aggr_mode { AGGR_CORE, }; +struct perf_counts_values { + union { + struct { + u64 val; + u64 ena; + u64 run; + }; + u64 values[3]; + }; +}; + +struct perf_counts { + s8 scaled; + struct perf_counts_values aggr; + struct perf_counts_values cpu[]; +}; + +static inline struct perf_counts_values* +perf_counts(struct perf_counts *counts, int cpu) +{ + return &counts->cpu[cpu]; +} + void update_stats(struct stats *stats, u64 val); double avg_stats(struct stats *stats); double stddev_stats(struct stats *stats); -- cgit v1.2.3 From a8e02324dfe6bcafc15d02b790f33321ec4facb0 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:10 +0200 Subject: perf stat: Use xyarray for cpu evsel counts Switching single dimensional array of 'struct perf_counts_values' with xyarray object, so we could store thread dimension counts. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-6-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 2 +- tools/perf/tests/openat-syscall.c | 2 +- tools/perf/util/stat.c | 31 ++++++++++++++++++++++--------- tools/perf/util/stat.h | 7 ++++--- 4 files changed, 28 insertions(+), 14 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 49b90374232c..055ce83dd6f2 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -218,7 +218,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist) evlist__for_each(evlist, evsel) { perf_evsel__reset_stat_priv(evsel); - perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel)); + perf_evsel__reset_counts(evsel); } perf_stat__reset_shadow_stats(); diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index e86fc477a74f..bd882f09ebbc 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -46,7 +46,7 @@ int test__openat_syscall_event(void) if (perf_counts(evsel->counts, 0)->val != nr_openat_calls) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n", - nr_openat_calls, evsel->counts->cpu[0].val); + nr_openat_calls, perf_counts(evsel->counts, 0)->val); goto out_close_fd; } diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 4014b709f956..453480aa7650 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -97,26 +97,39 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) struct perf_counts *perf_counts__new(int ncpus) { - int size = sizeof(struct perf_counts) + - ncpus * sizeof(struct perf_counts_values); + struct perf_counts *counts = zalloc(sizeof(*counts)); - return zalloc(size); + if (counts) { + struct xyarray *cpu; + + cpu = xyarray__new(ncpus, 1, sizeof(struct perf_counts_values)); + if (!cpu) { + free(counts); + return NULL; + } + + counts->cpu = cpu; + } + + return counts; } void perf_counts__delete(struct perf_counts *counts) { - free(counts); + if (counts) { + xyarray__delete(counts->cpu); + free(counts); + } } -static void perf_counts__reset(struct perf_counts *counts, int ncpus) +static void perf_counts__reset(struct perf_counts *counts) { - memset(counts, 0, (sizeof(*counts) + - (ncpus * sizeof(struct perf_counts_values)))); + xyarray__reset(counts->cpu); } -void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus) +void perf_evsel__reset_counts(struct perf_evsel *evsel) { - perf_counts__reset(evsel->counts, ncpus); + perf_counts__reset(evsel->counts); } int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 5e43348836a6..6d07612545e0 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -3,6 +3,7 @@ #include #include +#include "xyarray.h" struct stats { @@ -45,13 +46,13 @@ struct perf_counts_values { struct perf_counts { s8 scaled; struct perf_counts_values aggr; - struct perf_counts_values cpu[]; + struct xyarray *cpu; }; static inline struct perf_counts_values* perf_counts(struct perf_counts *counts, int cpu) { - return &counts->cpu[cpu]; + return xyarray__entry(counts->cpu, cpu, 0); } void update_stats(struct stats *stats, u64 val); @@ -88,7 +89,7 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, struct perf_counts *perf_counts__new(int ncpus); void perf_counts__delete(struct perf_counts *counts); -void perf_evsel__reset_counts(struct perf_evsel *evsel, int ncpus); +void perf_evsel__reset_counts(struct perf_evsel *evsel); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); void perf_evsel__free_counts(struct perf_evsel *evsel); #endif -- cgit v1.2.3 From a6fa003855d38d53d90c1a8a5827102e62702334 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:11 +0200 Subject: perf stat: Make stats work over the thread dimension Now that we have space for thread dimension counts, let's store it. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-7-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 32 +++++++++++++++++------------- tools/perf/tests/openat-syscall-all-cpus.c | 6 +++--- tools/perf/tests/openat-syscall.c | 4 ++-- tools/perf/util/evsel.c | 12 +++++------ tools/perf/util/evsel.h | 2 +- tools/perf/util/stat.c | 8 ++++---- tools/perf/util/stat.h | 8 ++++---- 7 files changed, 38 insertions(+), 34 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 055ce83dd6f2..983bcbbe8e0a 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -166,11 +166,12 @@ 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) +static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads) { struct perf_counts *counts; - counts = perf_counts__new(perf_evsel__nr_cpus(evsel)); + counts = perf_counts__new(ncpus, nthreads); if (counts) evsel->prev_raw_counts = counts; @@ -197,11 +198,14 @@ static void perf_evlist__free_stats(struct perf_evlist *evlist) static int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) { struct perf_evsel *evsel; + int nthreads = thread_map__nr(evsel_list->threads); evlist__for_each(evlist, evsel) { + int ncpus = perf_evsel__nr_cpus(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)) + perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || + (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0)) goto out_free; } @@ -294,7 +298,7 @@ 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, +static int read_cb(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { struct perf_counts_values *aggr = &evsel->counts->aggr; @@ -314,9 +318,9 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused, 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); - *perf_counts(evsel->counts, cpu) = *count; + *perf_counts(evsel->counts, cpu, thread) = *count; if (aggr_mode == AGGR_NONE) perf_stat__update_shadow_stats(evsel, count->values, cpu); break; @@ -352,7 +356,7 @@ static int read_counter_aggr(struct perf_evsel *counter) return -1; 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++) @@ -805,9 +809,9 @@ static void print_aggr(char *prefix) s2 = aggr_get_id(evsel_list->cpus, cpu2); if (s2 != id) continue; - val += perf_counts(counter->counts, cpu)->val; - ena += perf_counts(counter->counts, cpu)->ena; - run += perf_counts(counter->counts, 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) @@ -915,9 +919,9 @@ static void print_counter(struct perf_evsel *counter, char *prefix) int cpu; for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) { - val = perf_counts(counter->counts, cpu)->val; - ena = perf_counts(counter->counts, cpu)->ena; - run = perf_counts(counter->counts, 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); diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c index e8d944fe1bd0..a572f87e9c8d 100644 --- a/tools/perf/tests/openat-syscall-all-cpus.c +++ b/tools/perf/tests/openat-syscall-all-cpus.c @@ -78,7 +78,7 @@ int test__openat_syscall_event_on_all_cpus(void) * we use the auto allocation it will allocate just for 1 cpu, * as we start by cpu 0. */ - if (perf_evsel__alloc_counts(evsel, cpus->nr) < 0) { + if (perf_evsel__alloc_counts(evsel, cpus->nr, 1) < 0) { pr_debug("perf_evsel__alloc_counts(ncpus=%d)\n", cpus->nr); goto out_close_fd; } @@ -98,9 +98,9 @@ int test__openat_syscall_event_on_all_cpus(void) } expected = nr_openat_calls + cpu; - if (perf_counts(evsel->counts, cpu)->val != expected) { + if (perf_counts(evsel->counts, cpu, 0)->val != expected) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n", - expected, cpus->map[cpu], perf_counts(evsel->counts, cpu)->val); + expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val); err = -1; } } diff --git a/tools/perf/tests/openat-syscall.c b/tools/perf/tests/openat-syscall.c index bd882f09ebbc..c9a37bc6b33a 100644 --- a/tools/perf/tests/openat-syscall.c +++ b/tools/perf/tests/openat-syscall.c @@ -44,9 +44,9 @@ int test__openat_syscall_event(void) goto out_close_fd; } - if (perf_counts(evsel->counts, 0)->val != nr_openat_calls) { + if (perf_counts(evsel->counts, 0, 0)->val != nr_openat_calls) { pr_debug("perf_evsel__read_on_cpu: expected to intercept %d calls, got %" PRIu64 "\n", - nr_openat_calls, perf_counts(evsel->counts, 0)->val); + nr_openat_calls, perf_counts(evsel->counts, 0, 0)->val); goto out_close_fd; } diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 8401b042b9d4..cd6ce7066f85 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -898,7 +898,7 @@ void perf_evsel__delete(struct perf_evsel *evsel) free(evsel); } -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, +void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count) { struct perf_counts_values tmp; @@ -910,8 +910,8 @@ void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, tmp = evsel->prev_raw_counts->aggr; evsel->prev_raw_counts->aggr = *count; } else { - tmp = *perf_counts(evsel->prev_raw_counts, cpu); - *perf_counts(evsel->prev_raw_counts, cpu) = *count; + tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread); + *perf_counts(evsel->prev_raw_counts, cpu, thread) = *count; } count->val = count->val - tmp.val; @@ -964,15 +964,15 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel, if (FD(evsel, cpu, thread) < 0) return -EINVAL; - if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1) < 0) + if (evsel->counts == NULL && perf_evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0) return -ENOMEM; if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0) return -errno; - perf_evsel__compute_deltas(evsel, cpu, &count); + perf_evsel__compute_deltas(evsel, cpu, thread, &count); perf_counts_values__scale(&count, scale, NULL); - *perf_counts(evsel->counts, cpu) = count; + *perf_counts(evsel->counts, cpu, thread) = count; return 0; } diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h index b420f8f5fc5d..020f7e13634a 100644 --- a/tools/perf/util/evsel.h +++ b/tools/perf/util/evsel.h @@ -112,7 +112,7 @@ static inline int perf_evsel__nr_cpus(struct perf_evsel *evsel) void perf_counts_values__scale(struct perf_counts_values *count, bool scale, s8 *pscaled); -void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, +void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu, int thread, struct perf_counts_values *count); int perf_evsel__object_config(size_t object_size, diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 453480aa7650..7bcc19b62dd1 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -95,14 +95,14 @@ void perf_stat_evsel_id_init(struct perf_evsel *evsel) } } -struct perf_counts *perf_counts__new(int ncpus) +struct perf_counts *perf_counts__new(int ncpus, int nthreads) { struct perf_counts *counts = zalloc(sizeof(*counts)); if (counts) { struct xyarray *cpu; - cpu = xyarray__new(ncpus, 1, sizeof(struct perf_counts_values)); + cpu = xyarray__new(ncpus, nthreads, sizeof(struct perf_counts_values)); if (!cpu) { free(counts); return NULL; @@ -132,9 +132,9 @@ void perf_evsel__reset_counts(struct perf_evsel *evsel) perf_counts__reset(evsel->counts); } -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus) +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads) { - evsel->counts = perf_counts__new(ncpus); + evsel->counts = perf_counts__new(ncpus, nthreads); return evsel->counts != NULL ? 0 : -ENOMEM; } diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 6d07612545e0..e0b8dc50fbb6 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -50,9 +50,9 @@ struct perf_counts { }; static inline struct perf_counts_values* -perf_counts(struct perf_counts *counts, int cpu) +perf_counts(struct perf_counts *counts, int cpu, int thread) { - return xyarray__entry(counts->cpu, cpu, 0); + return xyarray__entry(counts->cpu, cpu, thread); } void update_stats(struct stats *stats, u64 val); @@ -86,10 +86,10 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count, void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel, double avg, int cpu, enum aggr_mode aggr); -struct perf_counts *perf_counts__new(int ncpus); +struct perf_counts *perf_counts__new(int ncpus, int nthreads); void perf_counts__delete(struct perf_counts *counts); void perf_evsel__reset_counts(struct perf_evsel *evsel); -int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus); +int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads); void perf_evsel__free_counts(struct perf_evsel *evsel); #endif -- cgit v1.2.3 From 254ecbc7474dfa08155c5595e90cd4a0fa9d14ce Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:13 +0200 Subject: perf stat: Introduce perf_evlist__reset_stats To fit in with the rest of the helpers (alloc and free). Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-9-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 983bcbbe8e0a..188cd98a4ab3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -216,7 +216,7 @@ out_free: return -1; } -static void perf_stat__reset_stats(struct perf_evlist *evlist) +static void perf_evlist__reset_stats(struct perf_evlist *evlist) { struct perf_evsel *evsel; @@ -224,7 +224,11 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist) perf_evsel__reset_stat_priv(evsel); perf_evsel__reset_counts(evsel); } +} +static void perf_stat__reset_stats(void) +{ + perf_evlist__reset_stats(evsel_list); perf_stat__reset_shadow_stats(); } @@ -1473,7 +1477,7 @@ 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); + perf_stat__reset_stats(); } } -- cgit v1.2.3 From 9689edfabc1547155a7cdd1304fd294107054291 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:14 +0200 Subject: perf stat: Move perf_evsel__(alloc|free|reset)_stat_priv into stat object Moving perf_evsel__(alloc|free|reset)_stat_priv into stat object, so it could be used outside stat command in following patches. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-10-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 25 ------------------------- tools/perf/util/stat.c | 25 +++++++++++++++++++++++++ tools/perf/util/stat.h | 4 ++++ 3 files changed, 29 insertions(+), 25 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 188cd98a4ab3..8a7fd0c60ab1 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -141,31 +141,6 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a, } } -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]); - - perf_stat_evsel_id_init(evsel); -} - -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, int ncpus, int nthreads) { diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 197a2db5f2c4..b8c329f41f13 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -143,3 +143,28 @@ void perf_evsel__free_counts(struct perf_evsel *evsel) perf_counts__delete(evsel->counts); evsel->counts = NULL; } + +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]); + + perf_stat_evsel_id_init(evsel); +} + +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; +} + +void perf_evsel__free_stat_priv(struct perf_evsel *evsel) +{ + zfree(&evsel->priv); +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 295d1e29d3d6..c441cb312565 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -92,4 +92,8 @@ void perf_counts__delete(struct perf_counts *counts); void perf_evsel__reset_counts(struct perf_evsel *evsel); int perf_evsel__alloc_counts(struct perf_evsel *evsel, int ncpus, int nthreads); void perf_evsel__free_counts(struct perf_evsel *evsel); + +void perf_evsel__reset_stat_priv(struct perf_evsel *evsel); +int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); +void perf_evsel__free_stat_priv(struct perf_evsel *evsel); #endif -- cgit v1.2.3 From a939512d10a5583a32ae85c1bff6c4ae63a8a517 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:15 +0200 Subject: perf stat: Move perf_evsel__(alloc|free)_prev_raw_counts into stat object Moving perf_evsel__(alloc|free)_prev_raw_counts into stat object, so it could be used in following patches. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-11-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 18 ------------------ tools/perf/util/stat.c | 18 ++++++++++++++++++ tools/perf/util/stat.h | 4 ++++ 3 files changed, 22 insertions(+), 18 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 8a7fd0c60ab1..0ccba5c6b61d 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -141,24 +141,6 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a, } } -static int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, - int ncpus, int nthreads) -{ - struct perf_counts *counts; - - counts = perf_counts__new(ncpus, nthreads); - if (counts) - evsel->prev_raw_counts = counts; - - return counts ? 0 : -ENOMEM; -} - -static void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) -{ - perf_counts__delete(evsel->prev_raw_counts); - evsel->prev_raw_counts = NULL; -} - static void perf_evlist__free_stats(struct perf_evlist *evlist) { struct perf_evsel *evsel; diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index b8c329f41f13..6221c3898397 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -168,3 +168,21 @@ void perf_evsel__free_stat_priv(struct perf_evsel *evsel) { zfree(&evsel->priv); } + +int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads) +{ + struct perf_counts *counts; + + counts = perf_counts__new(ncpus, nthreads); + if (counts) + evsel->prev_raw_counts = counts; + + return counts ? 0 : -ENOMEM; +} + +void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) +{ + perf_counts__delete(evsel->prev_raw_counts); + evsel->prev_raw_counts = NULL; +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index c441cb312565..454b26875aef 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -96,4 +96,8 @@ void perf_evsel__free_counts(struct perf_evsel *evsel); void perf_evsel__reset_stat_priv(struct perf_evsel *evsel); int perf_evsel__alloc_stat_priv(struct perf_evsel *evsel); void perf_evsel__free_stat_priv(struct perf_evsel *evsel); + +int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, + int ncpus, int nthreads); +void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel); #endif -- cgit v1.2.3 From 24e34f68e21a47a582b3cc2eccdb835b80b1830a Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:16 +0200 Subject: perf stat: Move perf_evlist__(alloc|free|reset)_stats into stat object Moving perf_evlist__(alloc|free|reset)_stats into stat object, so it could be used in following patches. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-12-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 42 ------------------------------------------ tools/perf/util/evlist.h | 1 - tools/perf/util/stat.c | 44 ++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/stat.h | 6 ++++++ 4 files changed, 50 insertions(+), 43 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 0ccba5c6b61d..3e385f9f12ee 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -141,48 +141,6 @@ static inline void diff_timespec(struct timespec *r, struct timespec *a, } } -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; - int nthreads = thread_map__nr(evsel_list->threads); - - evlist__for_each(evlist, evsel) { - int ncpus = perf_evsel__nr_cpus(evsel); - - if (perf_evsel__alloc_stat_priv(evsel) < 0 || - perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || - (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0)) - goto out_free; - } - - return 0; - -out_free: - perf_evlist__free_stats(evlist); - return -1; -} - -static void perf_evlist__reset_stats(struct perf_evlist *evlist) -{ - struct perf_evsel *evsel; - - evlist__for_each(evlist, evsel) { - perf_evsel__reset_stat_priv(evsel); - perf_evsel__reset_counts(evsel); - } -} - static void perf_stat__reset_stats(void) { perf_evlist__reset_stats(evsel_list); diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index a8489b9d2812..037633c1da9d 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -289,5 +289,4 @@ void perf_evlist__to_front(struct perf_evlist *evlist, void perf_evlist__set_tracking_event(struct perf_evlist *evlist, struct perf_evsel *tracking_evsel); - #endif /* __PERF_EVLIST_H */ diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index 6221c3898397..818cb022fcb6 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,6 +1,8 @@ #include #include "stat.h" +#include "evlist.h" #include "evsel.h" +#include "thread_map.h" void update_stats(struct stats *stats, u64 val) { @@ -186,3 +188,45 @@ void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel) perf_counts__delete(evsel->prev_raw_counts); evsel->prev_raw_counts = NULL; } + +int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw) +{ + struct perf_evsel *evsel; + int nthreads = thread_map__nr(evlist->threads); + + evlist__for_each(evlist, evsel) { + int ncpus = perf_evsel__nr_cpus(evsel); + + if (perf_evsel__alloc_stat_priv(evsel) < 0 || + perf_evsel__alloc_counts(evsel, ncpus, nthreads) < 0 || + (alloc_raw && perf_evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0)) + goto out_free; + } + + return 0; + +out_free: + perf_evlist__free_stats(evlist); + return -1; +} + +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); + } +} + +void perf_evlist__reset_stats(struct perf_evlist *evlist) +{ + struct perf_evsel *evsel; + + evlist__for_each(evlist, evsel) { + perf_evsel__reset_stat_priv(evsel); + perf_evsel__reset_counts(evsel); + } +} diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 454b26875aef..5f62db2472c7 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -70,6 +70,8 @@ static inline void init_stats(struct stats *stats) } struct perf_evsel; +struct perf_evlist; + bool __perf_evsel_stat__is(struct perf_evsel *evsel, enum perf_stat_evsel_id id); @@ -100,4 +102,8 @@ void perf_evsel__free_stat_priv(struct perf_evsel *evsel); int perf_evsel__alloc_prev_raw_counts(struct perf_evsel *evsel, int ncpus, int nthreads); void perf_evsel__free_prev_raw_counts(struct perf_evsel *evsel); + +int perf_evlist__alloc_stats(struct perf_evlist *evlist, bool alloc_raw); +void perf_evlist__free_stats(struct perf_evlist *evlist); +void perf_evlist__reset_stats(struct perf_evlist *evlist); #endif -- cgit v1.2.3 From 106a94a0f8c207ef4113ce7e32f34a00b3b174e7 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:19 +0200 Subject: perf stat: Introduce read_counters function Moving read counters logic into single read_counters function, which will be called for both interval and overall processing legs. The reason is to split reading and processing (following patches) counters code, so we could read counters from other sources (like perf.data) and process them in the same way as 'perf stat' command does. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-15-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 47 ++++++++++++++++++++++------------------------- 1 file changed, 22 insertions(+), 25 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 3e385f9f12ee..158859e622d3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -323,27 +323,35 @@ static int read_counter(struct perf_evsel *counter) return 0; } -static void print_interval(void) +static void read_counters(bool close) { - 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)); + evlist__for_each(evsel_list, counter) { + ps = counter->priv; + memset(ps->res_stats, 0, sizeof(ps->res_stats)); + + if (aggr_mode == AGGR_GLOBAL) read_counter_aggr(counter); - } - } else { - evlist__for_each(evsel_list, counter) { - ps = counter->priv; - memset(ps->res_stats, 0, sizeof(ps->res_stats)); + else read_counter(counter); + + if (close) { + perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), + thread_map__nr(evsel_list->threads)); } } +} + +static void print_interval(void) +{ + static int num_print_interval; + struct perf_evsel *counter; + struct timespec ts, rs; + char prefix[64]; + + read_counters(false); clock_gettime(CLOCK_MONOTONIC, &ts); diff_timespec(&rs, &ts, &ref_time); @@ -525,18 +533,7 @@ 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); } -- cgit v1.2.3 From 3b3eb044519ac4c422dbc6084303c470b8d2dc61 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:20 +0200 Subject: perf stat: Separate counters reading and processing Separating counters reading and processing so we could use the processing part in following patches. Using simple reading via perf_evsel__read function to read counters now, because part of the processing was in the read_cb callback. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-16-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 56 +++++++++++++++++++++++++++++++++-------------- 1 file changed, 39 insertions(+), 17 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 158859e622d3..74ac92baa2bd 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -217,8 +217,9 @@ 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, - 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; @@ -239,7 +240,6 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread, if (!evsel->snapshot) perf_evsel__compute_deltas(evsel, cpu, thread, count); perf_counts_values__scale(count, scale, NULL); - *perf_counts(evsel->counts, cpu, thread) = *count; if (aggr_mode == AGGR_NONE) perf_stat__update_shadow_stats(evsel, count->values, cpu); break; @@ -256,23 +256,41 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread, 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; - if (read_counter(counter)) - return -1; + 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, -1, aggr); @@ -315,7 +333,10 @@ static int read_counter(struct perf_evsel *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; } } @@ -332,10 +353,11 @@ static void read_counters(bool close) ps = counter->priv; memset(ps->res_stats, 0, sizeof(ps->res_stats)); - if (aggr_mode == AGGR_GLOBAL) - read_counter_aggr(counter); - else - read_counter(counter); + if (read_counter(counter)) + pr_warning("failed to read counter %s\n", counter->name); + + if (process_counter(counter)) + pr_warning("failed to process counter %s\n", counter->name); if (close) { perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter), -- cgit v1.2.3 From 32ce0a47aaa401a7dd27dfe65210f3e3aa809682 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:21 +0200 Subject: perf stat: Move zero_per_pkg into counter process code Moving zero_per_pkg into counter process code, to make the reading path free of processing logic. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-17-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 74ac92baa2bd..b7c184bd559c 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -285,6 +285,9 @@ static int process_counter(struct perf_evsel *counter) aggr->val = aggr->ena = aggr->run = 0; + if (counter->per_pkg) + zero_per_pkg(counter); + ret = process_counter_maps(counter); if (ret) return ret; @@ -328,9 +331,6 @@ 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++) { struct perf_counts_values *count; -- cgit v1.2.3 From 7ddb1b6bbf1e614e6700f226cb0a559c5c635336 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:22 +0200 Subject: perf stat: Move perf_stat initialization counter process code Moving perf_stat initialization counter process code, to make the reading path free of processing logic. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-18-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index b7c184bd559c..526f67753664 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -284,6 +284,7 @@ static int process_counter(struct perf_evsel *counter) int i, ret; aggr->val = aggr->ena = aggr->run = 0; + memset(ps->res_stats, 0, sizeof(ps->res_stats)); if (counter->per_pkg) zero_per_pkg(counter); @@ -347,12 +348,8 @@ static int read_counter(struct perf_evsel *counter) static void read_counters(bool close) { struct perf_evsel *counter; - struct perf_stat *ps; evlist__for_each(evsel_list, counter) { - ps = counter->priv; - memset(ps->res_stats, 0, sizeof(ps->res_stats)); - if (read_counter(counter)) pr_warning("failed to read counter %s\n", counter->name); -- cgit v1.2.3 From ba411a954eae3e88c02667a5670cac97fb9c3f58 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:24 +0200 Subject: perf stat: Rename print_interval to process_interval It suits better, because the function also reads counter's data. Also the 'print_interval' name will be used in following generalization of counters display. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-20-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 526f67753664..aa706fca410e 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -363,7 +363,7 @@ static void read_counters(bool close) } } -static void print_interval(void) +static void process_interval(void) { static int num_print_interval; struct perf_evsel *counter; @@ -526,7 +526,7 @@ 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); @@ -544,7 +544,7 @@ static int __run_perf_stat(int argc, const char **argv) while (!done) { nanosleep(&ts, NULL); if (interval) - print_interval(); + process_interval(); } } -- cgit v1.2.3 From 5835e2286583e4fa6c2a609446e1320e7da2b161 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:25 +0200 Subject: perf stat: Using init_stats instead of memset The init_stats function is meant to init 'struct stats'. Reported-by: David Ahern Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-21-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index aa706fca410e..39a97ade2cf3 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -284,7 +284,7 @@ static int process_counter(struct perf_evsel *counter) int i, ret; aggr->val = aggr->ena = aggr->run = 0; - memset(ps->res_stats, 0, sizeof(ps->res_stats)); + init_stats(ps->res_stats); if (counter->per_pkg) zero_per_pkg(counter); -- cgit v1.2.3 From d4f63a4741a808c0bf25d92884713008706fca16 Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:26 +0200 Subject: perf stat: Introduce print_counters function Centralize counters print code into single print_counters function. Signed-off-by: Jiri Olsa Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-22-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-stat.c | 127 +++++++++++++++++++++++----------------------- 1 file changed, 64 insertions(+), 63 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 39a97ade2cf3..56dc8881cb05 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -67,10 +67,7 @@ #define CNTR_NOT_SUPPORTED "" #define CNTR_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 *transaction_attrs = { @@ -365,53 +362,14 @@ static void read_counters(bool close) static void process_interval(void) { - static int num_print_interval; - struct perf_evsel *counter; struct timespec ts, rs; - char prefix[64]; read_counters(false); 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 (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 (++num_print_interval == 25) - num_print_interval = 0; - 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); - } - - fflush(output); + print_counters(&rs, 0, NULL); } static void handle_initial_delay(void) @@ -901,9 +859,35 @@ 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_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); @@ -929,36 +913,53 @@ 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_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; @@ -1407,13 +1408,13 @@ 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); + 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: -- cgit v1.2.3 From 32b8af82e3708bc19af75c31fa773a98449f0edc Mon Sep 17 00:00:00 2001 From: Jiri Olsa Date: Fri, 26 Jun 2015 11:29:27 +0200 Subject: perf stat: Introduce --per-thread option Currently all the -p option PID arguments tasks values get aggregated and printed as single values. Adding --per-tasks option to print values per task. $ perf stat -e cycles,instructions --per-thread -p 30190,30242 ^C Performance counter stats for process id '30190,30242': cat-30190 0 cycles yes-30242 3,842,525,421 cycles cat-30190 0 instructions yes-30242 10,370,817,010 instructions 1.143155657 seconds time elapsed Also works under interval mode: $ perf stat -e cycles,instructions --per-thread -p 30190,30242 -I 1000 # time comm-pid counts unit events 1.000073435 cat-30190 89,058 cycles 1.000073435 yes-30242 3,360,786,902 cycles (100.00%) 1.000073435 cat-30190 14,066 instructions 1.000073435 yes-30242 9,069,937,462 instructions 2.000204830 cat-30190 0 cycles 2.000204830 yes-30242 3,351,667,626 cycles 2.000204830 cat-30190 0 instructions 2.000204830 yes-30242 9,045,796,885 instructions ^C 2.771286639 cat-30190 0 cycles 2.771286639 yes-30242 2,593,884,166 cycles 2.771286639 cat-30190 0 instructions 2.771286639 yes-30242 7,001,171,191 instructions It works only with -t and -p options, otherwise following error is printed: $ perf stat -e cycles --per-thread -I 1000 ls The --per-thread option is only available when monitoring via -p -t options. -p, --pid stat events on existing process id -t, --tid stat events on existing thread id Signed-off-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Andi Kleen Cc: David Ahern Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Link: http://lkml.kernel.org/r/1435310967-14570-23-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-stat.txt | 4 ++ tools/perf/builtin-stat.c | 76 +++++++++++++++++++++++++++++++++- tools/perf/util/stat.h | 1 + 3 files changed, 79 insertions(+), 2 deletions(-) (limited to 'tools/perf/builtin-stat.c') diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt index 04e150d83e7d..47469abdcc1c 100644 --- a/tools/perf/Documentation/perf-stat.txt +++ b/tools/perf/Documentation/perf-stat.txt @@ -144,6 +144,10 @@ is a useful mode to detect imbalance between physical cores. To enable this mod use --per-core in addition to -a. (system-wide). The output includes the core number and the number of online logical processors on that physical processor. +--per-thread:: +Aggregate counts per monitored threads, when monitoring threads (-t option) +or processes (-p option). + -D msecs:: --delay msecs:: After starting the program, wait msecs before measuring. This is useful to diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c index 56dc8881cb05..37e301a32f43 100644 --- a/tools/perf/builtin-stat.c +++ b/tools/perf/builtin-stat.c @@ -231,6 +231,7 @@ process_counter_values(struct perf_evsel *evsel, int cpu, int thread, count = &zero; switch (aggr_mode) { + case AGGR_THREAD: case AGGR_CORE: case AGGR_SOCKET: case AGGR_NONE: @@ -602,6 +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; @@ -750,6 +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 @@ -876,6 +919,9 @@ static void print_interval(char *prefix, struct timespec *ts) 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"); @@ -944,6 +990,10 @@ static void print_counters(struct timespec *ts, int argc, const char **argv) case AGGR_SOCKET: 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, prefix); @@ -1031,6 +1081,7 @@ static int perf_stat_init_aggr_mode(void) break; case AGGR_NONE: case AGGR_GLOBAL: + case AGGR_THREAD: default: break; } @@ -1255,6 +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() @@ -1346,8 +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"); @@ -1375,6 +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); diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h index 9f05c571befe..1cfbe0a980ac 100644 --- a/tools/perf/util/stat.h +++ b/tools/perf/util/stat.h @@ -30,6 +30,7 @@ enum aggr_mode { AGGR_GLOBAL, AGGR_SOCKET, AGGR_CORE, + AGGR_THREAD, }; struct perf_counts_values { -- cgit v1.2.3