Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754497AbbGWTFu (ORCPT ); Thu, 23 Jul 2015 15:05:50 -0400 Received: from mga02.intel.com ([134.134.136.20]:40612 "EHLO mga02.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754318AbbGWTEb (ORCPT ); Thu, 23 Jul 2015 15:04:31 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.15,532,1432623600"; d="scan'208";a="768439046" From: kan.liang@intel.com To: a.p.zijlstra@chello.nl, acme@kernel.org Cc: luto@kernel.org, mingo@redhat.com, eranian@google.com, ak@linux.intel.com, mark.rutland@arm.com, adrian.hunter@intel.com, jolsa@kernel.org, namhyung@kernel.org, linux-kernel@vger.kernel.org, Kan Liang Subject: [PATCH 2/5] perf,tools: Dump per-sample freq/CPU%/CORE_BUSY% in report -D Date: Thu, 23 Jul 2015 07:49:40 -0400 Message-Id: <1437652183-62080-3-git-send-email-kan.liang@intel.com> X-Mailer: git-send-email 1.8.3.1 In-Reply-To: <1437652183-62080-1-git-send-email-kan.liang@intel.com> References: <1437652183-62080-1-git-send-email-kan.liang@intel.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6914 Lines: 215 From: Kan Liang The group read results from cycles/ref-cycles/TSC/ASTATE/MSTATE event can be used to calculate the frequency, CPU Utilization and percent performance during each sampling period. This patch shows them in report -D. Here is an example: $ perf record -e '{cycles,ref-cycles,msr/tsc/,msr/mperf/,msr/aperf/}:S' ~/tchain_edit Here is one sample from perf report -D 1972044565107 0x3498 [0x88]: PERF_RECORD_SAMPLE(IP, 0x2): 10608/10608: 0x4005fd period: 564686 addr: 0 ... sample_read: .... group nr 5 ..... id 0000000000000012, value 0000000002143901 ..... id 0000000000000052, value 0000000002143896 ..... id 0000000000000094, value 00000000021e443d ..... id 00000000000000d4, value 00000000021db984 ..... id 0000000000000114, value 00000000021db964 ..... Freq 2301 MHz ..... CPU% 98% ..... CORE_BUSY% 99% Signed-off-by: Kan Liang --- tools/perf/builtin-report.c | 3 +++ tools/perf/util/pmu.h | 2 ++ tools/perf/util/session.c | 34 +++++++++++++++++++++++++++++----- tools/perf/util/session.h | 38 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 72 insertions(+), 5 deletions(-) diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 62cce98..0cd0573 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -38,6 +38,8 @@ #include "util/auxtrace.h" +#include "util/pmu.h" + #include #include @@ -818,6 +820,7 @@ repeat: symbol_conf.cumulate_callchain = false; } + msr_pmu = perf_pmu__find("msr"); cpu_max_freq = get_cpu_max_freq() / 1000; if (setup_sorting() < 0) { diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h index 7b9c8cf..e3e67aa 100644 --- a/tools/perf/util/pmu.h +++ b/tools/perf/util/pmu.h @@ -27,6 +27,8 @@ struct perf_pmu { struct list_head list; /* ELEM */ }; +struct perf_pmu *msr_pmu; + struct perf_pmu_info { const char *unit; double scale; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index ed9dc25..6dd20b5 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -17,6 +17,7 @@ #include "asm/bug.h" #include "auxtrace.h" #include "thread-stack.h" +#include "pmu.h" static int perf_session__deliver_event(struct perf_session *session, union perf_event *event, @@ -851,8 +852,14 @@ static void perf_evlist__print_tstamp(struct perf_evlist *evlist, printf("%" PRIu64 " ", sample->time); } -static void sample_read__printf(struct perf_sample *sample, u64 read_format) +static void sample_read__printf(struct perf_evlist *evlist, + struct perf_sample *sample, + u64 read_format) { + struct perf_evsel *evsel; + struct perf_sample_id *sid; + u64 data[FREQ_PERF_MAX] = { 0 }; + printf("... sample_read:\n"); if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) @@ -875,10 +882,26 @@ static void sample_read__printf(struct perf_sample *sample, u64 read_format) printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n", value->id, value->value); + + sid = perf_evlist__id2sid(evlist, value->id); + evsel = sid->evsel; + if (evsel != NULL) + SET_FREQ_PERF_VALUE(evsel, data, + value->value); } } else printf("..... id %016" PRIx64 ", value %016" PRIx64 "\n", sample->read.one.id, sample->read.one.value); + + if (HAS_FREQ(data)) + printf("..... Freq %lu MHz\n", + (data[FREQ_PERF_CYCLES] * cpu_max_freq) / data[FREQ_PERF_REF_CYCLES]); + if (HAS_CPU_U(data)) + printf("..... CPU%% %lu%%\n", + (100 * data[FREQ_PERF_REF_CYCLES]) / data[FREQ_PERF_TSC]); + if (HAS_CORE_BUSY(data)) + printf("..... CORE_BUSY%% %lu%%\n", + (100 * data[FREQ_PERF_APERF]) / data[FREQ_PERF_MPERF]); } static void dump_event(struct perf_evlist *evlist, union perf_event *event, @@ -899,8 +922,8 @@ static void dump_event(struct perf_evlist *evlist, union perf_event *event, event->header.size, perf_event__name(event->header.type)); } -static void dump_sample(struct perf_evsel *evsel, union perf_event *event, - struct perf_sample *sample) +static void dump_sample(struct perf_evlist *evlist, struct perf_evsel *evsel, + union perf_event *event, struct perf_sample *sample) { u64 sample_type; @@ -938,7 +961,7 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event, printf("... transaction: %" PRIx64 "\n", sample->transaction); if (sample_type & PERF_SAMPLE_READ) - sample_read__printf(sample, evsel->attr.read_format); + sample_read__printf(evlist, sample, evsel->attr.read_format); } static struct machine *machines__find_for_cpumode(struct machines *machines, @@ -1053,11 +1076,12 @@ static int machines__deliver_event(struct machines *machines, switch (event->header.type) { case PERF_RECORD_SAMPLE: - dump_sample(evsel, event, sample); if (evsel == NULL) { ++evlist->stats.nr_unknown_id; return 0; } + dump_sample(evlist, evsel, event, sample); + if (machine == NULL) { ++evlist->stats.nr_unprocessable_samples; return 0; diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h index b44afc7..df2094d 100644 --- a/tools/perf/util/session.h +++ b/tools/perf/util/session.h @@ -42,6 +42,44 @@ struct perf_session { #define PRINT_IP_OPT_ONELINE (1<<4) #define PRINT_IP_OPT_SRCLINE (1<<5) +#define PERF_MSR_TSC 0 +#define PERF_MSR_APERF 1 +#define PERF_MSR_MPERF 2 + +enum perf_freq_perf_index { + FREQ_PERF_TSC = 0, + FREQ_PERF_APERF = 1, + FREQ_PERF_MPERF = 2, + FREQ_PERF_CYCLES = 3, + FREQ_PERF_REF_CYCLES = 4, + + FREQ_PERF_MAX +}; + +#define SET_FREQ_PERF_VALUE(event, array, value) \ +{ \ + if (event->attr.type == msr_pmu->type) { \ + if (event->attr.config == PERF_MSR_TSC) \ + array[FREQ_PERF_TSC] = value; \ + if (event->attr.config == PERF_MSR_APERF) \ + array[FREQ_PERF_APERF] = value; \ + if (event->attr.config == PERF_MSR_MPERF) \ + array[FREQ_PERF_MPERF] = value; \ + } \ + if (event->attr.type == PERF_TYPE_HARDWARE) { \ + if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES) \ + array[FREQ_PERF_CYCLES] = value; \ + if (event->attr.config == PERF_COUNT_HW_REF_CPU_CYCLES) \ + array[FREQ_PERF_REF_CYCLES] = value; \ + } \ +} + +#define HAS_FREQ(array) \ + ((array[FREQ_PERF_CYCLES] > 0) && (array[FREQ_PERF_REF_CYCLES] > 0)) +#define HAS_CPU_U(array) \ + ((array[FREQ_PERF_TSC] > 0) && (array[FREQ_PERF_REF_CYCLES] > 0)) +#define HAS_CORE_BUSY(array) \ + ((array[FREQ_PERF_APERF] > 0) && (array[FREQ_PERF_MPERF] > 0)) struct perf_tool; struct perf_session *perf_session__new(struct perf_data_file *file, -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/