From: Kan Liang <[email protected]> To generate the frequency and performance output, perf must sample read special events like cycles, ref-cycles, msr/tsc/, msr/aperf/ or msr/mperf/. With the --perf-freq option, perf record can automatically check and add those event into evlist as group for sampling read.
Signed-off-by: Kan Liang <[email protected]> Acked-by: Jiri Olsa <[email protected]> --- tools/perf/Documentation/perf-record.txt | 8 +++++++ tools/perf/builtin-record.c | 39 +++++++++++++++++++++++++++++++- tools/perf/util/event.h | 10 ++++++++ 3 files changed, 56 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index 2e9ce77..8a65f37 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -308,6 +308,14 @@ This option sets the time out limit. The default value is 500 ms. Record context switch events i.e. events of type PERF_RECORD_SWITCH or PERF_RECORD_SWITCH_CPU_WIDE. +--perf-freq:: +Collect CPU frequency and performance result per sample. It includes frequency, +CPU utilization and actual percent performance (APERF/MPERF%). +To generate the frequency and performance output, special events cycles, +ref-cycles, msr/tsc/, msr/aperf/ or msr/mperf/ must be read by group. +This option can automatically probe available special events on system, and +read their sample value by group. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 142eeb3..8c4da18 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -13,7 +13,7 @@ #include "util/util.h" #include "util/parse-options.h" #include "util/parse-events.h" - +#include "util/pmu.h" #include "util/callchain.h" #include "util/cgroup.h" #include "util/header.h" @@ -50,6 +50,7 @@ struct record { bool no_buildid; bool no_buildid_cache; long samples; + bool perf_freq; }; static int record__write(struct record *rec, void *bf, size_t size) @@ -948,6 +949,35 @@ out_free: return ret; } +const char *perf_freq_events[PERF_FREQ_MAX][3] = { + { "msr", "tsc", "msr/tsc/" }, + { "msr", "aperf", "msr/aperf/" }, + { "msr", "mperf", "msr/mperf/" }, + { NULL, "cycles", "cycles" }, + { NULL, "ref-cycles", "ref-cycles" }, +}; + +static int +record_add_perf_freq_events(struct perf_evlist *evlist) +{ + int i; + char perf_freq_attrs[100]; + + strcpy(perf_freq_attrs, "{cycles,ref-cycles"); + for (i = 0; i < PERF_FREQ_MAX; i++) { + if ((i == PERF_FREQ_CYCLES) || + (i == PERF_FREQ_REF_CYCLES)) + continue; + if (pmu_have_event(perf_freq_events[i][0], perf_freq_events[i][1])) { + strcat(perf_freq_attrs, ","); + strcat(perf_freq_attrs, perf_freq_events[i][2]); + } + } + strcat(perf_freq_attrs, "}:S"); + + return parse_events(evlist, perf_freq_attrs, NULL); +} + static const char * const __record_usage[] = { "perf record [<options>] [<command>]", "perf record [<options>] -- <command> [<options>]", @@ -1096,6 +1126,8 @@ struct option __record_options[] = { "per thread proc mmap processing timeout in ms"), OPT_BOOLEAN(0, "switch-events", &record.opts.record_switch_events, "Record context switch events"), + OPT_BOOLEAN(0, "perf-freq", &record.perf_freq, + "Collect CPU frequency and performance result per sample"), OPT_END() }; @@ -1157,6 +1189,11 @@ int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused) if (rec->no_buildid_cache || rec->no_buildid) disable_buildid_cache(); + if (rec->perf_freq && record_add_perf_freq_events(rec->evlist)) { + pr_err("Cannot set up freq and performance events\n"); + goto out_symbol_exit; + } + if (rec->evlist->nr_entries == 0 && perf_evlist__add_default(rec->evlist) < 0) { pr_err("Not enough memory for event selector list\n"); diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h index f729df5..3439462 100644 --- a/tools/perf/util/event.h +++ b/tools/perf/util/event.h @@ -177,6 +177,16 @@ enum { PERF_IP_FLAG_TRACE_BEGIN |\ PERF_IP_FLAG_TRACE_END) +enum perf_freqs { + PERF_FREQ_TSC = 0, + PERF_FREQ_APERF = 1, + PERF_FREQ_MPERF = 2, + PERF_FREQ_CYCLES = 3, + PERF_FREQ_REF_CYCLES = 4, + + PERF_FREQ_MAX +}; + struct perf_sample { u64 ip; u32 pid, tid; -- 1.8.3.1 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
