[PATCH 3/3] perf stat: Add support to measure SMI cost
From: kan . liang
Date: Thu Mar 23 2017 - 14:37:05 EST
From: Kan Liang <Kan.liang@xxxxxxxxx>
Implementing a new --smi-cost mode in perf stat to measure SMI cost.
During the measurement, the /sys/device/cpu/freeze_on_smi will be set.
The measurement can be done with one counter and two free running MSR
counters (IA32_APERF and SMI_COUNT).
The formula to caculate SMI cost is as below.
The percentages of SMI cycles = (aperf - cycles) / aperf
metric_only will be set by default unless the user explicitly disable
it.
Here is an example output.
Performance counter stats for 'sudo echo ':
SMI cycles% SMI#
0.1% 1
0.010858678 seconds time elapsed
Signed-off-by: Kan Liang <Kan.liang@xxxxxxxxx>
---
tools/perf/Documentation/perf-stat.txt | 9 +++++++
tools/perf/builtin-stat.c | 48 ++++++++++++++++++++++++++++++++++
tools/perf/util/stat-shadow.c | 33 +++++++++++++++++++++++
tools/perf/util/stat.c | 2 ++
tools/perf/util/stat.h | 2 ++
5 files changed, 94 insertions(+)
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 9785481..d8df8e9 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -236,6 +236,15 @@ To interpret the results it is usually needed to know on which
CPUs the workload runs on. If needed the CPUs can be forced using
taskset.
+--smi-cost::
+Measure SMI cost if support and SMI is detected
+
+During the measurement, the /sys/device/cpu/freeze_on_smi will be
+set to freeze cycles counter on SMI. The aperf event will not be
+effected by freeze_on_smi.
+
+The percentages of SMI cycles = (aperf - cycles) / aperf
+
EXAMPLES
--------
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f53f449..f10aad6 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -76,6 +76,7 @@
#define DEFAULT_SEPARATOR " "
#define CNTR_NOT_SUPPORTED "<not supported>"
#define CNTR_NOT_COUNTED "<not counted>"
+#define FREEZE_ON_SMI_PATH "devices/cpu/freeze_on_smi"
static void print_counters(struct timespec *ts, int argc, const char **argv);
@@ -112,6 +113,14 @@ static const char * topdown_attrs[] = {
NULL,
};
+static const char *smi_cost_attrs = {
+ "{"
+ "msr/aperf/,"
+ "msr/smi/,"
+ "cycles"
+ "}"
+};
+
static struct perf_evlist *evsel_list;
static struct target target = {
@@ -127,6 +136,8 @@ static bool null_run = false;
static int detailed_run = 0;
static bool transaction_run;
static bool topdown_run = false;
+static bool smi_cost = false;
+static bool smi_reset = false;
static bool big_num = true;
static int big_num_opt = -1;
static const char *csv_sep = NULL;
@@ -1670,6 +1681,8 @@ static const struct option stat_options[] = {
"Only print computed metrics. No raw values", enable_metric_only),
OPT_BOOLEAN(0, "topdown", &topdown_run,
"measure topdown level 1 statistics"),
+ OPT_BOOLEAN(0, "smi-cost", &smi_cost,
+ "measure SMI cost"),
OPT_END()
};
@@ -2048,6 +2061,38 @@ static int add_default_attributes(void)
return 0;
}
+ if (smi_cost) {
+ int smi;
+
+ if (sysfs__read_int(FREEZE_ON_SMI_PATH, &smi) < 0) {
+ fprintf(stderr, "freeze_on_smi is not supported.\n");
+ return -1;
+ }
+
+ if (!smi) {
+ if (sysfs__write_int(FREEZE_ON_SMI_PATH, 1) < 0) {
+ fprintf(stderr, "Failed to set freeze_on_smi.\n");
+ return -1;
+ }
+ smi_reset = true;
+ }
+
+ if (pmu_have_event("msr", "aperf") &&
+ pmu_have_event("msr", "smi")) {
+ if (!force_metric_only)
+ metric_only = true;
+ err = parse_events(evsel_list, smi_cost_attrs, NULL);
+ } else {
+ fprintf(stderr, "To measure SMI cost, it needs msr/aperf/, msr/smi/ and cpu/cycles/ events support\n");
+ return -1;
+ }
+ if (err) {
+ fprintf(stderr, "Cannot set up SMI cost events\n");
+ return -1;
+ }
+ return 0;
+ }
+
if (topdown_run) {
char *str = NULL;
bool warn = false;
@@ -2629,6 +2674,9 @@ int cmd_stat(int argc, const char **argv, const char *prefix __maybe_unused)
perf_stat__exit_aggr_mode();
perf_evlist__free_stats(evsel_list);
out:
+ if (smi_cost && smi_reset)
+ sysfs__write_int(FREEZE_ON_SMI_PATH, 0);
+
perf_evlist__delete(evsel_list);
return status;
}
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 8a2bbd2..dda7877 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -41,6 +41,8 @@ static struct stats runtime_topdown_slots_issued[NUM_CTX][MAX_NR_CPUS];
static struct stats runtime_topdown_slots_retired[NUM_CTX][MAX_NR_CPUS];
static struct stats runtime_topdown_fetch_bubbles[NUM_CTX][MAX_NR_CPUS];
static struct stats runtime_topdown_recovery_bubbles[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_smi_num_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_aperf_stats[NUM_CTX][MAX_NR_CPUS];
static bool have_frontend_stalled;
struct stats walltime_nsecs_stats;
@@ -92,6 +94,9 @@ void perf_stat__reset_shadow_stats(void)
memset(runtime_topdown_slots_issued, 0, sizeof(runtime_topdown_slots_issued));
memset(runtime_topdown_fetch_bubbles, 0, sizeof(runtime_topdown_fetch_bubbles));
memset(runtime_topdown_recovery_bubbles, 0, sizeof(runtime_topdown_recovery_bubbles));
+
+ memset(runtime_smi_num_stats, 0, sizeof(runtime_smi_num_stats));
+ memset(runtime_aperf_stats, 0, sizeof(runtime_aperf_stats));
}
/*
@@ -143,6 +148,10 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
update_stats(&runtime_dtlb_cache_stats[ctx][cpu], count[0]);
else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
update_stats(&runtime_itlb_cache_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, SMI_NUM))
+ update_stats(&runtime_smi_num_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, APERF))
+ update_stats(&runtime_aperf_stats[ctx][cpu], count[0]);
}
/* used for get_ratio_color() */
@@ -423,6 +432,25 @@ static double td_be_bound(int ctx, int cpu)
return sanitize_val(1.0 - sum);
}
+static void print_smi_cost(int cpu, struct perf_evsel *evsel,
+ struct perf_stat_output_ctx *out)
+{
+ double smi_num, aperf, cycles, cost = 0.0;
+ int ctx = evsel_context(evsel);
+ const char *color = NULL;
+
+ smi_num = avg_stats(&runtime_smi_num_stats[ctx][cpu]);
+ aperf = avg_stats(&runtime_aperf_stats[ctx][cpu]);
+ cycles = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+ cost = (aperf - cycles) / aperf * 100.00;
+
+ if (cost > 10)
+ color = PERF_COLOR_RED;
+ out->print_metric(out->ctx, color, "%8.1f%%", "SMI cycles%", cost);
+ out->print_metric(out->ctx, NULL, "%4.0f", "SMI#", smi_num);
+}
+
void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
double avg, int cpu,
struct perf_stat_output_ctx *out)
@@ -628,6 +656,11 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
}
snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
print_metric(ctxp, NULL, "%8.3f", unit_buf, ratio);
+ } else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
+ if (avg_stats(&runtime_smi_num_stats[ctx][cpu]))
+ print_smi_cost(cpu, evsel, out);
+ else
+ print_metric(ctxp, NULL, NULL, " no SMI detected", 0);
} else {
print_metric(ctxp, NULL, NULL, NULL, 0);
}
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 0d51334..8ae3160f 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -84,6 +84,8 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
ID(TOPDOWN_SLOTS_RETIRED, topdown-slots-retired),
ID(TOPDOWN_FETCH_BUBBLES, topdown-fetch-bubbles),
ID(TOPDOWN_RECOVERY_BUBBLES, topdown-recovery-bubbles),
+ ID(SMI_NUM, msr/smi/),
+ ID(APERF, msr/aperf/),
};
#undef ID
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index c29bb94..c3be07d 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -22,6 +22,8 @@ enum perf_stat_evsel_id {
PERF_STAT_EVSEL_ID__TOPDOWN_SLOTS_RETIRED,
PERF_STAT_EVSEL_ID__TOPDOWN_FETCH_BUBBLES,
PERF_STAT_EVSEL_ID__TOPDOWN_RECOVERY_BUBBLES,
+ PERF_STAT_EVSEL_ID__SMI_NUM,
+ PERF_STAT_EVSEL_ID__APERF,
PERF_STAT_EVSEL_ID__MAX,
};
--
2.7.4