redonkable
/
alistair23-linux
1
0
Fork 0
Code Releases Activity

perf stat: Support new per thread TopDown metrics 

Icelake has support for reporting per thread TopDown metrics.

These are reported differently than the previous TopDown support,
each metric is standalone, but scaled to pipeline "slots".

We don't need to do anything special for HyperThreading anymore.
Teach perf stat --topdown to handle these new metrics and
print them in the same way as the previous TopDown metrics.

The restrictions of only being able to report information per core is
gone.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Co-developed-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/20200911144808.27603-4-kan.liang@linux.intel.com
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
zero-sugar-mainline-defconfig
Andi Kleen 2020-09-11 07:48:07 -07:00 committed by Arnaldo Carvalho de Melo
parent acb65150a4
commit 55c36a9fc2
5 changed files with 134 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
tools/perf/Documentation/perf-stat.txt
View File

@ -363,6 +363,11 @@ if the workload is actually bound by the CPU and not by something else.
For best results it is usually a good idea to use it with interval
mode like -I 1000, as the bottleneck of workloads can change often.
This enables --metric-only, unless overridden with --no-metric-only.
The following restrictions only apply to older Intel CPUs and Atom,
on newer CPUs (IceLake and later) TopDown can be collected for any thread:
The top down metrics are collected per core instead of per
CPU thread. Per core mode is automatically enabled
and -a (global monitoring) is needed, requiring root rights or
@ -374,8 +379,6 @@ echo 0 > /proc/sys/kernel/nmi_watchdog
for best results. Otherwise the bottlenecks may be inconsistent
on workload with changing phases.
This enables --metric-only, unless overridden with --no-metric-only.
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.

30
tools/perf/builtin-stat.c
View File

@ -128,6 +128,15 @@ static const char * topdown_attrs[] = {
NULL,
};
static const char *topdown_metric_attrs[] = {
"slots",
"topdown-retiring",
"topdown-bad-spec",
"topdown-fe-bound",
"topdown-be-bound",
NULL,
};
static const char *smi_cost_attrs = {
"{"
"msr/aperf/,"
@ -1677,6 +1686,24 @@ static int add_default_attributes(void)
char *str = NULL;
bool warn = false;
if (!force_metric_only)
stat_config.metric_only = true;
if (topdown_filter_events(topdown_metric_attrs, &str, 1) < 0) {
pr_err("Out of memory\n");
return -1;
}
if (topdown_metric_attrs[0] && str) {
if (!stat_config.interval && !stat_config.metric_only) {
fprintf(stat_config.output,
"Topdown accuracy may decrease when measuring long periods.\n"
"Please print the result regularly, e.g. -I1000\n");
}
goto setup_metrics;
}
zfree(&str);
if (stat_config.aggr_mode != AGGR_GLOBAL &&
stat_config.aggr_mode != AGGR_CORE) {
pr_err("top down event configuration requires --per-core mode\n");
@ -1688,8 +1715,6 @@ static int add_default_attributes(void)
return -1;
}
if (!force_metric_only)
stat_config.metric_only = true;
if (topdown_filter_events(topdown_attrs, &str,
arch_topdown_check_group(&warn)) < 0) {
pr_err("Out of memory\n");
@ -1698,6 +1723,7 @@ static int add_default_attributes(void)
if (topdown_attrs[0] && str) {
if (warn)
arch_topdown_group_warn();
setup_metrics:
err = parse_events(evsel_list, str, &errinfo);
if (err) {
fprintf(stderr,

89
tools/perf/util/stat-shadow.c
View File

@ -241,6 +241,18 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
ctx, cpu, count);
else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
ctx, cpu, count);
else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
ctx, cpu, count);
@ -705,6 +717,47 @@ static double td_be_bound(int ctx, int cpu, struct runtime_stat *st)
return sanitize_val(1.0 - sum);
}
/*
* Kernel reports metrics multiplied with slots. To get back
* the ratios we need to recreate the sum.
*/
static double td_metric_ratio(int ctx, int cpu,
enum stat_type type,
struct runtime_stat *stat)
{
double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) +
runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) +
runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) +
runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu);
double d = runtime_stat_avg(stat, type, ctx, cpu);
if (sum)
return d / sum;
return 0;
}
/*
* ... but only if most of the values are actually available.
* We allow two missing.
*/
static bool full_td(int ctx, int cpu,
struct runtime_stat *stat)
{
int c = 0;
if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, ctx, cpu) > 0)
c++;
if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, ctx, cpu) > 0)
c++;
if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, ctx, cpu) > 0)
c++;
if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, ctx, cpu) > 0)
c++;
return c >= 2;
}
static void print_smi_cost(struct perf_stat_config *config,
int cpu, struct evsel *evsel,
struct perf_stat_output_ctx *out,
@ -1073,6 +1126,42 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
be_bound * 100.);
else
print_metric(config, ctxp, NULL, NULL, name, 0);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
full_td(ctx, cpu, st)) {
double retiring = td_metric_ratio(ctx, cpu,
STAT_TOPDOWN_RETIRING, st);
if (retiring > 0.7)
color = PERF_COLOR_GREEN;
print_metric(config, ctxp, color, "%8.1f%%", "retiring",
retiring * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
full_td(ctx, cpu, st)) {
double fe_bound = td_metric_ratio(ctx, cpu,
STAT_TOPDOWN_FE_BOUND, st);
if (fe_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
fe_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
full_td(ctx, cpu, st)) {
double be_bound = td_metric_ratio(ctx, cpu,
STAT_TOPDOWN_BE_BOUND, st);
if (be_bound > 0.2)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
be_bound * 100.);
} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
full_td(ctx, cpu, st)) {
double bad_spec = td_metric_ratio(ctx, cpu,
STAT_TOPDOWN_BAD_SPEC, st);
if (bad_spec > 0.1)
color = PERF_COLOR_RED;
print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
bad_spec * 100.);
} else if (evsel->metric_expr) {
generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);

4
tools/perf/util/stat.c
View File

@ -95,6 +95,10 @@ 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(TOPDOWN_RETIRING, topdown-retiring),
ID(TOPDOWN_BAD_SPEC, topdown-bad-spec),
ID(TOPDOWN_FE_BOUND, topdown-fe-bound),
ID(TOPDOWN_BE_BOUND, topdown-be-bound),
ID(SMI_NUM, msr/smi/),
ID(APERF, msr/aperf/),
};

8
tools/perf/util/stat.h
View File

@ -28,6 +28,10 @@ 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__TOPDOWN_RETIRING,
PERF_STAT_EVSEL_ID__TOPDOWN_BAD_SPEC,
PERF_STAT_EVSEL_ID__TOPDOWN_FE_BOUND,
PERF_STAT_EVSEL_ID__TOPDOWN_BE_BOUND,
PERF_STAT_EVSEL_ID__SMI_NUM,
PERF_STAT_EVSEL_ID__APERF,
PERF_STAT_EVSEL_ID__MAX,
@ -82,6 +86,10 @@ enum stat_type {
STAT_TOPDOWN_SLOTS_RETIRED,
STAT_TOPDOWN_FETCH_BUBBLES,
STAT_TOPDOWN_RECOVERY_BUBBLES,
STAT_TOPDOWN_RETIRING,
STAT_TOPDOWN_BAD_SPEC,
STAT_TOPDOWN_FE_BOUND,
STAT_TOPDOWN_BE_BOUND,
STAT_SMI_NUM,
STAT_APERF,
STAT_MAX