summaryrefslogtreecommitdiffstats
path: root/tools
diff options
context:
space:
mode:
authorJiri Olsa <jolsa@kernel.org>2015-06-03 16:25:59 +0200
committerArnaldo Carvalho de Melo <acme@redhat.com>2015-06-08 10:30:31 -0300
commitf87027b9689d591ec22720944563a2d43ec835c4 (patch)
tree8fc281e89b585dc338836da78bb41ac1539419cb /tools
parent7a23f57c89cec0e6d3189d420d992902d4465ff4 (diff)
downloadop-kernel-dev-f87027b9689d591ec22720944563a2d43ec835c4.zip
op-kernel-dev-f87027b9689d591ec22720944563a2d43ec835c4.tar.gz
perf stat: Move shadow stat counters into separate object
Separating shadow counters code into separate object as a cleanup, but mainly for upcomming changes, so could use it from script command context. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1433341559-31848-10-git-send-email-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools')
-rw-r--r--tools/perf/builtin-stat.c444
-rw-r--r--tools/perf/util/Build1
-rw-r--r--tools/perf/util/stat-shadow.c434
-rw-r--r--tools/perf/util/stat.h16
4 files changed, 455 insertions, 440 deletions
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 50918dc..ff3d258 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -102,13 +102,6 @@ static struct target target = {
.uid = UINT_MAX,
};
-enum aggr_mode {
- AGGR_NONE,
- AGGR_GLOBAL,
- AGGR_SOCKET,
- AGGR_CORE,
-};
-
static int run_count = 1;
static bool no_inherit = false;
static bool scale = true;
@@ -234,72 +227,6 @@ out_free:
return -1;
}
-enum {
- CTX_BIT_USER = 1 << 0,
- CTX_BIT_KERNEL = 1 << 1,
- CTX_BIT_HV = 1 << 2,
- CTX_BIT_HOST = 1 << 3,
- CTX_BIT_IDLE = 1 << 4,
- CTX_BIT_MAX = 1 << 5,
-};
-
-#define NUM_CTX CTX_BIT_MAX
-
-static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
-static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats walltime_nsecs_stats;
-static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
-static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
-
-static int evsel_context(struct perf_evsel *evsel)
-{
- int ctx = 0;
-
- if (evsel->attr.exclude_kernel)
- ctx |= CTX_BIT_KERNEL;
- if (evsel->attr.exclude_user)
- ctx |= CTX_BIT_USER;
- if (evsel->attr.exclude_hv)
- ctx |= CTX_BIT_HV;
- if (evsel->attr.exclude_host)
- ctx |= CTX_BIT_HOST;
- if (evsel->attr.exclude_idle)
- ctx |= CTX_BIT_IDLE;
-
- return ctx;
-}
-
-static void reset_shadow_stats(void)
-{
- memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
- memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
- memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
- memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
- memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
- memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
- memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
- memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
- memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
- memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
- memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
- memset(runtime_cycles_in_tx_stats, 0,
- sizeof(runtime_cycles_in_tx_stats));
- memset(runtime_transaction_stats, 0,
- sizeof(runtime_transaction_stats));
- memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
- memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
-}
-
static void perf_stat__reset_stats(struct perf_evlist *evlist)
{
struct perf_evsel *evsel;
@@ -309,7 +236,7 @@ static void perf_stat__reset_stats(struct perf_evlist *evlist)
perf_evsel__reset_counts(evsel, perf_evsel__nr_cpus(evsel));
}
- reset_shadow_stats();
+ perf_stat__reset_shadow_stats();
}
static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -346,46 +273,6 @@ static inline int nsec_counter(struct perf_evsel *evsel)
return 0;
}
-/*
- * Update various tracking values we maintain to print
- * more semantic information such as miss/hit ratios,
- * instruction rates, etc:
- */
-static void update_shadow_stats(struct perf_evsel *counter, u64 *count,
- int cpu)
-{
- int ctx = evsel_context(counter);
-
- if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
- update_stats(&runtime_nsecs_stats[cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
- update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
- else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
- update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
- else if (perf_stat_evsel__is(counter, TRANSACTION_START))
- update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
- else if (perf_stat_evsel__is(counter, ELISION_START))
- update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
- update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
- update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
- update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
- update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
- update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
- update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
- else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
- 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]);
-}
-
static void zero_per_pkg(struct perf_evsel *counter)
{
if (counter->per_pkg_mask)
@@ -446,7 +333,7 @@ static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
perf_counts_values__scale(count, scale, NULL);
evsel->counts->cpu[cpu] = *count;
if (aggr_mode == AGGR_NONE)
- update_shadow_stats(evsel, count->values, cpu);
+ perf_stat__update_shadow_stats(evsel, count->values, cpu);
break;
case AGGR_GLOBAL:
aggr->val += count->val;
@@ -494,7 +381,7 @@ static int read_counter_aggr(struct perf_evsel *counter)
/*
* Save the full runtime - to allow normalization during printout:
*/
- update_shadow_stats(counter, count, 0);
+ perf_stat__update_shadow_stats(counter, count, 0);
return 0;
}
@@ -872,329 +759,6 @@ static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
fprintf(output, " ");
}
-/* used for get_ratio_color() */
-enum grc_type {
- GRC_STALLED_CYCLES_FE,
- GRC_STALLED_CYCLES_BE,
- GRC_CACHE_MISSES,
- GRC_MAX_NR
-};
-
-static const char *get_ratio_color(enum grc_type type, double ratio)
-{
- static const double grc_table[GRC_MAX_NR][3] = {
- [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
- [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
- [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 },
- };
- const char *color = PERF_COLOR_NORMAL;
-
- if (ratio > grc_table[type][0])
- color = PERF_COLOR_RED;
- else if (ratio > grc_table[type][1])
- color = PERF_COLOR_MAGENTA;
- else if (ratio > grc_table[type][2])
- color = PERF_COLOR_YELLOW;
-
- return color;
-}
-
-static void print_stalled_cycles_frontend(FILE *out, int cpu,
- struct perf_evsel *evsel
- __maybe_unused, double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " frontend cycles idle ");
-}
-
-static void print_stalled_cycles_backend(FILE *out, int cpu,
- struct perf_evsel *evsel
- __maybe_unused, double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " backend cycles idle ");
-}
-
-static void print_branch_misses(FILE *out, int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_branches_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all branches ");
-}
-
-static void print_l1_dcache_misses(FILE *out, int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all L1-dcache hits ");
-}
-
-static void print_l1_icache_misses(FILE *out, int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all L1-icache hits ");
-}
-
-static void print_dtlb_cache_misses(FILE *out, int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all dTLB cache hits ");
-}
-
-static void print_itlb_cache_misses(FILE *out, int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all iTLB cache hits ");
-}
-
-static void print_ll_cache_misses(FILE *out, int cpu,
- struct perf_evsel *evsel __maybe_unused,
- double avg)
-{
- double total, ratio = 0.0;
- const char *color;
- int ctx = evsel_context(evsel);
-
- total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
-
- if (total)
- ratio = avg / total * 100.0;
-
- color = get_ratio_color(GRC_CACHE_MISSES, ratio);
-
- fprintf(out, " # ");
- color_fprintf(out, color, "%6.2f%%", ratio);
- fprintf(out, " of all LL-cache hits ");
-}
-
-static void print_shadow_stats(FILE *out, struct perf_evsel *evsel,
- double avg, int cpu, enum aggr_mode aggr)
-{
- double total, ratio = 0.0, total2;
- int ctx = evsel_context(evsel);
-
- if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
- if (total) {
- ratio = avg / total;
- fprintf(out, " # %5.2f insns per cycle ", ratio);
- } else {
- fprintf(out, " ");
- }
- total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
- total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
-
- if (total && avg) {
- ratio = total / avg;
- fprintf(out, "\n");
- if (aggr == AGGR_NONE)
- fprintf(out, " ");
- fprintf(out, " # %5.2f stalled cycles per insn", ratio);
- }
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
- runtime_branches_stats[ctx][cpu].n != 0) {
- print_branch_misses(out, cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_l1_dcache_stats[ctx][cpu].n != 0) {
- print_l1_dcache_misses(out, cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_l1_icache_stats[ctx][cpu].n != 0) {
- print_l1_icache_misses(out, cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
- print_dtlb_cache_misses(out, cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_itlb_cache_stats[ctx][cpu].n != 0) {
- print_itlb_cache_misses(out, cpu, evsel, avg);
- } else if (
- evsel->attr.type == PERF_TYPE_HW_CACHE &&
- evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
- ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
- ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
- runtime_ll_cache_stats[ctx][cpu].n != 0) {
- print_ll_cache_misses(out, cpu, evsel, avg);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
- runtime_cacherefs_stats[ctx][cpu].n != 0) {
- total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
-
- if (total)
- ratio = avg * 100 / total;
-
- fprintf(out, " # %8.3f %% of all cache refs ", ratio);
-
- } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
- print_stalled_cycles_frontend(out, cpu, evsel, avg);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
- print_stalled_cycles_backend(out, cpu, evsel, avg);
- } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
- total = avg_stats(&runtime_nsecs_stats[cpu]);
-
- if (total) {
- ratio = avg / total;
- fprintf(out, " # %8.3f GHz ", ratio);
- } else {
- fprintf(out, " ");
- }
- } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
- if (total)
- fprintf(out,
- " # %5.2f%% transactional cycles ",
- 100.0 * (avg / total));
- } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
- total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
- total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
- if (total2 < avg)
- total2 = avg;
- if (total)
- fprintf(out,
- " # %5.2f%% aborted cycles ",
- 100.0 * ((total2-avg) / total));
- } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
- avg > 0 &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
- total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
-
- if (total)
- ratio = total / avg;
-
- fprintf(out, " # %8.0f cycles / transaction ", ratio);
- } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
- avg > 0 &&
- runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
- total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
-
- if (total)
- ratio = total / avg;
-
- fprintf(out, " # %8.0f cycles / elision ", ratio);
- } else if (runtime_nsecs_stats[cpu].n != 0) {
- char unit = 'M';
-
- total = avg_stats(&runtime_nsecs_stats[cpu]);
-
- if (total)
- ratio = 1000.0 * avg / total;
- if (ratio < 0.001) {
- ratio *= 1000;
- unit = 'K';
- }
-
- fprintf(out, " # %8.3f %c/sec ", ratio, unit);
- } else {
- fprintf(out, " ");
- }
-}
-
static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
{
double sc = evsel->scale;
@@ -1230,7 +794,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
if (csv_output || interval)
return;
- print_shadow_stats(output, evsel, avg, cpu, aggr_mode);
+ perf_stat__print_shadow_stats(output, evsel, avg, cpu, aggr_mode);
}
static void print_aggr(char *prefix)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index e4b676d..586a59d 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -68,6 +68,7 @@ libperf-y += rblist.o
libperf-y += intlist.o
libperf-y += vdso.o
libperf-y += stat.o
+libperf-y += stat-shadow.o
libperf-y += record.o
libperf-y += srcline.o
libperf-y += data.o
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
new file mode 100644
index 0000000..53e8bb7
--- /dev/null
+++ b/tools/perf/util/stat-shadow.c
@@ -0,0 +1,434 @@
+#include <stdio.h>
+#include "evsel.h"
+#include "stat.h"
+#include "color.h"
+
+enum {
+ CTX_BIT_USER = 1 << 0,
+ CTX_BIT_KERNEL = 1 << 1,
+ CTX_BIT_HV = 1 << 2,
+ CTX_BIT_HOST = 1 << 3,
+ CTX_BIT_IDLE = 1 << 4,
+ CTX_BIT_MAX = 1 << 5,
+};
+
+#define NUM_CTX CTX_BIT_MAX
+
+static struct stats runtime_nsecs_stats[MAX_NR_CPUS];
+static struct stats runtime_cycles_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_front_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_stalled_cycles_back_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_branches_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cacherefs_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_dcache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_l1_icache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_ll_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_itlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_dtlb_cache_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_cycles_in_tx_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_transaction_stats[NUM_CTX][MAX_NR_CPUS];
+static struct stats runtime_elision_stats[NUM_CTX][MAX_NR_CPUS];
+
+struct stats walltime_nsecs_stats;
+
+static int evsel_context(struct perf_evsel *evsel)
+{
+ int ctx = 0;
+
+ if (evsel->attr.exclude_kernel)
+ ctx |= CTX_BIT_KERNEL;
+ if (evsel->attr.exclude_user)
+ ctx |= CTX_BIT_USER;
+ if (evsel->attr.exclude_hv)
+ ctx |= CTX_BIT_HV;
+ if (evsel->attr.exclude_host)
+ ctx |= CTX_BIT_HOST;
+ if (evsel->attr.exclude_idle)
+ ctx |= CTX_BIT_IDLE;
+
+ return ctx;
+}
+
+void perf_stat__reset_shadow_stats(void)
+{
+ memset(runtime_nsecs_stats, 0, sizeof(runtime_nsecs_stats));
+ memset(runtime_cycles_stats, 0, sizeof(runtime_cycles_stats));
+ memset(runtime_stalled_cycles_front_stats, 0, sizeof(runtime_stalled_cycles_front_stats));
+ memset(runtime_stalled_cycles_back_stats, 0, sizeof(runtime_stalled_cycles_back_stats));
+ memset(runtime_branches_stats, 0, sizeof(runtime_branches_stats));
+ memset(runtime_cacherefs_stats, 0, sizeof(runtime_cacherefs_stats));
+ memset(runtime_l1_dcache_stats, 0, sizeof(runtime_l1_dcache_stats));
+ memset(runtime_l1_icache_stats, 0, sizeof(runtime_l1_icache_stats));
+ memset(runtime_ll_cache_stats, 0, sizeof(runtime_ll_cache_stats));
+ memset(runtime_itlb_cache_stats, 0, sizeof(runtime_itlb_cache_stats));
+ memset(runtime_dtlb_cache_stats, 0, sizeof(runtime_dtlb_cache_stats));
+ memset(runtime_cycles_in_tx_stats, 0,
+ sizeof(runtime_cycles_in_tx_stats));
+ memset(runtime_transaction_stats, 0,
+ sizeof(runtime_transaction_stats));
+ memset(runtime_elision_stats, 0, sizeof(runtime_elision_stats));
+ memset(&walltime_nsecs_stats, 0, sizeof(walltime_nsecs_stats));
+}
+
+/*
+ * Update various tracking values we maintain to print
+ * more semantic information such as miss/hit ratios,
+ * instruction rates, etc:
+ */
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+ int cpu)
+{
+ int ctx = evsel_context(counter);
+
+ if (perf_evsel__match(counter, SOFTWARE, SW_TASK_CLOCK))
+ update_stats(&runtime_nsecs_stats[cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
+ update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
+ update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, TRANSACTION_START))
+ update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+ else if (perf_stat_evsel__is(counter, ELISION_START))
+ update_stats(&runtime_elision_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
+ update_stats(&runtime_stalled_cycles_front_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
+ update_stats(&runtime_stalled_cycles_back_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
+ update_stats(&runtime_branches_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
+ update_stats(&runtime_cacherefs_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+ update_stats(&runtime_l1_dcache_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_LL))
+ update_stats(&runtime_ll_cache_stats[ctx][cpu], count[0]);
+ else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
+ 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]);
+}
+
+/* used for get_ratio_color() */
+enum grc_type {
+ GRC_STALLED_CYCLES_FE,
+ GRC_STALLED_CYCLES_BE,
+ GRC_CACHE_MISSES,
+ GRC_MAX_NR
+};
+
+static const char *get_ratio_color(enum grc_type type, double ratio)
+{
+ static const double grc_table[GRC_MAX_NR][3] = {
+ [GRC_STALLED_CYCLES_FE] = { 50.0, 30.0, 10.0 },
+ [GRC_STALLED_CYCLES_BE] = { 75.0, 50.0, 20.0 },
+ [GRC_CACHE_MISSES] = { 20.0, 10.0, 5.0 },
+ };
+ const char *color = PERF_COLOR_NORMAL;
+
+ if (ratio > grc_table[type][0])
+ color = PERF_COLOR_RED;
+ else if (ratio > grc_table[type][1])
+ color = PERF_COLOR_MAGENTA;
+ else if (ratio > grc_table[type][2])
+ color = PERF_COLOR_YELLOW;
+
+ return color;
+}
+
+static void print_stalled_cycles_frontend(FILE *out, int cpu,
+ struct perf_evsel *evsel
+ __maybe_unused, double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_STALLED_CYCLES_FE, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " frontend cycles idle ");
+}
+
+static void print_stalled_cycles_backend(FILE *out, int cpu,
+ struct perf_evsel *evsel
+ __maybe_unused, double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_STALLED_CYCLES_BE, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " backend cycles idle ");
+}
+
+static void print_branch_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_branches_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all branches ");
+}
+
+static void print_l1_dcache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_l1_dcache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all L1-dcache hits ");
+}
+
+static void print_l1_icache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_l1_icache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all L1-icache hits ");
+}
+
+static void print_dtlb_cache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_dtlb_cache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all dTLB cache hits ");
+}
+
+static void print_itlb_cache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_itlb_cache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all iTLB cache hits ");
+}
+
+static void print_ll_cache_misses(FILE *out, int cpu,
+ struct perf_evsel *evsel __maybe_unused,
+ double avg)
+{
+ double total, ratio = 0.0;
+ const char *color;
+ int ctx = evsel_context(evsel);
+
+ total = avg_stats(&runtime_ll_cache_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg / total * 100.0;
+
+ color = get_ratio_color(GRC_CACHE_MISSES, ratio);
+
+ fprintf(out, " # ");
+ color_fprintf(out, color, "%6.2f%%", ratio);
+ fprintf(out, " of all LL-cache hits ");
+}
+
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+ double avg, int cpu, enum aggr_mode aggr)
+{
+ double total, ratio = 0.0, total2;
+ int ctx = evsel_context(evsel);
+
+ if (perf_evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ if (total) {
+ ratio = avg / total;
+ fprintf(out, " # %5.2f insns per cycle ", ratio);
+ } else {
+ fprintf(out, " ");
+ }
+ total = avg_stats(&runtime_stalled_cycles_front_stats[ctx][cpu]);
+ total = max(total, avg_stats(&runtime_stalled_cycles_back_stats[ctx][cpu]));
+
+ if (total && avg) {
+ ratio = total / avg;
+ fprintf(out, "\n");
+ if (aggr == AGGR_NONE)
+ fprintf(out, " ");
+ fprintf(out, " # %5.2f stalled cycles per insn", ratio);
+ }
+
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
+ runtime_branches_stats[ctx][cpu].n != 0) {
+ print_branch_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1D |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_l1_dcache_stats[ctx][cpu].n != 0) {
+ print_l1_dcache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_L1I |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_l1_icache_stats[ctx][cpu].n != 0) {
+ print_l1_icache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_DTLB |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_dtlb_cache_stats[ctx][cpu].n != 0) {
+ print_dtlb_cache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_ITLB |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_itlb_cache_stats[ctx][cpu].n != 0) {
+ print_itlb_cache_misses(out, cpu, evsel, avg);
+ } else if (
+ evsel->attr.type == PERF_TYPE_HW_CACHE &&
+ evsel->attr.config == ( PERF_COUNT_HW_CACHE_LL |
+ ((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
+ ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16)) &&
+ runtime_ll_cache_stats[ctx][cpu].n != 0) {
+ print_ll_cache_misses(out, cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
+ runtime_cacherefs_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cacherefs_stats[ctx][cpu]);
+
+ if (total)
+ ratio = avg * 100 / total;
+
+ fprintf(out, " # %8.3f %% of all cache refs ", ratio);
+
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
+ print_stalled_cycles_frontend(out, cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
+ print_stalled_cycles_backend(out, cpu, evsel, avg);
+ } else if (perf_evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
+ total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+ if (total) {
+ ratio = avg / total;
+ fprintf(out, " # %8.3f GHz ", ratio);
+ } else {
+ fprintf(out, " ");
+ }
+ } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ if (total)
+ fprintf(out,
+ " # %5.2f%% transactional cycles ",
+ 100.0 * (avg / total));
+ } else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
+ total = avg_stats(&runtime_cycles_stats[ctx][cpu]);
+ total2 = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+ if (total2 < avg)
+ total2 = avg;
+ if (total)
+ fprintf(out,
+ " # %5.2f%% aborted cycles ",
+ 100.0 * ((total2-avg) / total));
+ } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
+ avg > 0 &&
+ runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+ if (total)
+ ratio = total / avg;
+
+ fprintf(out, " # %8.0f cycles / transaction ", ratio);
+ } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
+ avg > 0 &&
+ runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
+ total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
+
+ if (total)
+ ratio = total / avg;
+
+ fprintf(out, " # %8.0f cycles / elision ", ratio);
+ } else if (runtime_nsecs_stats[cpu].n != 0) {
+ char unit = 'M';
+
+ total = avg_stats(&runtime_nsecs_stats[cpu]);
+
+ if (total)
+ ratio = 1000.0 * avg / total;
+ if (ratio < 0.001) {
+ ratio *= 1000;
+ unit = 'K';
+ }
+
+ fprintf(out, " # %8.3f %c/sec ", ratio, unit);
+ } else {
+ fprintf(out, " ");
+ }
+}
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 3df529b..615c779 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -2,6 +2,7 @@
#define __PERF_STATS_H
#include <linux/types.h>
+#include <stdio.h>
struct stats
{
@@ -23,6 +24,13 @@ struct perf_stat {
enum perf_stat_evsel_id id;
};
+enum aggr_mode {
+ AGGR_NONE,
+ AGGR_GLOBAL,
+ AGGR_SOCKET,
+ AGGR_CORE,
+};
+
void update_stats(struct stats *stats, u64 val);
double avg_stats(struct stats *stats);
double stddev_stats(struct stats *stats);
@@ -46,4 +54,12 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
void perf_stat_evsel_id_init(struct perf_evsel *evsel);
+extern struct stats walltime_nsecs_stats;
+
+void perf_stat__reset_shadow_stats(void);
+void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
+ int cpu);
+void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
+ double avg, int cpu, enum aggr_mode aggr);
+
#endif
OpenPOWER on IntegriCloud