perf stat: Print out miss/hit ratio for L1 data-cache events

Print out this kind of l1-dcache-misses percentage:

 Performance counter stats for './bw_tcp localhost':

    29,956,262,201 cycles                   #    3.002 GHz                      (scaled from 85.14%)
     8,255,209,558 stalled-cycles           #   27.56% of all cycles are idle   (scaled from 86.56%)
     1,206,130,308 l1-dcache-misses         #   40.49% of all L1-dcache hits    (scaled from 86.30%)
     2,978,756,779 l1-dcache-refs           #  298.512 M/sec                    (scaled from 70.02%)
     8,861,956,159 instructions             #    0.30  insns per cycle
                                            #    0.93  stalled cycles per insn  (scaled from 84.27%)
     1,644,306,068 branches                 #  164.782 M/sec                    (scaled from 86.43%)
        74,778,443 branch-misses            #    4.55% of all branches          (scaled from 70.69%)
       9978.695711 task-clock               #    0.693 CPUs utilized

       14.404347983  seconds time elapsed

And color the result depending on the severity of cache-trashing.

Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/n/tip-54gmz0zymaid84zcs7joq02p@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 33 insertions, 0 deletions

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 5d4e1b9b2d89..03bac6aa014b 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -159,6 +159,7 @@ struct stats			runtime_cycles_stats[MAX_NR_CPUS];
 struct stats                    runtime_stalled_cycles_stats[MAX_NR_CPUS];
 struct stats                    runtime_branches_stats[MAX_NR_CPUS];
 struct stats                    runtime_cacherefs_stats[MAX_NR_CPUS];
+struct stats                    runtime_l1_dcache_stats[MAX_NR_CPUS];
 struct stats                    walltime_nsecs_stats;
 
 static int create_perf_stat_counter(struct perf_evsel *evsel)
@@ -211,6 +212,8 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
                 update_stats(&runtime_branches_stats[0], count[0]);
         else if (perf_evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
                 update_stats(&runtime_cacherefs_stats[0], count[0]);
+        else if (perf_evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
+                update_stats(&runtime_l1_dcache_stats[0], count[0]);
 }
 
 /*
@@ -473,6 +476,29 @@ static void print_branch_misses(int cpu, struct perf_evsel *evsel __used, double
         fprintf(stderr, " of all branches        ");
 }
 
+static void print_l1_dcache_misses(int cpu, struct perf_evsel *evsel __used, double avg)
+{
+        double total, ratio = 0.0;
+        const char *color;
+
+        total = avg_stats(&runtime_l1_dcache_stats[cpu]);
+
+        if (total)
+                ratio = avg / total * 100.0;
+
+        color = PERF_COLOR_NORMAL;
+        if (ratio > 20.0)
+                color = PERF_COLOR_RED;
+        else if (ratio > 10.0)
+                color = PERF_COLOR_MAGENTA;
+        else if (ratio > 5.0)
+                color = PERF_COLOR_YELLOW;
+
+        fprintf(stderr, " #   ");
+        color_fprintf(stderr, color, "%5.2f%%", ratio);
+        fprintf(stderr, " of all L1-dcache hits  ");
+}
+
 static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
 {
         double total, ratio = 0.0;
@@ -519,6 +545,13 @@ static void abs_printout(int cpu, struct perf_evsel *evsel, double avg)
         } else if (perf_evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES) &&
                         runtime_branches_stats[cpu].n != 0) {
                 print_branch_misses(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_branches_stats[cpu].n != 0) {
+                print_l1_dcache_misses(cpu, evsel, avg);
         } else if (perf_evsel__match(evsel, HARDWARE, HW_CACHE_MISSES) &&
                         runtime_cacherefs_stats[cpu].n != 0) {
                 total = avg_stats(&runtime_cacherefs_stats[cpu]);