perf stat: Improve output

Increase size for event name to handle bigger names like
'L1-d$-prefetch-misses'

Changed scaled counters from percentage to a multiplicative
factor because the latter is more expressive.

Also aligned the scaling factor, otherwise sometimes it looks
like:

            384  iTLB-load-misses           (4.74x scaled)
         452029  branch-loads               (8.00x scaled)
           5892  branch-load-misses         (20.39x scaled)
         972315  iTLB-loads                 (3.24x scaled)

Before:
         150708  L1-d$-stores          (scaled from 23.57%)
         428804  L1-d$-prefetches      (scaled from 23.47%)
         314446  L1-d$-prefetch-misses  (scaled from 23.42%)
      252626137  L1-i$-loads           (scaled from 23.24%)
        5297550  dTLB-load-misses      (scaled from 23.96%)
      106992392  branch-loads          (scaled from 23.67%)
        5239561  branch-load-misses    (scaled from 23.43%)

After:
        1731713  L1-d$-loads               (  14.25x scaled)
          44241  L1-d$-prefetches          (   3.88x scaled)
          21076  L1-d$-prefetch-misses     (   3.40x scaled)
        5789421  L1-i$-loads               (   3.78x scaled)
          29645  dTLB-load-misses          (   2.95x scaled)
         461474  branch-loads              (   6.52x scaled)
           7493  branch-load-misses        (  26.57x scaled)

Reported-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Jaswinder Singh Rajput <jaswinderrajput@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <1246051927.2988.10.camel@hpdv5.satnam>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 52c176cc683ec4c7b5bffbec552c4460b705208f..3840a70f05b7297df70ff921f1293672961d3699 100644 (file)
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -32,6 +32,7 @@
  *   Wu Fengguang <fengguang.wu@intel.com>
  *   Mike Galbraith <efault@gmx.de>
  *   Paul Mackerras <paulus@samba.org>
+ *   Jaswinder Singh Rajput <jaswinder@kernel.org>
  *
  * Released under the GPL v2. (and only v2, not any later version)
  */
@@ -251,7 +252,7 @@ static void nsec_printout(int counter, u64 *count, u64 *noise)
 {
        double msecs = (double)count[0] / 1000000;
 
-       fprintf(stderr, " %14.6f  %-20s", msecs, event_name(counter));
+       fprintf(stderr, " %14.6f  %-24s", msecs, event_name(counter));
 
        if (attrs[counter].type == PERF_TYPE_SOFTWARE &&
                attrs[counter].config == PERF_COUNT_SW_TASK_CLOCK) {
@@ -265,7 +266,7 @@ static void nsec_printout(int counter, u64 *count, u64 *noise)
 
 static void abs_printout(int counter, u64 *count, u64 *noise)
 {
-       fprintf(stderr, " %14Ld  %-20s", count[0], event_name(counter));
+       fprintf(stderr, " %14Ld  %-24s", count[0], event_name(counter));
 
        if (runtime_cycles_avg &&
                attrs[counter].type == PERF_TYPE_HARDWARE &&
@@ -295,7 +296,7 @@ static void print_counter(int counter)
        scaled = event_scaled_avg[counter];
 
        if (scaled == -1) {
-               fprintf(stderr, " %14s  %-20s\n",
+               fprintf(stderr, " %14s  %-24s\n",
                        "<not counted>", event_name(counter));
                return;
        }
@@ -306,8 +307,7 @@ static void print_counter(int counter)
                abs_printout(counter, count, noise);
 
        if (scaled)
-               fprintf(stderr, "  (scaled from %.2f%%)",
-                       (double) count[2] / count[1] * 100);
+               fprintf(stderr, "  (%7.2fx scaled)", (double)count[1]/count[2]);
 
        fprintf(stderr, "\n");
 }
@@ -421,7 +421,6 @@ static void print_stat(int argc, const char **argv)
        for (counter = 0; counter < nr_counters; counter++)
                print_counter(counter);
 
-
        fprintf(stderr, "\n");
        fprintf(stderr, " %14.9f  seconds time elapsed",
                        (double)walltime_nsecs_avg/1e9);