perf trace: Tweak summary output

Tweak the summary output as suggested by Ingo Molnar:

  [penberg@localhost ~]$ perf trace -a --duration 10000 --summary -- sleep 1
  ^C
   Summary of events:

   Xorg (817), 148 events, 0.0%, 0.000 msec

     syscall            calls      min       avg       max      stddev
                                 (msec)    (msec)    (msec)        (%)
     --------------- -------- --------- --------- ---------     ------
     read                   7     0.002     0.004     0.011     32.00%
     rt_sigprocmask        40     0.001     0.001     0.002      1.31%
     ioctl                  6     0.002     0.003     0.005     19.45%
     writev                 7     0.004     0.018     0.059     43.76%
     select                 9     0.000    74.513   507.869     74.61%
     setitimer              4     0.001     0.002     0.002     10.08%

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Pekka Enberg <penberg@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Link: http://lkml.kernel.org/r/1384345308-24404-1-git-send-email-penberg@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-trace.c

@@ -2112,9 +2112,9 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 
 	printed += fprintf(fp, "\n");
 
-	printed += fprintf(fp, "                                                    msec/call\n");
-	printed += fprintf(fp, "   syscall            calls      min      avg      max stddev\n");
-	printed += fprintf(fp, "   --------------- -------- -------- -------- -------- ------\n");
+	printed += fprintf(fp, "   syscall            calls      min       avg       max      stddev\n");
+	printed += fprintf(fp, "                               (msec)    (msec)    (msec)        (%%)\n");
+	printed += fprintf(fp, "   --------------- -------- --------- --------- ---------     ------\n");
 
 	/* each int_node is a syscall */
 	while (inode) {
@@ -2131,9 +2131,9 @@ static size_t thread__dump_stats(struct thread_trace *ttrace,
 
 			sc = &trace->syscalls.table[inode->i];
 			printed += fprintf(fp, "   %-15s", sc->name);
-			printed += fprintf(fp, " %8" PRIu64 " %8.3f %8.3f",
+			printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f",
 					   n, min, avg);
-			printed += fprintf(fp, " %8.3f %6.2f\n", max, pct);
+			printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
 		}
 
 		inode = intlist__next(inode);