On Thu, 2011-04-14 at 14:01 -0300, Arnaldo Carvalho de Melo wrote: > > There was another, sillier problem, now seems to work, ack? > > [acme@emilia linux]$ perf stat ~/loop_1b_instructions-4x > > Performance counter stats for '/home/acme/loop_1b_instructions-4x': > > 1451.781634 task-clock-msecs # 3.965 CPUs > 1,463 context-switches # 0.001 M/sec > 3 CPU-migrations # 0.000 M/sec > 187 page-faults # 0.000 M/sec > 2,865,021,951 cycles # 1973.452 M/sec (scaled from 70.29%) > 4,001,127,146 instructions # 1.397 IPC (scaled from 80.24%) > 401,476,915 branches # 276.541 M/sec (scaled from 80.27%) > 63,800 branch-misses # 0.016 % (scaled from 80.29%) > 262,866 cache-references # 0.181 M/sec (scaled from 20.14%) > 10,938 cache-misses # 0.008 M/sec (scaled from 20.07%) > > 0.366184692 seconds time elapsed > > [acme@emilia linux]$ > > From 41d8ff6c4be9216cae74dd82381d9f486e82bf22 Mon Sep 17 00:00:00 2001 > From: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx> > Date: Thu, 14 Apr 2011 11:20:14 -0300 > Subject: [PATCH] perf evsel: Fix use of inherit > > perf stat doesn't mmap and its perfectly fine for it to use task-bound > counters with inheritance. > > So set the attr.inherit on the caller and leave the syscall itself to > validate it. > > When the mmap fails perf_evlist__mmap will just emit a warning if this > is the failure reason. > > Reported-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx> > Cc: Frederic Weisbecker <fweisbec@xxxxxxxxx> > Cc: Ingo Molnar <mingo@xxxxxxx> > Cc: Mike Galbraith <efault@xxxxxx> > Cc: Paul Mackerras <paulus@xxxxxxxxx> > Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx> > Cc: Stephane Eranian <eranian@xxxxxxxxxx> > Cc: Tom Zanussi <tzanussi@xxxxxxxxx> > Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx> Yay works! Acked-by: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> -- To unsubscribe from this list: send the line "unsubscribe linux-tip-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
|