Messages in this thread | | | Date | Wed, 6 Jun 2012 12:12:40 +0200 | Subject | Re: [PATCH] perf: Fix intel shared extra msr allocation | From | Stephane Eranian <> |
| |
There is something wrong with this patch, I instrumented the code and I can see: [ 1377.324575] 1. idx=1 reg_idx=1 ref=-1 config=0xff01 era->config=0xff01 ^^^^^^ The test case on WSM (RSP0, RSP1):
$ perf stat -a -C13 -e offcore_response_1:dmnd_data_rd,offcore_response_1:dmnd_data_rd sleep 100 & $ perf stat -a -C1 -e offcore_response_1:dmnd_rfo sleep 1
I think this happens during scheduling of the events, i.e., during the run and not on initial programming. That could happen with cgroups, for instance.
On Tue, Jun 5, 2012 at 3:51 PM, Stephane Eranian <eranian@google.com> wrote: > On Tue, Jun 5, 2012 at 3:47 PM, Peter Zijlstra <peterz@infradead.org> wrote: >> On Tue, 2012-06-05 at 15:38 +0200, Stephane Eranian wrote: >> >>> Will try it on my systems. Though it appears the patch has some >>> ^M all over. >> >> Yeah, stupid evolution can only do quoted-printable these days.. >> progress they call this :/ >> >> I can send you an awk script to unmangle it if you want.. but git can do >> it too somehow. > > Will try with git, otherwise can do it manually, patch is small enough. > Thanks.
| |