lkml.org 
[lkml]   [2015]   [Jul]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
From
Date
SubjectRe: perf: multiplexing broken on amd fam16h?
On Wed, 22 Jul 2015, Peter Zijlstra wrote:

> On Tue, Jul 21, 2015 at 02:14:54PM -0400, Vince Weaver wrote:
> > If I run the perf_event_tests check_multiplexing test it fails like this:
>
> FWIW, that contains:
>
> /* we have to close, because PERF_EVENT_IOC_RESET */
> /* does not clear multiplexing informatio. */
>
> Do you need that? We could add another reset ioctl with a flags argument
> on what all to clear.

I remember being surprised by that behavior at the time, but I don't think
I've run into the issue much. PAPI (which has pretty awful multiplexing
support) tends to close and reopen events anytime you change the config,
rather than trying to RESET them.

I'll be rebooting the A8 system with your patch shortly.
$%C&^*# systemd insits on delaying reboots by 90 seconds for obscure
reasons which is slowing down my testing regime a bit.

Vince


\
 
 \ /
  Last update: 2015-07-22 16:41    [W:0.090 / U:1.096 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site