lkml.org 
[lkml]   [2012]   [Jun]   [6]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    Date
    From
    SubjectRe: [PATCH 2/5] perf, x86: Don't assume there can be only 4 PEBS events
    On Wed, Jun 06, 2012 at 05:00:03PM +0200, Peter Zijlstra wrote:
    > On Tue, 2012-06-05 at 17:56 -0700, Andi Kleen wrote:
    > > On Sandy Bridge in non HT mode there are 8 counters available. Since every
    > > counter can write a PEBS record assuming there are 4 max is incorrect. Use
    > > the reported counter number -- with an upper limit for a static array -- instead.
    >
    >
    > While I queued this patch, its effectively a NOP since all SNB PEBS
    > constraints are still on 4 counters.

    Yes need to update the constraints too. I think Stephane was looking at that.
    Perhaps two sets depending on the counters in CPUID?

    FWIW I saw the warn on triggering.

    -Andi
    --
    ak@linux.intel.com -- Speaking for myself only.


    \
     
     \ /
      Last update: 2012-06-07 12:43    [W:9.647 / U:0.248 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site