Messages in this thread | | | From | Andi Kleen <> | Subject | Re: [PATCH v4 0/9] perf, x86: large PEBS interrupt threshold | Date | Thu, 31 Jul 2014 07:50:44 -0700 |
| |
Peter Zijlstra <peterz@infradead.org> writes: > > No feedback on the correctness aspects of the overflow crap?
I assume you mean collisions? See below.
> A quick look at patch 6 reads like you still don't understand the issue > right. There are no 'collisions' as such in PEBS record generation, or > are there? See the earlier open discussion.
There can be collisions, but they are in practice extremely rare.
The only way you can get a lot of collision is if you count the same thing multiple times which is not a useful configuration. A single monitoring tool only needs a single event once. While multiple processes may be configuring multiple events at the same time, they will not start them at the same time which also prevents collisions.
-Andi
-- ak@linux.intel.com -- Speaking for myself only
| |