Messages in this thread | | | Date | Mon, 10 Oct 2011 08:05:37 +0200 | From | Ingo Molnar <> | Subject | Re: [V3][PATCH 0/7] perf, x86: Implement AMD IBS |
| |
* Peter Zijlstra <peterz@infradead.org> wrote:
> On Tue, 2011-10-04 at 09:41 -0700, Andi Kleen wrote: > > Ingo Molnar <mingo@elte.hu> writes: > > > > > > - Testable IBS user-space code a bit more prominently integrated > > > than having to go down into a cellar with no working lights and > > > finding the code on display in tools/perf/Documentation/examples/ > > > on the bottom of a locked filing cabinet stuck in a disused > > > lavatory with a sign on the door saying 'Beware of the Leopard.' > > > > I looked at this for PEBS, and the best solution currently seems > > to be a python script that works with perf script and does some post > > processing to present the data as summary or individual samples. > > I assume that could work for IBS too. > > > > Comments? > > I would much prefer perf {ibs,pebs} commands implemented in C, so > that normal people can change/improve them too.
The other issue is performance, obviously. So for core functionality we are pretty sure we want to offer to everyone C is the preferred form.
Scripting integration *in addition* to that is obviously welcome too.
Thanks,
Ingo
| |