Re: [RFC][PATCH 0/8] perf pmu interface

[Frederic Weisbecker <fweisbec@gmail.com>]

On Wed, Jun 16, 2010 at 08:19:32PM +0200, Peter Zijlstra wrote:
> On Wed, 2010-06-16 at 18:00 +0200, Peter Zijlstra wrote:
> > These patches prepare the perf code for multiple pmus (no user
> > interface yet, Lin Ming is working on that). These patches remove all
> > weak functions and rework the struct pmu interface.
> > 
> > The latter is inspired by the work Frederic is doing to to filter out
> > IRQ contexts.
> > 
> > These patches are very prelimenary, they haven't seen a compiler yet and
> > the last patch still needs sparc,ppc and arm converted.
> > 
> > But they patches seem to be in a good enough shape to see what people
> > think..
> 
> Another idea I was kicking about was to push find_get_context()
> partially into struct pmu, so that we can have context's per pmu.
> 
> For cpu-wide contexts its easy, for per-task contexts we need more
> pointers in task_struct, so I was thinking of something like:
> 
> enum {
>   perf_swevent_context = 0,
>   perf_cpu_context,
> #ifdef HW_BREAKPOINT
>   perf_bp_context,
> #endif
>   perf_nr_task_context
> };
> 
> struct task_struct {
>   ...
>   struct perf_event_context *perf_event_ctxs[perf_nr_task_context];
>   ...
> };
> 
> and have add for loops over the struct pmu list for the cpu-wide
> contexts and for loops over perf_nr_task_context for the task contexts.
> 
> It would add some extra code to the hot-paths, but its the best I can
> come up with.


I'm not sure what you mean. Would that be to optimize the start_txn / commit_txn ?
Then that sounds a good idea. But you'd only need two groups I think:

enum {
   perf_swevent_context = 0,
   perf_cpu_context,
   perf_nr_task_context
};


As only the cpu pmu needs the txn game, at least for now.

It seems that would drop the ability to gather hardware and software
events in a same group though.