Messages in this thread |  | | | Date | Thu, 2 Apr 2009 13:32:34 +0200 | | From | Ingo Molnar <> | | Subject | Re: [PATCH 3/6] perf_counter: per event wakeups |
| |
* Peter Zijlstra <a.p.zijlstra@chello.nl> wrote:
> By request, provide a way to request a wakeup every 'n' events instead > of every page of output. > > Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> > --- > include/linux/perf_counter.h | 3 ++- > kernel/perf_counter.c | 10 +++++++++- > 2 files changed, 11 insertions(+), 2 deletions(-) > > Index: linux-2.6/include/linux/perf_counter.h > =================================================================== > --- linux-2.6.orig/include/linux/perf_counter.h > +++ linux-2.6/include/linux/perf_counter.h > @@ -146,7 +146,7 @@ struct perf_counter_hw_event { > __reserved_1 : 52; > > __u32 extra_config_len; > - __u32 __reserved_4; > + __u32 wakeup_events; /* wakeup every n events */
[ Sidenote: i think we need more reserved bits :-) Expand the ABI while it's still easy ;-) ]
I have a design observation here:
i think 'wakeup' is a user-space notification type. Another type of notication can be 'signal', or 'none'.
Perhaps your current scheme makes the most sense: to treat them as separate attributes, and allow signal delivery and wakeups at once. (if user-space so wishes)
Agreed?
Ingo
|  |