Re: [PATCH 3/4] perf/x86/mbm: Fix mbm counting when RMIDs are reused

[Vikas Shivappa]

On Mon, 25 Apr 2016, Peter Zijlstra wrote:

> On Mon, Apr 25, 2016 at 09:44:53AM -0700, Vikas Shivappa wrote:
> > On Mon, 25 Apr 2016, Peter Zijlstra wrote:
> >
> > > On Fri, Apr 22, 2016 at 05:27:20PM -0700, Vikas Shivappa wrote:
> > > > When multiple instances of perf reuse RMID, then we need to start
> > > > counting for each instance rather than reporting the current RMID count.
> > > > This patch adds a st_count(start count) per event to track the same.
> > >
> > > what?
> >
> > Will fix the comit log :
> >
> > When multiple instances of perf reuse RMID for the same PID, then we need to
> > start counting from zero for each new event, rather than reporting the
> > current RMID. This patch adds a st_count(start count) per event to track the
> > same.
> >
> > For ex:
> > 1.RMID1's total_bytes is 100MB for event1(PID1)
> > 2.another perf instance starts measuring the same PID1 with event2. We reuse
> > RMID1 as the PID1 is already counted.
> > 3.event2 stores st_count as 100MB.
> > 4.After some time, when user wants to count event2 and say RMID1's current
> > total_bytes 110MB, we report 110MB - 100MB = 10MB
>
> This is naturally handled by the scheme I outlined in the other patch.

Something similar although there is one per rmid and one per event..

u64 read_sample(rmid...) // for each rmid
{
...

start:
  'per rmid' prev = read_hw_counter();

count:
  cur_count = read_hw_counter();
  delta = cur_count - prev;
  prev = cur_count;
  total_bytes += delta;

  return total_bytes;
}

when we lose the rmid -

xchng(event, rmid=-1)
{
..

'per event' rc_count = read_sample(event->rmid) - per event start count;
'per event' start_count = 0;

}


for each event -

start:
  if rmid is reused
   'per event' prev = read_sample(rmid);
  else
   prev = 0;

count: // we use count instead of read
  count = read_sample(rmid) + rc_count - prev;


>