Messages in this thread | | | Subject | Re: [PATCH 1/2] Make the batch size of the percpu_counter configurable | From | Tim Chen <> | Date | Tue, 30 Apr 2013 11:28:09 -0700 |
| |
On Tue, 2013-04-30 at 11:10 -0700, Eric Dumazet wrote: > On Tue, 2013-04-30 at 09:23 -0700, Tim Chen wrote: > > On Tue, 2013-04-30 at 13:32 +0000, Christoph Lameter wrote: > > > On Mon, 29 Apr 2013, Tim Chen wrote: > > > > > > > diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h > > > > index d5dd465..5ca7df5 100644 > > > > --- a/include/linux/percpu_counter.h > > > > +++ b/include/linux/percpu_counter.h > > > > @@ -22,6 +22,7 @@ struct percpu_counter { > > > > struct list_head list; /* All percpu_counters are on a list */ > > > > #endif > > > > s32 __percpu *counters; > > > > + int *batch ____cacheline_aligned_in_smp; > > > > }; > > > > > > What is this for and why does it have that alignmend? > > > > I was assuming that if batch is frequently referenced, it probably > > should not share a cache line with the counters field. > > But 'counters' field has the same requirement. Its supposed to be read > only field. > > So please remove this '____cacheline_aligned_in_smp', as it makes the > whole struct percpu_counter at least two cache lines wide, for no > obvious reason. >
Will do.
Thanks.
Tim
| |