Messages in this thread | | | Subject | Re: [PATCH 16/23] mm: scalable bdi statistics counters. | From | Peter Zijlstra <> | Date | Fri, 17 Aug 2007 18:23:02 +0200 |
| |
On Fri, 2007-08-17 at 12:20 -0400, Josef Sipek wrote: > On Thu, Aug 16, 2007 at 09:45:41AM +0200, Peter Zijlstra wrote: > .... > > Index: linux-2.6/include/linux/backing-dev.h > > =================================================================== > > --- linux-2.6.orig/include/linux/backing-dev.h > > +++ linux-2.6/include/linux/backing-dev.h > .... > > @@ -24,6 +26,12 @@ enum bdi_state { > > > > typedef int (congested_fn)(void *, int); > > > > +enum bdi_stat_item { > > + NR_BDI_STAT_ITEMS > > +}; > > enum numbering starts at 0, so NR_BDI_STAT_ITEMS == 0 > > > + > > +#define BDI_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) > > + > > struct backing_dev_info { > > unsigned long ra_pages; /* max readahead in PAGE_CACHE_SIZE units */ > > unsigned long state; /* Always use atomic bitops on this */ > > @@ -32,15 +40,86 @@ struct backing_dev_info { > > void *congested_data; /* Pointer to aux data for congested func */ > > void (*unplug_io_fn)(struct backing_dev_info *, struct page *); > > void *unplug_io_data; > > + > > + struct percpu_counter bdi_stat[NR_BDI_STAT_ITEMS]; > > So, this is a 0-element array. > > > }; > > > > -static inline int bdi_init(struct backing_dev_info *bdi) > > +int bdi_init(struct backing_dev_info *bdi); > > +void bdi_destroy(struct backing_dev_info *bdi); > > + > > +static inline void __add_bdi_stat(struct backing_dev_info *bdi, > > + enum bdi_stat_item item, s64 amount) > > { > > - return 0; > > + __percpu_counter_add(&bdi->bdi_stat[item], amount, BDI_STAT_BATCH); > > Boom! > > > }
Quite so, but since there are no callers _yet_ it will not go boom :-)
This patch introduces the framework, patch 17 and 18 will introduce both stat items and callers.
So it should all work out just fine. [unhandled content-type:application/pgp-signature] | |