Re: [PATCH 3/4] Embed zone_id information within the zonelist->zones pointer

[Mel Gorman]

On (09/08/07 14:37), Christoph Lameter didst pronounce:
> On Thu, 9 Aug 2007, Mel Gorman wrote:
> 
> >  }
> >  
> > +#if defined(CONFIG_SMP) && INTERNODE_CACHE_SHIFT > ZONES_SHIFT
> 
> Is this necessary? ZONES_SHIFT is always <= 2 so it will work with 
> any pointer. Why disable this for UP?
> 

Caution in case the number of zones increases. There was no guarantee of
zone alignment. It's the same reason I have a BUG_ON in the encode
function so that if we don't catch problems at compile-time, it'll go
BANG in a nice predictable fashion.

> > --- linux-2.6.23-rc1-mm2-010_use_zonelist/mm/vmstat.c	2007-08-07 14:45:11.000000000 +0100
> > +++ linux-2.6.23-rc1-mm2-015_zoneid_zonelist/mm/vmstat.c	2007-08-09 15:52:12.000000000 +0100
> > @@ -365,11 +365,11 @@ void refresh_cpu_vm_stats(int cpu)
> >   */
> >  void zone_statistics(struct zonelist *zonelist, struct zone *z)
> >  {
> > -	if (z->zone_pgdat == zonelist->zones[0]->zone_pgdat) {
> > +	if (z->zone_pgdat == zonelist_zone(zonelist->_zones[0])->zone_pgdat) {
> >  		__inc_zone_state(z, NUMA_HIT);
> >  	} else {
> >  		__inc_zone_state(z, NUMA_MISS);
> > -		__inc_zone_state(zonelist->zones[0], NUMA_FOREIGN);
> > +		__inc_zone_state(zonelist_zone(zonelist->_zones[0]), NUMA_FOREIGN);
> >  	}
> >  	if (z->node == numa_node_id())
> >  		__inc_zone_state(z, NUMA_LOCAL);
> 
> Hmmmm. I hope the compiler does subexpression optimization on 
> 
> 	zonelist_zone(zonelist->_zones[0]) 
> 

I'll check

> Acked-by: Christoph Lameter <clameter@xxxxxxx>
> 

-- 
-- 
Mel Gorman
Part-time Phd Student                          Linux Technology Center
University of Limerick                         IBM Dublin Software Lab
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/