Commit a1cb2c60 authored Oct 31, 2011 by Dimitri Sivanich Committed by Linus Torvalds Oct 31, 2011

mm/vmstat.c: cache align vm_stat



Avoid false sharing of the vm_stat array.

This was found to adversely affect tmpfs I/O performance.

Tests run on a 640 cpu UV system.

With 120 threads doing parallel writes, each to different tmpfs mounts:
No patch:		~300 MB/sec
With vm_stat alignment:	~430 MB/sec

Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
Acked-by: Christoph Lameter <cl@gentwo.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

parent 3d470fc3

mm/vmstat.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -78,7 +78,7 @@ void vm_events_fold_cpu(int cpu)
		*
		* vm_stat contains the global counters
		*/
		atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
		atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
		EXPORT_SYMBOL(vm_stat);

		#ifdef CONFIG_SMP