VM Statistics: Make timer deferrable VM statistics updates do not matter if the kernel is in idle powersaving mode. So allow the timer to be deferred. It would be better though if we could switch the timer between deferrable and nondeferrable based on differentials present. The timer would start out nondeferrable and if we find that there were no updates in the last statistics interval then we would switch the timer to deferrable. If the timer then finds that there are differentials again then go to nondeferrable again. And yet another way would be to run the timer shortly before going to idle? The solution here means that the VM counters may be slightly off during idle since differentials may be still pending while the timer is deferred. Signed-off-by: Christoph Lameter --- mm/vmstat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) Index: slub/mm/vmstat.c =================================================================== --- slub.orig/mm/vmstat.c 2007-05-10 10:09:19.000000000 -0700 +++ slub/mm/vmstat.c 2007-05-10 10:10:14.000000000 -0700 @@ -698,7 +698,7 @@ static void __devinit start_cpu_timer(in { struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu); - INIT_DELAYED_WORK(vmstat_work, vmstat_update); + INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update); schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu); }