From: Rik van Riel Date: Fri, 16 May 2014 04:13:32 +0000 (-0400) Subject: sched/numa: Decay ->wakee_flips instead of zeroing X-Git-Url: http://git.cdn.openwrt.org/?a=commitdiff_plain;h=096aa33863a5e48de52d2ff30e0801b7487944f4;p=openwrt%2Fstaging%2Fblogic.git sched/numa: Decay ->wakee_flips instead of zeroing Affine wakeups have the potential to interfere with NUMA placement. If a task wakes up too many other tasks, affine wakeups will get disabled. However, regardless of how many other tasks it wakes up, it gets re-enabled once a second, potentially interfering with NUMA placement of other tasks. By decaying wakee_wakes in half instead of zeroing it, we can avoid that problem for some workloads. Signed-off-by: Rik van Riel Signed-off-by: Peter Zijlstra Cc: chegu_vinod@hp.com Cc: umgwanakikbuti@gmail.com Link: http://lkml.kernel.org/r/20140516001332.67f91af2@annuminas.surriel.com Signed-off-by: Ingo Molnar --- diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 503f750c2d25..c9617b73bcc0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4065,7 +4065,7 @@ static void record_wakee(struct task_struct *p) * about the loss. */ if (jiffies > current->wakee_flip_decay_ts + HZ) { - current->wakee_flips = 0; + current->wakee_flips >>= 1; current->wakee_flip_decay_ts = jiffies; }