From ca28aa53dd95868c9e38917b9881c09dacfacf1a Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 7 Oct 2013 11:29:32 +0100 Subject: [PATCH] sched/numa: Fix task or group comparison This patch separately considers task and group affinities when searching for swap candidates during NUMA placement. If tasks are part of the same group, or no group at all, the task weights are considered. Some hysteresis is added to prevent tasks within one group from getting bounced between NUMA nodes due to tiny differences. If tasks are part of different groups, the code compares group weights, in order to favor grouping task groups together. The patch also changes the group weight multiplier to be the same as the task weight multiplier, since the two are no longer added up like before. Signed-off-by: Rik van Riel Signed-off-by: Mel Gorman Cc: Andrea Arcangeli Cc: Johannes Weiner Cc: Srikar Dronamraju Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/1381141781-10992-55-git-send-email-mgorman@suse.de Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 6f45461..423316c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -962,7 +962,7 @@ static inline unsigned long group_weight(struct task_struct *p, int nid) if (!total_faults) return 0; - return 1200 * group_faults(p, nid) / total_faults; + return 1000 * group_faults(p, nid) / total_faults; } static unsigned long weighted_cpuload(const int cpu); @@ -1068,16 +1068,34 @@ static void task_numa_compare(struct task_numa_env *env, /* * If dst and source tasks are in the same NUMA group, or not - * in any group then look only at task weights otherwise give - * priority to the group weights. + * in any group then look only at task weights. */ - if (!cur->numa_group || !env->p->numa_group || - cur->numa_group == env->p->numa_group) { + if (cur->numa_group == env->p->numa_group) { imp = taskimp + task_weight(cur, env->src_nid) - task_weight(cur, env->dst_nid); + /* + * Add some hysteresis to prevent swapping the + * tasks within a group over tiny differences. + */ + if (cur->numa_group) + imp -= imp/16; } else { - imp = groupimp + group_weight(cur, env->src_nid) - - group_weight(cur, env->dst_nid); + /* + * Compare the group weights. If a task is all by + * itself (not part of a group), use the task weight + * instead. + */ + if (env->p->numa_group) + imp = groupimp; + else + imp = taskimp; + + if (cur->numa_group) + imp += group_weight(cur, env->src_nid) - + group_weight(cur, env->dst_nid); + else + imp += task_weight(cur, env->src_nid) - + task_weight(cur, env->dst_nid); } } -- 2.7.4