From 792568ec6a31ca560ca4d528782cbc6cd2cea8b0 Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Fri, 11 Apr 2014 13:00:27 -0400 Subject: [PATCH] sched/numa: Count pages on active node as local The NUMA code is smart enough to distribute the memory of workloads that span multiple NUMA nodes across those NUMA nodes. However, it still has a pretty high scan rate for such workloads, because any memory that is left on a node other than the node of the CPU that faulted on the memory is counted as non-local, which causes the scan rate to go up. Counting the memory on any node where the task's numa group is actively running as local, allows the scan rate to slow down once the application is settled in. This should reduce the overhead of the automatic NUMA placement code, when a workload spans multiple NUMA nodes. Signed-off-by: Rik van Riel Tested-by: Vinod Chegu Acked-by: Mel Gorman Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1397235629-16328-2-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5d859ec975c2..f6457b63c95c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1738,6 +1738,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) struct task_struct *p = current; bool migrated = flags & TNF_MIGRATED; int cpu_node = task_node(current); + int local = !!(flags & TNF_FAULT_LOCAL); int priv; if (!numabalancing_enabled) @@ -1786,6 +1787,17 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) task_numa_group(p, last_cpupid, flags, &priv); } + /* + * If a workload spans multiple NUMA nodes, a shared fault that + * occurs wholly within the set of nodes that the workload is + * actively using should be counted as local. This allows the + * scan rate to slow down when a workload has settled down. + */ + if (!priv && !local && p->numa_group && + node_isset(cpu_node, p->numa_group->active_nodes) && + node_isset(mem_node, p->numa_group->active_nodes)) + local = 1; + task_numa_placement(p); /* @@ -1800,7 +1812,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages; p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages; - p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages; + p->numa_faults_locality[local] += pages; } static void reset_ptenuma_scan(struct task_struct *p)