From 10f39042711ba21773763f267b4943a2c66c8bef Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Mon, 27 Jan 2014 17:03:44 -0500 Subject: sched/numa, mm: Use active_nodes nodemask to limit numa migrations Use the active_nodes nodemask to make smarter decisions on NUMA migrations. In order to maximize performance of workloads that do not fit in one NUMA node, we want to satisfy the following criteria: 1) keep private memory local to each thread 2) avoid excessive NUMA migration of pages 3) distribute shared memory across the active nodes, to maximize memory bandwidth available to the workload This patch accomplishes that by implementing the following policy for NUMA migrations: 1) always migrate on a private fault 2) never migrate to a node that is not in the set of active nodes for the numa_group 3) always migrate from a node outside of the set of active nodes, to a node that is in that set 4) within the set of active nodes in the numa_group, only migrate from a node with more NUMA page faults, to a node with fewer NUMA page faults, with a 25% margin to avoid ping-ponging This results in most pages of a workload ending up on the actively used nodes, with reduced ping-ponging of pages between those nodes. Signed-off-by: Rik van Riel Acked-by: Mel Gorman Signed-off-by: Peter Zijlstra Cc: Chegu Vinod Link: http://lkml.kernel.org/r/1390860228-21539-6-git-send-email-riel@redhat.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 5fb0cfb43ecf..5ab3b89fc33e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1589,6 +1589,8 @@ extern void task_numa_fault(int last_node, int node, int pages, int flags); extern pid_t task_numa_group_id(struct task_struct *p); extern void set_numabalancing_state(bool enabled); extern void task_numa_free(struct task_struct *p); +extern bool should_numa_migrate_memory(struct task_struct *p, struct page *page, + int src_nid, int dst_cpu); #else static inline void task_numa_fault(int last_node, int node, int pages, int flags) @@ -1604,6 +1606,11 @@ static inline void set_numabalancing_state(bool enabled) static inline void task_numa_free(struct task_struct *p) { } +static inline bool should_numa_migrate_memory(struct task_struct *p, + struct page *page, int src_nid, int dst_cpu) +{ + return true; +} #endif static inline struct pid *task_pid(struct task_struct *task) -- cgit v1.2.3