summaryrefslogtreecommitdiffstats
path: root/mm/mempolicy.c
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2012-11-02 18:19:13 +0000
committerMel Gorman <mgorman@suse.de>2012-12-11 14:42:48 +0000
commit5606e3877ad8baea42f3a71ebde0a03622bbb551 (patch)
tree4fc481ccb482236ced5fca76ad19729ba083e8da /mm/mempolicy.c
parent03c5a6e16322c997bf8f264851bfa3f532ad515f (diff)
downloadlinux-stable-5606e3877ad8baea42f3a71ebde0a03622bbb551.tar.gz
linux-stable-5606e3877ad8baea42f3a71ebde0a03622bbb551.tar.bz2
linux-stable-5606e3877ad8baea42f3a71ebde0a03622bbb551.zip
mm: numa: Migrate on reference policy
This is the simplest possible policy that still does something of note. When a pte_numa is faulted, it is moved immediately. Any replacement policy must at least do better than this and in all likelihood this policy regresses normal workloads. Signed-off-by: Mel Gorman <mgorman@suse.de> Acked-by: Rik van Riel <riel@redhat.com>
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r--mm/mempolicy.c38
1 files changed, 36 insertions, 2 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 516491fbfaa8..4c1c8d83ac6a 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -118,6 +118,26 @@ static struct mempolicy default_policy = {
.flags = MPOL_F_LOCAL,
};
+static struct mempolicy preferred_node_policy[MAX_NUMNODES];
+
+static struct mempolicy *get_task_policy(struct task_struct *p)
+{
+ struct mempolicy *pol = p->mempolicy;
+ int node;
+
+ if (!pol) {
+ node = numa_node_id();
+ if (node != -1)
+ pol = &preferred_node_policy[node];
+
+ /* preferred_node_policy is not initialised early in boot */
+ if (!pol->mode)
+ pol = NULL;
+ }
+
+ return pol;
+}
+
static const struct mempolicy_operations {
int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
/*
@@ -1598,7 +1618,7 @@ asmlinkage long compat_sys_mbind(compat_ulong_t start, compat_ulong_t len,
struct mempolicy *get_vma_policy(struct task_struct *task,
struct vm_area_struct *vma, unsigned long addr)
{
- struct mempolicy *pol = task->mempolicy;
+ struct mempolicy *pol = get_task_policy(task);
if (vma) {
if (vma->vm_ops && vma->vm_ops->get_policy) {
@@ -2021,7 +2041,7 @@ retry_cpuset:
*/
struct page *alloc_pages_current(gfp_t gfp, unsigned order)
{
- struct mempolicy *pol = current->mempolicy;
+ struct mempolicy *pol = get_task_policy(current);
struct page *page;
unsigned int cpuset_mems_cookie;
@@ -2295,6 +2315,11 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
default:
BUG();
}
+
+ /* Migrate the page towards the node whose CPU is referencing it */
+ if (pol->flags & MPOL_F_MORON)
+ polnid = numa_node_id();
+
if (curnid != polnid)
ret = polnid;
out:
@@ -2483,6 +2508,15 @@ void __init numa_policy_init(void)
sizeof(struct sp_node),
0, SLAB_PANIC, NULL);
+ for_each_node(nid) {
+ preferred_node_policy[nid] = (struct mempolicy) {
+ .refcnt = ATOMIC_INIT(1),
+ .mode = MPOL_PREFERRED,
+ .flags = MPOL_F_MOF | MPOL_F_MORON,
+ .v = { .preferred_node = nid, },
+ };
+ }
+
/*
* Set interleaving policy for system init. Interleaving is only
* enabled across suitably sized nodes (default is >= 16MB), or