summaryrefslogtreecommitdiffstats
path: root/mm/mempolicy.c
diff options
context:
space:
mode:
authorMel Gorman <mgorman@suse.de>2012-11-12 09:17:07 +0000
committerMel Gorman <mgorman@suse.de>2012-12-11 14:42:54 +0000
commite42c8ff2999de1239a57d434bfbd8e9f2a56e814 (patch)
treefd1975853a79bf28356d86a4822e8cd2111129a8 /mm/mempolicy.c
parentbac0382c6ad764156025978845147e5a6eccca09 (diff)
downloadlinux-e42c8ff2999de1239a57d434bfbd8e9f2a56e814.tar.bz2
mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
Note: This two-stage filter was taken directly from the sched/numa patch "sched, numa, mm: Add the scanning page fault machinery" but is only a partial extraction. As the end result is not necessarily recognisable, the signed-offs-by had to be removed. Will be added back if requested. While it is desirable that all threads in a process run on its home node, this is not always possible or necessary. There may be more threads than exist within the node or the node might over-subscribed with unrelated processes. This can cause a situation whereby a page gets migrated off its home node because the threads clearing pte_numa were running off-node. This patch uses page->last_nid to build a two-stage filter before pages get migrated to avoid problems with short or unlikely task<->node relationships. Signed-off-by: Mel Gorman <mgorman@suse.de>
Diffstat (limited to 'mm/mempolicy.c')
-rw-r--r--mm/mempolicy.c30
1 files changed, 29 insertions, 1 deletions
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4c1c8d83ac6a..fd20e28fd2ad 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2317,9 +2317,37 @@ int mpol_misplaced(struct page *page, struct vm_area_struct *vma, unsigned long
}
/* Migrate the page towards the node whose CPU is referencing it */
- if (pol->flags & MPOL_F_MORON)
+ if (pol->flags & MPOL_F_MORON) {
+ int last_nid;
+
polnid = numa_node_id();
+ /*
+ * Multi-stage node selection is used in conjunction
+ * with a periodic migration fault to build a temporal
+ * task<->page relation. By using a two-stage filter we
+ * remove short/unlikely relations.
+ *
+ * Using P(p) ~ n_p / n_t as per frequentist
+ * probability, we can equate a task's usage of a
+ * particular page (n_p) per total usage of this
+ * page (n_t) (in a given time-span) to a probability.
+ *
+ * Our periodic faults will sample this probability and
+ * getting the same result twice in a row, given these
+ * samples are fully independent, is then given by
+ * P(n)^2, provided our sample period is sufficiently
+ * short compared to the usage pattern.
+ *
+ * This quadric squishes small probabilities, making
+ * it less likely we act on an unlikely task<->page
+ * relation.
+ */
+ last_nid = page_xchg_last_nid(page, polnid);
+ if (last_nid != polnid)
+ goto out;
+ }
+
if (curnid != polnid)
ret = polnid;
out: