The patch titled
Apply memory policies to top two highest zones when highest zone is ZONE_MOVABLE
has been added to the -mm tree. Its filename is
apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: Apply memory policies to top two highest zones when highest zone is ZONE_MOVABLE
From: Mel Gorman <mel@xxxxxxxxx>
The NUMA layer only supports NUMA policies for the highest zone. When
ZONE_MOVABLE is configured with kernelcore=, the the highest zone becomes
ZONE_MOVABLE. The result is that policies are only applied to allocations
like anonymous pages and page cache allocated from ZONE_MOVABLE when the
zone is used.
This patch applies policies to the two highest zones when the highest zone
is ZONE_MOVABLE. As ZONE_MOVABLE consists of pages from the highest "real"
zone, it's always functionally equivalent.
The patch has been tested on a variety of machines both NUMA and non-NUMA
covering x86, x86_64 and ppc64. No abnormal results were seen in
kernbench, tbench, dbench or hackbench. It passes regression tests from
the numactl package with and without kernelcore= once numactl tests are
patched to wait for vmstat counters to update.
akpm: this is a nasty hack to fix NUMA mempolicies in the presence of
ZONE_MOVABLE in 2.6.23. Christoph says "For .24 either merge the mobility or
get the other solution that Mel is working on. That solution would only use a
single zonelist per node and filter on the fly. That may help performance and
also help to make memory policies work better."
Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
Acked-by: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
Tested-by: Lee Schermerhorn <lee.schermerhorn@xxxxxx>
Acked-by: Christoph Lameter <clameter@xxxxxxx>
Cc: Andi Kleen <ak@xxxxxxx>
Cc: Paul Mundt <lethal@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/mempolicy.h | 2 +-
include/linux/mmzone.h | 18 ++++++++++++++++++
mm/mempolicy.c | 2 +-
mm/page_alloc.c | 13 +++++++++++++
4 files changed, 33 insertions(+), 2 deletions(-)
diff -puN include/linux/mempolicy.h~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable include/linux/mempolicy.h
--- a/include/linux/mempolicy.h~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable
+++ a/include/linux/mempolicy.h
@@ -166,7 +166,7 @@ extern enum zone_type policy_zone;
static inline void check_highest_zone(enum zone_type k)
{
- if (k > policy_zone)
+ if (k > policy_zone && k != ZONE_MOVABLE)
policy_zone = k;
}
diff -puN include/linux/mmzone.h~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable include/linux/mmzone.h
--- a/include/linux/mmzone.h~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable
+++ a/include/linux/mmzone.h
@@ -410,6 +410,24 @@ struct zonelist {
#endif
};
+#ifdef CONFIG_NUMA
+/*
+ * Only custom zonelists like MPOL_BIND need to be filtered as part of
+ * policies. As described in the comment for struct zonelist_cache, these
+ * zonelists will not have a zlcache so zlcache_ptr will not be set. Use
+ * that to determine if the zonelists needs to be filtered or not.
+ */
+static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
+{
+ return !zonelist->zlcache_ptr;
+}
+#else
+static inline int alloc_should_filter_zonelist(struct zonelist *zonelist)
+{
+ return 0;
+}
+#endif /* CONFIG_NUMA */
+
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
struct node_active_region {
unsigned long start_pfn;
diff -puN mm/mempolicy.c~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable mm/mempolicy.c
--- a/mm/mempolicy.c~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable
+++ a/mm/mempolicy.c
@@ -149,7 +149,7 @@ static struct zonelist *bind_zonelist(no
lower zones etc. Avoid empty zones because the memory allocator
doesn't like them. If you implement node hot removal you
have to fix that. */
- k = policy_zone;
+ k = MAX_NR_ZONES - 1;
while (1) {
for_each_node_mask(nd, *nodes) {
struct zone *z = &NODE_DATA(nd)->node_zones[k];
diff -puN mm/page_alloc.c~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable mm/page_alloc.c
--- a/mm/page_alloc.c~apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable
+++ a/mm/page_alloc.c
@@ -1157,6 +1157,7 @@ get_page_from_freelist(gfp_t gfp_mask, u
nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */
int zlc_active = 0; /* set if using zonelist_cache */
int did_zlc_setup = 0; /* just call zlc_setup() one time */
+ enum zone_type highest_zoneidx = -1; /* Gets set for policy zonelists */
zonelist_scan:
/*
@@ -1166,6 +1167,18 @@ zonelist_scan:
z = zonelist->zones;
do {
+ /*
+ * In NUMA, this could be a policy zonelist which contains
+ * zones that may not be allowed by the current gfp_mask.
+ * Check the zone is allowed by the current flags
+ */
+ if (unlikely(alloc_should_filter_zonelist(zonelist))) {
+ if (highest_zoneidx == -1)
+ highest_zoneidx = gfp_zone(gfp_mask);
+ if (zone_idx(*z) > highest_zoneidx)
+ continue;
+ }
+
if (NUMA_BUILD && zlc_active &&
!zlc_zone_worth_trying(zonelist, z, allowednodes))
continue;
_
Patches currently in -mm which might be from mel@xxxxxxxxx are
fix-missing-numa_zonelist_order-sysctl.patch
apply-memory-policies-to-top-two-highest-zones-when-highest-zone-is-zone_movable.patch
sparsemem-clean-up-spelling-error-in-comments.patch
sparsemem-record-when-a-section-has-a-valid-mem_map.patch
generic-virtual-memmap-support-for-sparsemem.patch
generic-virtual-memmap-support-for-sparsemem-remove-excess-debugging.patch
x86_64-sparsemem_vmemmap-2m-page-size-support.patch
x86_64-sparsemem_vmemmap-2m-page-size-support-ensure-end-of-section-memmap-is-initialised.patch
ia64-sparsemem_vmemmap-16k-page-size-support.patch
sparc64-sparsemem_vmemmap-support.patch
ppc64-sparsemem_vmemmap-support.patch
ensure-we-count-pages-transitioning-inactive-via-clear_active_flags.patch
wait-for-page-writeback-when-directly-reclaiming-contiguous-areas.patch
add-a-bitmap-that-is-used-to-track-flags-affecting-a-block-of-pages.patch
split-the-free-lists-for-movable-and-unmovable-allocations.patch
choose-pages-from-the-per-cpu-list-based-on-migration-type.patch
add-a-configure-option-to-group-pages-by-mobility.patch
drain-per-cpu-lists-when-high-order-allocations-fail.patch
move-free-pages-between-lists-on-steal.patch
group-short-lived-and-reclaimable-kernel-allocations.patch
group-high-order-atomic-allocations.patch
do-not-group-pages-by-mobility-type-on-low-memory-systems.patch
bias-the-placement-of-kernel-pages-at-lower-pfns.patch
be-more-agressive-about-stealing-when-migrate_reclaimable-allocations-fallback.patch
fix-corruption-of-memmap-on-ia64-sparsemem-when-mem_section-is-not-a-power-of-2.patch
fix-corruption-of-memmap-on-ia64-sparsemem-when-mem_section-is-not-a-power-of-2-fix.patch
fix-corruption-of-memmap-on-ia64-sparsemem-when-mem_section-is-not-a-power-of-2-fix-fix.patch
bias-the-location-of-pages-freed-for-min_free_kbytes-in-the-same-max_order_nr_pages-blocks.patch
remove-page_group_by_mobility.patch
dont-group-high-order-atomic-allocations.patch
fix-calculation-in-move_freepages_block-for-counting-pages.patch
breakout-page_order-to-internalh-to-avoid-special-knowledge-of-the-buddy-allocator.patch
do-not-depend-on-max_order-when-grouping-pages-by-mobility.patch
print-out-statistics-in-relation-to-fragmentation-avoidance-to-proc-pagetypeinfo.patch
have-kswapd-keep-a-minimum-order-free-other-than-order-0.patch
only-check-absolute-watermarks-for-alloc_high-and-alloc_harder-allocations.patch
slub-slab-validation-move-tracking-information-alloc-outside-of-melstuff.patch
ext2-reservations.patch
add-__gfp_movable-for-callers-to-flag-allocations-from-high-memory-that-may-be-migrated-swap-prefetch.patch
rename-gfp_high_movable-to-gfp_highuser_movable-prefetch.patch
page-owner-tracking-leak-detector.patch
add-debugging-aid-for-memory-initialisation-problems.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
