The patch titled
mm: compaction: defer compaction using an exponential backoff when compaction fails
has been added to the -mm tree. Its filename is
mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find
out what to do about this
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: mm: compaction: defer compaction using an exponential backoff when compaction fails
From: Mel Gorman <mel@xxxxxxxxx>
The fragmentation index may indicate that a failure is due to external
fragmentation but after a compaction run completes, it is still possible
for an allocation to fail. There are two obvious reasons as to why
o Page migration cannot move all pages so fragmentation remains
o A suitable page may exist but watermarks are not met
In the event of compaction followed by an allocation failure, this patch
defers further compaction in the zone (1 << compact_defer_shift) times.
If the next compaction attempt also fails, compact_defer_shift is
increased up to a maximum of 6. If compaction succeeds, the defer
counters are reset again.
The zone that is deferred is the first zone in the zonelist - i.e. the
preferred zone. To defer compaction in the other zones, the information
would need to be stored in the zonelist or implemented similar to the
zonelist_cache. This would impact the fast-paths and is not justified at
this time.
Signed-off-by: Mel Gorman <mel@xxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Minchan Kim <minchan.kim@xxxxxxxxx>
Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/compaction.h | 39 +++++++++++++++++++++++++++++++++++
include/linux/mmzone.h | 9 ++++++++
mm/page_alloc.c | 5 +++-
3 files changed, 52 insertions(+), 1 deletion(-)
diff -puN include/linux/compaction.h~mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails include/linux/compaction.h
--- a/include/linux/compaction.h~mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails
+++ a/include/linux/compaction.h
@@ -22,6 +22,36 @@ extern int sysctl_extfrag_handler(struct
extern int fragmentation_index(struct zone *zone, unsigned int order);
extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
int order, gfp_t gfp_mask, nodemask_t *mask);
+
+/* Do not skip compaction more than 64 times */
+#define COMPACT_MAX_DEFER_SHIFT 6
+
+/*
+ * Compaction is deferred when compaction fails to result in a page
+ * allocation success. 1 << compact_defer_limit compactions are skipped up
+ * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
+ */
+static inline void defer_compaction(struct zone *zone)
+{
+ zone->compact_considered = 0;
+ zone->compact_defer_shift++;
+
+ if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
+ zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
+}
+
+/* Returns true if compaction should be skipped this time */
+static inline bool compaction_deferred(struct zone *zone)
+{
+ unsigned long defer_limit = 1UL << zone->compact_defer_shift;
+
+ /* Avoid possible overflow */
+ if (++zone->compact_considered > defer_limit)
+ zone->compact_considered = defer_limit;
+
+ return zone->compact_considered < (1UL << zone->compact_defer_shift);
+}
+
#else
static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
int order, gfp_t gfp_mask, nodemask_t *nodemask)
@@ -29,6 +59,15 @@ static inline unsigned long try_to_compa
return COMPACT_CONTINUE;
}
+static inline void defer_compaction(struct zone *zone)
+{
+}
+
+static inline bool compaction_deferred(struct zone *zone)
+{
+ return 1;
+}
+
#endif /* CONFIG_COMPACTION */
#if defined(CONFIG_COMPACTION) && defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
diff -puN include/linux/mmzone.h~mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails include/linux/mmzone.h
--- a/include/linux/mmzone.h~mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails
+++ a/include/linux/mmzone.h
@@ -321,6 +321,15 @@ struct zone {
unsigned long *pageblock_flags;
#endif /* CONFIG_SPARSEMEM */
+#ifdef CONFIG_COMPACTION
+ /*
+ * On compaction failure, 1<<compact_defer_shift compactions
+ * are skipped before trying again. The number attempted since
+ * last failure is tracked with compact_considered.
+ */
+ unsigned int compact_considered;
+ unsigned int compact_defer_shift;
+#endif
ZONE_PADDING(_pad1_)
diff -puN mm/page_alloc.c~mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails mm/page_alloc.c
--- a/mm/page_alloc.c~mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails
+++ a/mm/page_alloc.c
@@ -1772,7 +1772,7 @@ __alloc_pages_direct_compact(gfp_t gfp_m
{
struct page *page;
- if (!order)
+ if (!order || compaction_deferred(preferred_zone))
return NULL;
*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
@@ -1788,6 +1788,8 @@ __alloc_pages_direct_compact(gfp_t gfp_m
alloc_flags, preferred_zone,
migratetype);
if (page) {
+ preferred_zone->compact_considered = 0;
+ preferred_zone->compact_defer_shift = 0;
__count_vm_event(COMPACTSUCCESS);
return page;
}
@@ -1798,6 +1800,7 @@ __alloc_pages_direct_compact(gfp_t gfp_m
* but not enough to satisfy watermarks.
*/
count_vm_event(COMPACTFAIL);
+ defer_compaction(preferred_zone);
cond_resched();
}
_
Patches currently in -mm which might be from mel@xxxxxxxxx are
linux-next.patch
hugetlb-fix-infinite-loop-in-get_futex_key-when-backed-by-huge-pages.patch
hugetlb-fix-infinite-loop-in-get_futex_key-when-backed-by-huge-pages-fix.patch
hugetlbfs-kill-applications-that-use-map_noreserve-with-sigbus-instead-of-oom-killer.patch
page-allocator-reduce-fragmentation-in-buddy-allocator-by-adding-buddies-that-are-merging-to-the-tail-of-the-free-lists.patch
mempolicy-remove-redundant-code.patch
mm-default-to-node-zonelist-ordering-when-nodes-have-only-lowmem.patch
mmmigration-take-a-reference-to-the-anon_vma-before-migrating.patch
mmmigration-share-the-anon_vma-ref-counts-between-ksm-and-page-migration.patch
mmmigration-do-not-try-to-migrate-unmapped-anonymous-pages.patch
mmmigration-allow-the-migration-of-pageswapcache-pages.patch
mm-allow-config_migration-to-be-set-without-config_numa-or-memory-hot-remove.patch
mm-export-unusable-free-space-index-via-debugfs.patch
mm-export-fragmentation-index-via-debugfs.patch
mm-move-definition-for-lru-isolation-modes-to-a-header.patch
mmcompaction-memory-compaction-core.patch
mmcompaction-add-proc-trigger-for-memory-compaction.patch
mmcompaction-add-sys-trigger-for-per-node-memory-compaction.patch
mmcompaction-direct-compact-when-a-high-order-allocation-fails.patch
mmcompaction-add-a-tunable-that-decides-when-memory-should-be-compacted-and-when-it-should-be-reclaimed.patch
mmcompaction-defer-compaction-using-an-exponential-backoff-when-compaction-fails.patch
mm-introduce-free_pages_prepare.patch
mm-introduce-free_pages_prepare-fix.patch
delay-accounting-re-implement-c-for-getdelaysc-to-report-information-on-a-target-command.patch
delay-accounting-re-implement-c-for-getdelaysc-to-report-information-on-a-target-command-checkpatch-fixes.patch
numa-add-generic-percpu-var-numa_node_id-implementation.patch
numa-x86_64-use-generic-percpu-var-numa_node_id-implementation.patch
numa-ia64-use-generic-percpu-var-numa_node_id-implementation.patch
numa-introduce-numa_mem_id-effective-local-memory-node-id.patch
numa-ia64-support-numa_mem_id-for-memoryless-nodes.patch
numa-slab-use-numa_mem_id-for-slab-local-memory-node.patch
numa-in-kernel-profiling-use-cpu_to_mem-for-per-cpu-allocations.patch
numa-update-documentation-vm-numa-add-memoryless-node-info.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
