Subject: [to-be-updated] mm-compaction-avoid-isolating-pinned-pages.patch removed from -mm tree
To: rientjes@xxxxxxxxxx,mgorman@xxxxxxx,riel@xxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx
From: akpm@xxxxxxxxxxxxxxxxxxxx
Date: Tue, 04 Feb 2014 12:14:35 -0800
The patch titled
Subject: mm, compaction: avoid isolating pinned pages
has been removed from the -mm tree. Its filename was
mm-compaction-avoid-isolating-pinned-pages.patch
This patch was dropped because an updated version will be merged
------------------------------------------------------
From: David Rientjes <rientjes@xxxxxxxxxx>
Subject: mm, compaction: avoid isolating pinned pages
Page migration will fail for memory that is pinned in memory with, for
example, get_user_pages(). In this case, it is unnecessary to take
zone->lru_lock or isolating the page and passing it to page migration
which will ultimately fail.
This is a racy check, the page can still change from under us, but in that
case we'll just fail later when attempting to move the page.
This avoids very expensive memory compaction when faulting transparent
hugepages after pinning a lot of memory with a Mellanox driver.
On a 128GB machine and pinning ~120GB of memory, before this patch we
see the enormous disparity in the number of page migration failures
because of the pinning (from /proc/vmstat):
compact_blocks_moved 7609
compact_pages_moved 3431
compact_pagemigrate_failed 133219
compact_stall 13
After the patch, it is much more efficient:
compact_blocks_moved 7998
compact_pages_moved 6403
compact_pagemigrate_failed 3
compact_stall 15
Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/compaction.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff -puN mm/compaction.c~mm-compaction-avoid-isolating-pinned-pages mm/compaction.c
--- a/mm/compaction.c~mm-compaction-avoid-isolating-pinned-pages
+++ a/mm/compaction.c
@@ -578,6 +578,14 @@ isolate_migratepages_range(struct zone *
continue;
}
+ /*
+ * Migration will fail if an anonymous page is pinned in memory,
+ * so avoid taking zone->lru_lock and isolating it unnecessarily
+ * in an admittedly racy check.
+ */
+ if (!page_mapping(page) && page_count(page))
+ continue;
+
/* Check if it is ok to still hold the lock */
locked = compact_checklock_irqsave(&zone->lru_lock, &flags,
locked, cc);
_
Patches currently in -mm which might be from rientjes@xxxxxxxxxx are
documentation-kernel-parameterstxt-fix-memmap=-language.patch
mm-__set_page_dirty_nobuffers-uses-spin_lock_irqseve-instead-of-spin_lock_irq.patch
mm-slub-list_lock-may-not-be-held-in-some-circumstances.patch
numa-mem-hotplug-initialize-numa_kernel_nodes-in-numa_clear_kernel_node_hotplug.patch
numa-mem-hotplug-initialize-numa_kernel_nodes-in-numa_clear_kernel_node_hotplug-fix.patch
numa-mem-hotplug-fix-array-index-overflow-when-synchronizing-nid-to-memblockreserved.patch
kthread-ensure-locality-of-task_struct-allocations.patch
mm-compaction-ignore-pageblock-skip-when-manually-invoking-compaction.patch
mm-vmscan-shrink_slab-rename-max_pass-freeable.patch
mm-utilc-add-kstrimdup.patch
cpusets-allocate-heap-only-when-required.patch
linux-next.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
