Subject: + mm-compaction-avoid-isolating-pinned-pages.patch added to -mm tree To: rientjes@xxxxxxxxxx,gthelen@xxxxxxxxxx,hughd@xxxxxxxxxx,iamjoonsoo.kim@xxxxxxx,mgorman@xxxxxxx,riel@xxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Thu, 06 Feb 2014 13:37:45 -0800 The patch titled Subject: mm, compaction: avoid isolating pinned pages has been added to the -mm tree. Its filename is mm-compaction-avoid-isolating-pinned-pages.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/mm-compaction-avoid-isolating-pinned-pages.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/mm-compaction-avoid-isolating-pinned-pages.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 *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ 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_pages_moved 8450 compact_pagemigrate_failed 15614415 0.05% of pages isolated are successfully migrated and explicitly triggering memory compaction takes 102 seconds. After the patch: compact_pages_moved 9197 compact_pagemigrate_failed 7 99.9% of pages isolated are now successfully migrated in this configuration and memory compaction takes less than one second. Signed-off-by: David Rientjes <rientjes@xxxxxxxxxx> Acked-by: Hugh Dickins <hughd@xxxxxxxxxx> Acked-by: Mel Gorman <mgorman@xxxxxxx> Cc: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Greg Thelen <gthelen@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/compaction.c | 9 +++++++++ 1 file changed, 9 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 +578,15 @@ isolate_migratepages_range(struct zone * continue; } + /* + * Migration will fail if an anonymous page is pinned in memory, + * so avoid taking lru_lock and isolating it unnecessarily in an + * admittedly racy check. + */ + if (!page_mapping(page) && + page_count(page) > page_mapcount(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 numa-mem-hotplug-initialize-numa_kernel_nodes-in-numa_clear_kernel_node_hotplug.patch numa-mem-hotplug-fix-array-index-overflow-when-synchronizing-nid-to-memblockreserved.patch mm-__set_page_dirty-uses-spin_lock_irqsave-instead-of-spin_lock_irq.patch mm-slub-list_lock-may-not-be-held-in-some-circumstances.patch fs-filec-fdtable-avoid-triggering-ooms-from-alloc_fdmem.patch mm-page_alloc-make-first_page-visible-before-pagetail.patch kthread-ensure-locality-of-task_struct-allocations.patch mm-slab-slub-use-page-list-consistently-instead-of-page-lru.patch mm-compaction-ignore-pageblock-skip-when-manually-invoking-compaction.patch mm-vmscan-shrink_slab-rename-max_pass-freeable.patch mm-hugetlb-mark-some-bootstrap-functions-as-__init.patch mm-compaction-avoid-isolating-pinned-pages.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