Subject: + mm-activate-pagelru-pages-on-mark_page_accessed-if-page-is-on-local-pagevec.patch added to -mm tree To: mgorman@xxxxxxx,Trond.Myklebust@xxxxxxxxxx,alexey.lyashkov@xxxxxxxxx,anserper@xxxxx,bernd.schubert@xxxxxxxxxxx,dhowells@xxxxxxxxxx,hannes@xxxxxxxxxxx,hughd@xxxxxxxxxx,jack@xxxxxxx,riel@xxxxxxxxxx,sanbai@xxxxxxxxxx,tytso@xxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Tue, 28 May 2013 13:06:14 -0700 The patch titled Subject: mm: activate !PageLRU pages on mark_page_accessed if page is on local pagevec has been added to the -mm tree. Its filename is mm-activate-pagelru-pages-on-mark_page_accessed-if-page-is-on-local-pagevec.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: Mel Gorman <mgorman@xxxxxxx> Subject: mm: activate !PageLRU pages on mark_page_accessed if page is on local pagevec If a page is on a pagevec then it is !PageLRU and mark_page_accessed() may fail to move a page to the active list as expected. Now that the LRU is selected at LRU drain time, mark pages PageActive if they are on the local pagevec so it gets moved to the correct list at LRU drain time. Using a debugging patch it was found that for a simple git checkout based workload that pages were never added to the active file list in practice but with this patch applied they are. before after LRU Add Active File 0 750583 LRU Add Active Anon 2640587 2702818 LRU Add Inactive File 8833662 8068353 LRU Add Inactive Anon 207 200 Note that only pages on the local pagevec are considered on purpose. A !PageLRU page could be in the process of being released, reclaimed, migrated or on a remote pagevec that is currently being drained. Marking it PageActive is vunerable to races where PageLRU and Active bits are checked at the wrong time. Page reclaim will trigger VM_BUG_ONs but depending on when the race hits, it could also free a PageActive page to the page allocator and trigger a bad_page warning. Similarly a potential race exists between a per-cpu drain on a pagevec list and an activation on a remote CPU. lru_add_drain_cpu __pagevec_lru_add lru = page_lru(page); mark_page_accessed if (PageLRU(page)) activate_page else SetPageActive SetPageLRU(page); add_page_to_lru_list(page, lruvec, lru); In this case a PageActive page is added to the inactivate list and later the inactive/active stats will get skewed. While the PageActive checks in vmscan could be removed and potentially dealt with, a skew in the statistics would be very difficult to detect. Hence this patch deals just with the common case where a page being marked accessed has just been added to the local pagevec. Signed-off-by: Mel Gorman <mgorman@xxxxxxx> Cc: Jan Kara <jack@xxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: Alexey Lyahkov <alexey.lyashkov@xxxxxxxxx> Cc: Andrew Perepechko <anserper@xxxxx> Cc: Robin Dong <sanbai@xxxxxxxxxx> Cc: Theodore Tso <tytso@xxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Bernd Schubert <bernd.schubert@xxxxxxxxxxx> Cc: David Howells <dhowells@xxxxxxxxxx> Cc: Trond Myklebust <Trond.Myklebust@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/swap.c | 41 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) diff -puN mm/swap.c~mm-activate-pagelru-pages-on-mark_page_accessed-if-page-is-on-local-pagevec mm/swap.c --- a/mm/swap.c~mm-activate-pagelru-pages-on-mark_page_accessed-if-page-is-on-local-pagevec +++ a/mm/swap.c @@ -432,6 +432,33 @@ void activate_page(struct page *page) } #endif +static void __lru_cache_activate_page(struct page *page) +{ + struct pagevec *pvec = &get_cpu_var(lru_add_pvec); + int i; + + /* + * Search backwards on the optimistic assumption that the page being + * activated has just been added to this pagevec. Note that only + * the local pagevec is examined as a !PageLRU page could be in the + * process of being released, reclaimed, migrated or on a remote + * pagevec that is currently being drained. Furthermore, marking + * a remote pagevec's page PageActive potentially hits a race where + * a page is marked PageActive just after it is added to the inactive + * list causing accounting errors and BUG_ON checks to trigger. + */ + for (i = pagevec_count(pvec) - 1; i >= 0; i--) { + struct page *pagevec_page = pvec->pages[i]; + + if (pagevec_page == page) { + SetPageActive(page); + break; + } + } + + put_cpu_var(lru_add_pvec); +} + /* * Mark a page as having seen activity. * @@ -442,8 +469,18 @@ void activate_page(struct page *page) void mark_page_accessed(struct page *page) { if (!PageActive(page) && !PageUnevictable(page) && - PageReferenced(page) && PageLRU(page)) { - activate_page(page); + PageReferenced(page)) { + + /* + * If the page is on the LRU, queue it for activation via + * activate_page_pvecs. Otherwise, assume the page is on a + * pagevec, mark it active and it'll be moved to the active + * LRU on the next drain. + */ + if (PageLRU(page)) + activate_page(page); + else + __lru_cache_activate_page(page); ClearPageReferenced(page); } else if (!PageReferenced(page)) { SetPageReferenced(page); _ Patches currently in -mm which might be from mgorman@xxxxxxx are linux-next.patch mm-page_alloc-factor-out-setting-of-pcp-high-and-pcp-batch.patch mm-page_alloc-prevent-concurrent-updaters-of-pcp-batch-and-high.patch mm-page_alloc-insert-memory-barriers-to-allow-async-update-of-pcp-batch-and-high.patch mm-page_alloc-protect-pcp-batch-accesses-with-access_once.patch mm-page_alloc-convert-zone_pcp_update-to-rely-on-memory-barriers-instead-of-stop_machine.patch mm-page_alloc-when-handling-percpu_pagelist_fraction-dont-unneedly-recalulate-high.patch mm-page_alloc-factor-setup_pageset-into-pageset_init-and-pageset_set_batch.patch mm-page_alloc-relocate-comment-to-be-directly-above-code-it-refers-to.patch mm-page_alloc-factor-zone_pageset_init-out-of-setup_zone_pageset.patch mm-page_alloc-in-zone_pcp_update-uze-zone_pageset_init.patch mm-page_alloc-rename-setup_pagelist_highmark-to-match-naming-of-pageset_set_batch.patch mm-vmscan-limit-the-number-of-pages-kswapd-reclaims-at-each-priority.patch mm-vmscan-obey-proportional-scanning-requirements-for-kswapd.patch mm-vmscan-flatten-kswapd-priority-loop.patch mm-vmscan-decide-whether-to-compact-the-pgdat-based-on-reclaim-progress.patch mm-vmscan-do-not-allow-kswapd-to-scan-at-maximum-priority.patch mm-vmscan-have-kswapd-writeback-pages-based-on-dirty-pages-encountered-not-priority.patch mm-vmscan-block-kswapd-if-it-is-encountering-pages-under-writeback.patch mm-vmscan-block-kswapd-if-it-is-encountering-pages-under-writeback-fix.patch mm-vmscan-check-if-kswapd-should-writepage-once-per-pgdat-scan.patch mm-vmscan-move-logic-from-balance_pgdat-to-kswapd_shrink_zone.patch mm-add-tracepoints-for-lru-activation-and-insertions.patch mm-pagevec-defer-deciding-what-lru-to-add-a-page-to-until-pagevec-drain-time.patch mm-activate-pagelru-pages-on-mark_page_accessed-if-page-is-on-local-pagevec.patch mm-remove-lru-parameter-from-__pagevec_lru_add-and-remove-parts-of-pagevec-api.patch mm-remove-lru-parameter-from-__lru_cache_add-and-lru_cache_add_lru.patch mm-memmap_init_zone-performance-improvement.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