The patch titled Subject: mm: page allocator: do not call direct reclaim for THP allocations while compaction is deferred has been added to the -mm tree. Its filename is mm-page-allocator-do-not-call-direct-reclaim-for-thp-allocations-while-compaction-is-deferred.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/ ------------------------------------------------------ From: Mel Gorman <mgorman@xxxxxxx> Subject: mm: page allocator: do not call direct reclaim for THP allocations while compaction is deferred If compaction is deferred, direct reclaim is used to try to free enough pages for the allocation to succeed. For small high-orders, this has a reasonable chance of success. However, if the caller has specified __GFP_NO_KSWAPD to limit the disruption to the system, it makes more sense to fail the allocation rather than stall the caller in direct reclaim. This patch skips direct reclaim if compaction is deferred and the caller specifies __GFP_NO_KSWAPD. Async compaction only considers a subset of pages so it is possible for compaction to be deferred prematurely and not enter direct reclaim even in cases where it should. To compensate for this, this patch also defers compaction only if sync compaction failed. Signed-off-by: Mel Gorman <mgorman@xxxxxxx> Acked-by: Minchan Kim <minchan.kim@xxxxxxxxx> Reviewed-by: Rik van Riel<riel@xxxxxxxxxx> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx> Cc: Dave Jones <davej@xxxxxxxxxx> Cc: Jan Kara <jack@xxxxxxx> Cc: Andy Isaacson <adi@xxxxxxxxxxxxx> Cc: Nai Xia <nai.xia@xxxxxxxxx> Cc: Johannes Weiner <jweiner@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 45 +++++++++++++++++++++++++++++++++++---------- 1 file changed, 35 insertions(+), 10 deletions(-) diff -puN mm/page_alloc.c~mm-page-allocator-do-not-call-direct-reclaim-for-thp-allocations-while-compaction-is-deferred mm/page_alloc.c --- a/mm/page_alloc.c~mm-page-allocator-do-not-call-direct-reclaim-for-thp-allocations-while-compaction-is-deferred +++ a/mm/page_alloc.c @@ -2003,14 +2003,20 @@ static struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress, - bool sync_migration) + int migratetype, bool sync_migration, + bool *deferred_compaction, + unsigned long *did_some_progress) { struct page *page; - if (!order || compaction_deferred(preferred_zone)) + if (!order) return NULL; + if (compaction_deferred(preferred_zone)) { + *deferred_compaction = true; + return NULL; + } + current->flags |= PF_MEMALLOC; *did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask, nodemask, sync_migration); @@ -2038,7 +2044,13 @@ __alloc_pages_direct_compact(gfp_t gfp_m * but not enough to satisfy watermarks. */ count_vm_event(COMPACTFAIL); - defer_compaction(preferred_zone); + + /* + * As async compaction considers a subset of pageblocks, only + * defer if the failure was a sync compaction failure. + */ + if (sync_migration) + defer_compaction(preferred_zone); cond_resched(); } @@ -2050,8 +2062,9 @@ static inline struct page * __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, - int migratetype, unsigned long *did_some_progress, - bool sync_migration) + int migratetype, bool sync_migration, + bool *deferred_compaction, + unsigned long *did_some_progress) { return NULL; } @@ -2201,6 +2214,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, u unsigned long pages_reclaimed = 0; unsigned long did_some_progress; bool sync_migration = false; + bool deferred_compaction = false; /* * In the slowpath, we sanity check order to avoid ever trying to @@ -2281,12 +2295,22 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress, - sync_migration); + migratetype, sync_migration, + &deferred_compaction, + &did_some_progress); if (page) goto got_pg; sync_migration = true; + /* + * If compaction is deferred for high-order allocations, it is because + * sync compaction recently failed. In this is the case and the caller + * has requested the system not be heavily disrupted, fail the + * allocation now instead of entering direct reclaim + */ + if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD)) + goto nopage; + /* Try direct reclaim and then allocating */ page = __alloc_pages_direct_reclaim(gfp_mask, order, zonelist, high_zoneidx, @@ -2350,8 +2374,9 @@ rebalance: zonelist, high_zoneidx, nodemask, alloc_flags, preferred_zone, - migratetype, &did_some_progress, - sync_migration); + migratetype, sync_migration, + &deferred_compaction, + &did_some_progress); if (page) goto got_pg; } _ Subject: Subject: mm: page allocator: do not call direct reclaim for THP allocations while compaction is deferred Patches currently in -mm which might be from mgorman@xxxxxxx are linux-next.patch mm-page-writebackc-make-determine_dirtyable_memory-static-again.patch mm-reduce-the-amount-of-work-done-when-updating-min_free_kbytes.patch mm-reduce-the-amount-of-work-done-when-updating-min_free_kbytes-checkpatch-fixes.patch mm-avoid-livelock-on-__gfp_fs-allocations-v2.patch mm-more-intensive-memory-corruption-debug.patch mm-more-intensive-memory-corruption-debug-fix.patch pm-hibernate-do-not-count-debug-pages-as-savable.patch slub-min-order-when-debug_guardpage_minorder-0.patch mm-debug-test-for-online-nid-when-allocating-on-single-node.patch mm-exclude-reserved-pages-from-dirtyable-memory.patch mm-exclude-reserved-pages-from-dirtyable-memory-fix.patch mm-try-to-distribute-dirty-pages-fairly-across-zones.patch mm-filemap-pass-__gfp_write-from-grab_cache_page_write_begin.patch btrfs-pass-__gfp_write-for-buffered-write-page-allocations.patch mm-compaction-push-isolate-search-base-of-compact-control-one-pfn-ahead.patch mm-fix-off-by-two-in-__zone_watermark_ok.patch mremap-enforce-rmap-src-dst-vma-ordering-in-case-of-vma_merge-succeeding-in-copy_vma.patch mremap-enforce-rmap-src-dst-vma-ordering-in-case-of-vma_merge-succeeding-in-copy_vma-update.patch mm-do-not-stall-in-synchronous-compaction-for-thp-allocations.patch revert-mm-do-not-stall-in-synchronous-compaction-for-thp-allocations.patch mm-compaction-allow-compaction-to-isolate-dirty-pages.patch mm-compaction-use-synchronous-compaction-for-proc-sys-vm-compact_memory.patch mm-vmscan-check-if-we-isolated-a-compound-page-during-lumpy-scan.patch mm-vmscan-do-not-oom-if-aborting-reclaim-to-start-compaction.patch mm-compaction-determine-if-dirty-pages-can-be-migrated-without-blocking-within-migratepage.patch mm-compaction-make-isolate_lru_page-filter-aware-again.patch mm-page-allocator-do-not-call-direct-reclaim-for-thp-allocations-while-compaction-is-deferred.patch mm-compaction-introduce-sync-light-migration-for-use-by-compaction.patch mm-vmscan-when-reclaiming-for-compaction-ensure-there-are-sufficient-free-pages-available.patch mm-vmscan-check-if-reclaim-should-really-abort-even-if-compaction_ready-is-true-for-one-zone.patch mm-isolate-pages-for-immediate-reclaim-on-their-own-lru.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