The patch titled thp: use compaction in kswapd for GFP_ATOMIC order > 0 has been added to the -mm tree. Its filename is thp-use-compaction-in-kswapd-for-gfp_atomic-order-0.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: thp: use compaction in kswapd for GFP_ATOMIC order > 0 From: Andrea Arcangeli <aarcange@xxxxxxxxxx> This takes advantage of memory compaction to properly generate pages of order > 0 if regular page reclaim fails and priority level becomes more severe and we don't reach the proper watermarks. Signed-off-by: Andrea Arcangeli <aarcange@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- include/linux/compaction.h | 11 ++++++++--- mm/compaction.c | 31 ++++++++++++++++++++++++++----- mm/vmscan.c | 30 ++++++++++++++++++++---------- 3 files changed, 54 insertions(+), 18 deletions(-) diff -puN include/linux/compaction.h~thp-use-compaction-in-kswapd-for-gfp_atomic-order-0 include/linux/compaction.h --- a/include/linux/compaction.h~thp-use-compaction-in-kswapd-for-gfp_atomic-order-0 +++ a/include/linux/compaction.h @@ -11,6 +11,9 @@ /* The full zone was compacted */ #define COMPACT_COMPLETE 3 +#define COMPACT_MODE_DIRECT_RECLAIM 0 +#define COMPACT_MODE_KSWAPD 1 + #ifdef CONFIG_COMPACTION extern int sysctl_compact_memory; extern int sysctl_compaction_handler(struct ctl_table *table, int write, @@ -25,7 +28,8 @@ extern unsigned long try_to_compact_page bool sync); extern unsigned long compaction_suitable(struct zone *zone, int order); extern unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask, bool sync); + gfp_t gfp_mask, bool sync, + int compact_mode); /* Do not skip compaction more than 64 times */ #define COMPACT_MAX_DEFER_SHIFT 6 @@ -70,9 +74,10 @@ static inline unsigned long compaction_s } static inline unsigned long compact_zone_order(struct zone *zone, int order, - gfp_t gfp_mask, bool sync) + gfp_t gfp_mask, bool sync, + int compact_mode) { - return 0; + return COMPACT_CONTINUE; } static inline void defer_compaction(struct zone *zone) diff -puN mm/compaction.c~thp-use-compaction-in-kswapd-for-gfp_atomic-order-0 mm/compaction.c --- a/mm/compaction.c~thp-use-compaction-in-kswapd-for-gfp_atomic-order-0 +++ a/mm/compaction.c @@ -42,6 +42,8 @@ struct compact_control { unsigned int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; + + int compact_mode; }; static unsigned long release_freepages(struct list_head *freelist) @@ -382,10 +384,10 @@ static void update_nr_listpages(struct c } static int compact_finished(struct zone *zone, - struct compact_control *cc) + struct compact_control *cc) { unsigned int order; - unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order); + unsigned long watermark; if (fatal_signal_pending(current)) return COMPACT_PARTIAL; @@ -395,12 +397,27 @@ static int compact_finished(struct zone return COMPACT_COMPLETE; /* Compaction run is not finished if the watermark is not met */ + if (cc->compact_mode != COMPACT_MODE_KSWAPD) + watermark = low_wmark_pages(zone); + else + watermark = high_wmark_pages(zone); + watermark += (1 << cc->order); + if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0)) return COMPACT_CONTINUE; if (cc->order == -1) return COMPACT_CONTINUE; + /* + * Generating only one page of the right order is not enough + * for kswapd, we must continue until we're above the high + * watermark as a pool for high order GFP_ATOMIC allocations + * too. + */ + if (cc->compact_mode == COMPACT_MODE_KSWAPD) + return COMPACT_CONTINUE; + /* Direct compactor: Is a suitable page free? */ for (order = cc->order; order < MAX_ORDER; order++) { /* Job done if page is free of the right migratetype */ @@ -514,8 +531,9 @@ static int compact_zone(struct zone *zon } unsigned long compact_zone_order(struct zone *zone, - int order, gfp_t gfp_mask, - bool sync) + int order, gfp_t gfp_mask, + bool sync, + int compact_mode) { struct compact_control cc = { .nr_freepages = 0, @@ -524,6 +542,7 @@ unsigned long compact_zone_order(struct .migratetype = allocflags_to_migratetype(gfp_mask), .zone = zone, .sync = sync, + .compact_mode = compact_mode, }; INIT_LIST_HEAD(&cc.freepages); INIT_LIST_HEAD(&cc.migratepages); @@ -569,7 +588,8 @@ unsigned long try_to_compact_pages(struc nodemask) { int status; - status = compact_zone_order(zone, order, gfp_mask, sync); + status = compact_zone_order(zone, order, gfp_mask, sync, + COMPACT_MODE_DIRECT_RECLAIM); rc = max(status, rc); /* If a normal allocation would succeed, stop compacting */ @@ -600,6 +620,7 @@ static int compact_node(int nid) .nr_freepages = 0, .nr_migratepages = 0, .order = -1, + .compact_mode = COMPACT_MODE_DIRECT_RECLAIM, }; zone = &pgdat->node_zones[zoneid]; diff -puN mm/vmscan.c~thp-use-compaction-in-kswapd-for-gfp_atomic-order-0 mm/vmscan.c --- a/mm/vmscan.c~thp-use-compaction-in-kswapd-for-gfp_atomic-order-0 +++ a/mm/vmscan.c @@ -41,6 +41,7 @@ #include <linux/memcontrol.h> #include <linux/delayacct.h> #include <linux/sysctl.h> +#include <linux/compaction.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -2382,6 +2383,7 @@ loop_again: * cause too much scanning of the lower zones. */ for (i = 0; i <= end_zone; i++) { + int compaction; struct zone *zone = pgdat->node_zones + i; int nr_slab; @@ -2411,9 +2413,26 @@ loop_again: lru_pages); sc.nr_reclaimed += reclaim_state->reclaimed_slab; total_scanned += sc.nr_scanned; + + compaction = 0; + if (order && + zone_watermark_ok(zone, 0, + high_wmark_pages(zone), + end_zone, 0) && + !zone_watermark_ok(zone, order, + high_wmark_pages(zone), + end_zone, 0)) { + compact_zone_order(zone, + order, + sc.gfp_mask, false, + COMPACT_MODE_KSWAPD); + compaction = 1; + } + if (zone->all_unreclaimable) continue; - if (nr_slab == 0 && !zone_reclaimable(zone)) + if (!compaction && nr_slab == 0 && + !zone_reclaimable(zone)) zone->all_unreclaimable = 1; /* * If we've done a decent amount of scanning and @@ -2424,15 +2443,6 @@ loop_again: total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2) sc.may_writepage = 1; - /* - * Compact the zone for higher orders to reduce - * latencies for higher-order allocations that - * would ordinarily call try_to_compact_pages() - */ - if (sc.order > PAGE_ALLOC_COSTLY_ORDER) - compact_zone_order(zone, sc.order, sc.gfp_mask, - false); - if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), end_zone, 0)) { all_zones_ok = 0; _ Patches currently in -mm which might be from aarcange@xxxxxxxxxx are mm-compaction-add-trace-events-for-memory-compaction-activity.patch mm-vmscan-convert-lumpy_mode-into-a-bitmask.patch mm-vmscan-reclaim-order-0-and-use-compaction-instead-of-lumpy-reclaim.patch mm-vmscan-reclaim-order-0-and-use-compaction-instead-of-lumpy-reclaim-fix.patch mm-migration-allow-migration-to-operate-asynchronously-and-avoid-synchronous-compaction-in-the-faster-path.patch mm-migration-allow-migration-to-operate-asynchronously-and-avoid-synchronous-compaction-in-the-faster-path-fix.patch mm-migration-cleanup-migrate_pages-api-by-matching-types-for-offlining-and-sync.patch mm-compaction-perform-a-faster-migration-scan-when-migrating-asynchronously.patch mm-vmscan-rename-lumpy_mode-to-reclaim_mode.patch mm-vmscan-rename-lumpy_mode-to-reclaim_mode-fix.patch thp-ksm-free-swap-when-swapcache-page-is-replaced.patch thp-fix-bad_page-to-show-the-real-reason-the-page-is-bad.patch thp-transparent-hugepage-support-documentation.patch thp-mm-define-madv_hugepage.patch thp-compound_lock.patch thp-alter-compound-get_page-put_page.patch thp-put_page-recheck-pagehead-after-releasing-the-compound_lock.patch thp-update-futex-compound-knowledge.patch thp-clear-compound-mapping.patch thp-add-native_set_pmd_at.patch thp-add-pmd-paravirt-ops.patch thp-no-paravirt-version-of-pmd-ops.patch thp-export-maybe_mkwrite.patch thp-comment-reminder-in-destroy_compound_page.patch thp-config_transparent_hugepage.patch thp-special-pmd_trans_-functions.patch thp-add-pmd-mangling-generic-functions.patch thp-add-pmd-mangling-functions-to-x86.patch thp-bail-out-gup_fast-on-splitting-pmd.patch thp-pte-alloc-trans-splitting.patch thp-add-pmd-mmu_notifier-helpers.patch thp-clear-page-compound.patch thp-add-pmd_huge_pte-to-mm_struct.patch thp-split_huge_page_mm-vma.patch thp-split_huge_page-paging.patch thp-clear_copy_huge_page.patch thp-_gfp_no_kswapd.patch thp-dont-alloc-harder-for-gfp-nomemalloc-even-if-nowait.patch thp-transparent-hugepage-core.patch thp-split_huge_page-anon_vma-ordering-dependency.patch thp-verify-pmd_trans_huge-isnt-leaking.patch thp-madvisemadv_hugepage.patch thp-add-pagetranscompound.patch thp-pmd_trans_huge-migrate-bugcheck.patch thp-memcg-compound.patch thp-transhuge-memcg-commit-tail-pages-at-charge.patch thp-memcg-huge-memory.patch thp-transparent-hugepage-vmstat.patch thp-khugepaged.patch thp-khugepaged-vma-merge.patch thp-skip-transhuge-pages-in-ksm-for-now.patch thp-remove-pg_buddy.patch thp-add-x86-32bit-support.patch thp-mincore-transparent-hugepage-support.patch thp-add-pmd_modify.patch thp-mprotect-pass-vma-down-to-page-table-walkers.patch thp-mprotect-transparent-huge-page-support.patch thp-set-recommended-min-free-kbytes.patch thp-enable-direct-defrag.patch thp-add-numa-awareness-to-hugepage-allocations.patch thp-allocate-memory-in-khugepaged-outside-of-mmap_sem-write-mode.patch thp-transparent-hugepage-config-choice.patch thp-select-config_compaction-if-transparent_hugepage-enabled.patch thp-transhuge-isolate_migratepages.patch thp-avoid-breaking-huge-pmd-invariants-in-case-of-vma_adjust-failures.patch thp-dont-allow-transparent-hugepage-support-without-pse.patch thp-mmu_notifier_test_young.patch thp-freeze-khugepaged-and-ksmd.patch thp-use-compaction-in-kswapd-for-gfp_atomic-order-0.patch thp-use-compaction-for-all-allocation-orders.patch thp-disable-transparent-hugepages-by-default-on-small-systems.patch thp-fix-anon-memory-statistics-with-transparent-hugepages.patch thp-scale-nr_rotated-to-balance-memory-pressure.patch thp-transparent-hugepage-sysfs-meminfo.patch thp-add-debug-checks-for-mapcount-related-invariants.patch thp-fix-memory-failure-hugetlbfs-vs-thp-collision.patch thp-compound_trans_order.patch thp-mm-define-madv_nohugepage.patch thp-madvisemadv_nohugepage.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