The patch titled Subject: mm: vmscan: rework compaction-ready signaling in direct reclaim has been removed from the -mm tree. Its filename was mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Johannes Weiner <hannes@xxxxxxxxxxx> Subject: mm: vmscan: rework compaction-ready signaling in direct reclaim Page reclaim for a higher-order page runs until compaction is ready, then aborts and signals this situation through the return value of shrink_zones(). This is an oddly specific signal to encode in the return value of shrink_zones(), though, and can be quite confusing. Introduce sc->compaction_ready and signal the compactability of the zones out-of-band to free up the return value of shrink_zones() for actual zone reclaimability. Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx> Acked-by: Vlastimil Babka <vbabka@xxxxxxx> Cc: Mel Gorman <mgorman@xxxxxxx> Cc: Rik van Riel <riel@xxxxxxxxxx> Cc: Michal Hocko <mhocko@xxxxxxx> Acked-by: Minchan Kim <minchan@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/vmscan.c | 70 ++++++++++++++++++++++---------------------------- 1 file changed, 32 insertions(+), 38 deletions(-) diff -puN mm/vmscan.c~mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim mm/vmscan.c --- a/mm/vmscan.c~mm-vmscan-rework-compaction-ready-signaling-in-direct-reclaim +++ a/mm/vmscan.c @@ -65,6 +65,9 @@ struct scan_control { /* Number of pages freed so far during a call to shrink_zones() */ unsigned long nr_reclaimed; + /* One of the zones is ready for compaction */ + int compaction_ready; + /* How many pages shrink_list() should reclaim */ unsigned long nr_to_reclaim; @@ -2292,15 +2295,11 @@ static void shrink_zone(struct zone *zon } /* Returns true if compaction should go ahead for a high-order request */ -static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) +static inline bool compaction_ready(struct zone *zone, int order) { unsigned long balance_gap, watermark; bool watermark_ok; - /* Do not consider compaction for orders reclaim is meant to satisfy */ - if (sc->order <= PAGE_ALLOC_COSTLY_ORDER) - return false; - /* * Compaction takes time to run and there are potentially other * callers using the pages just freed. Continue reclaiming until @@ -2309,18 +2308,18 @@ static inline bool compaction_ready(stru */ balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP( zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO)); - watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order); + watermark = high_wmark_pages(zone) + balance_gap + (2UL << order); watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0); /* * If compaction is deferred, reclaim up to a point where * compaction will have a chance of success when re-enabled */ - if (compaction_deferred(zone, sc->order)) + if (compaction_deferred(zone, order)) return watermark_ok; /* If compaction is not ready to start, keep reclaiming */ - if (!compaction_suitable(zone, sc->order)) + if (!compaction_suitable(zone, order)) return false; return watermark_ok; @@ -2341,20 +2340,14 @@ static inline bool compaction_ready(stru * * If a zone is deemed to be full of pinned pages then just give it a light * scan then give up on it. - * - * This function returns true if a zone is being reclaimed for a costly - * high-order allocation and compaction is ready to begin. This indicates to - * the caller that it should consider retrying the allocation instead of - * further reclaim. */ -static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) +static void shrink_zones(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; unsigned long lru_pages = 0; - bool aborted_reclaim = false; struct reclaim_state *reclaim_state = current->reclaim_state; gfp_t orig_mask; struct shrink_control shrink = { @@ -2391,22 +2384,24 @@ static bool shrink_zones(struct zonelist if (sc->priority != DEF_PRIORITY && !zone_reclaimable(zone)) continue; /* Let kswapd poll it */ - if (IS_ENABLED(CONFIG_COMPACTION)) { - /* - * If we already have plenty of memory free for - * compaction in this zone, don't free any more. - * Even though compaction is invoked for any - * non-zero order, only frequent costly order - * reclamation is disruptive enough to become a - * noticeable problem, like transparent huge - * page allocations. - */ - if ((zonelist_zone_idx(z) <= requested_highidx) - && compaction_ready(zone, sc)) { - aborted_reclaim = true; - continue; - } + + /* + * If we already have plenty of memory free for + * compaction in this zone, don't free any more. + * Even though compaction is invoked for any + * non-zero order, only frequent costly order + * reclamation is disruptive enough to become a + * noticeable problem, like transparent huge + * page allocations. + */ + if (IS_ENABLED(CONFIG_COMPACTION) && + sc->order > PAGE_ALLOC_COSTLY_ORDER && + zonelist_zone_idx(z) <= requested_highidx && + compaction_ready(zone, sc->order)) { + sc->compaction_ready = true; + continue; } + /* * This steals pages from memory cgroups over softlimit * and returns the number of reclaimed pages and @@ -2444,8 +2439,6 @@ static bool shrink_zones(struct zonelist * promoted it to __GFP_HIGHMEM. */ sc->gfp_mask = orig_mask; - - return aborted_reclaim; } /* All zones in zonelist are unreclaimable? */ @@ -2489,7 +2482,6 @@ static unsigned long do_try_to_free_page { unsigned long total_scanned = 0; unsigned long writeback_threshold; - bool aborted_reclaim; delayacct_freepages_start(); @@ -2500,11 +2492,14 @@ static unsigned long do_try_to_free_page vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, sc->priority); sc->nr_scanned = 0; - aborted_reclaim = shrink_zones(zonelist, sc); + shrink_zones(zonelist, sc); total_scanned += sc->nr_scanned; if (sc->nr_reclaimed >= sc->nr_to_reclaim) - goto out; + break; + + if (sc->compaction_ready) + break; /* * If we're getting trouble reclaiming, start doing @@ -2526,16 +2521,15 @@ static unsigned long do_try_to_free_page WB_REASON_TRY_TO_FREE_PAGES); sc->may_writepage = 1; } - } while (--sc->priority >= 0 && !aborted_reclaim); + } while (--sc->priority >= 0); -out: delayacct_freepages_end(); if (sc->nr_reclaimed) return sc->nr_reclaimed; /* Aborted reclaim to try compaction? don't OOM, then */ - if (aborted_reclaim) + if (sc->compaction_ready) return 1; /* top priority shrink_zones still had more to do? don't OOM, then */ _ Patches currently in -mm which might be from hannes@xxxxxxxxxxx are origin.patch mm-memcontrol-rewrite-charge-api.patch mm-memcontrol-rewrite-uncharge-api.patch mm-memcontrol-use-page-lists-for-uncharge-batching.patch mm-memcontrol-use-page-lists-for-uncharge-batching-fix-hugetlb-page-lru.patch page-cgroup-trivial-cleanup.patch page-cgroup-get-rid-of-nr_pcg_flags.patch memcg-remove-lookup_cgroup_page-prototype.patch mm-memcontrol-avoid-charge-statistics-churn-during-page-migration.patch nilfs2-integrate-sysfs-support-into-driver-fix.patch linux-next.patch debugging-keep-track-of-page-owners.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