Subject: [merged] mm-vmscan-move-logic-from-balance_pgdat-to-kswapd_shrink_zone.patch removed from -mm tree To: mgorman@xxxxxxx,Valdis.Kletnieks@xxxxxx,dormando@xxxxxxxxx,hannes@xxxxxxxxxxx,jslaby@xxxxxxx,kamezawa.hiroyu@xxxxxxxxxxxxxx,mhocko@xxxxxxx,riel@xxxxxxxxxx,zcalusic@xxxxxxxxxxx,mm-commits@xxxxxxxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Mon, 08 Jul 2013 12:24:49 -0700 The patch titled Subject: mm: vmscan: move logic from balance_pgdat() to kswapd_shrink_zone() has been removed from the -mm tree. Its filename was mm-vmscan-move-logic-from-balance_pgdat-to-kswapd_shrink_zone.patch This patch was dropped because it was merged into mainline or a subsystem tree ------------------------------------------------------ From: Mel Gorman <mgorman@xxxxxxx> Subject: mm: vmscan: move logic from balance_pgdat() to kswapd_shrink_zone() balance_pgdat() is very long and some of the logic can and should be internal to kswapd_shrink_zone(). Move it so the flow of balance_pgdat() is marginally easier to follow. Signed-off-by: Mel Gorman <mgorman@xxxxxxx> Acked-by: Johannes Weiner <hannes@xxxxxxxxxxx> Reviewed-by: Michal Hocko <mhocko@xxxxxxx> Acked-by: Rik van Riel <riel@xxxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: Jiri Slaby <jslaby@xxxxxxx> Cc: Valdis Kletnieks <Valdis.Kletnieks@xxxxxx> Tested-by: Zlatko Calusic <zcalusic@xxxxxxxxxxx> Cc: dormando <dormando@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/vmscan.c | 112 ++++++++++++++++++++++++-------------------------- 1 file changed, 55 insertions(+), 57 deletions(-) diff -puN mm/vmscan.c~mm-vmscan-move-logic-from-balance_pgdat-to-kswapd_shrink_zone mm/vmscan.c --- a/mm/vmscan.c~mm-vmscan-move-logic-from-balance_pgdat-to-kswapd_shrink_zone +++ a/mm/vmscan.c @@ -2709,18 +2709,53 @@ static bool prepare_kswapd_sleep(pg_data * This is used to determine if the scanning priority needs to be raised. */ static bool kswapd_shrink_zone(struct zone *zone, + int classzone_idx, struct scan_control *sc, unsigned long lru_pages, unsigned long *nr_attempted) { unsigned long nr_slab; + int testorder = sc->order; + unsigned long balance_gap; struct reclaim_state *reclaim_state = current->reclaim_state; struct shrink_control shrink = { .gfp_mask = sc->gfp_mask, }; + bool lowmem_pressure; /* Reclaim above the high watermark. */ sc->nr_to_reclaim = max(SWAP_CLUSTER_MAX, high_wmark_pages(zone)); + + /* + * Kswapd reclaims only single pages with compaction enabled. Trying + * too hard to reclaim until contiguous free pages have become + * available can hurt performance by evicting too much useful data + * from memory. Do not reclaim more than needed for compaction. + */ + if (IS_ENABLED(CONFIG_COMPACTION) && sc->order && + compaction_suitable(zone, sc->order) != + COMPACT_SKIPPED) + testorder = 0; + + /* + * We put equal pressure on every zone, unless one zone has way too + * many pages free already. The "too many pages" is defined as the + * high wmark plus a "gap" where the gap is either the low + * watermark or 1% of the zone, whichever is smaller. + */ + balance_gap = min(low_wmark_pages(zone), + (zone->managed_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / + KSWAPD_ZONE_BALANCE_GAP_RATIO); + + /* + * If there is no low memory pressure or the zone is balanced then no + * reclaim is necessary + */ + lowmem_pressure = (buffer_heads_over_limit && is_highmem(zone)); + if (!lowmem_pressure && zone_balanced(zone, testorder, + balance_gap, classzone_idx)) + return true; + shrink_zone(zone, sc); reclaim_state->reclaimed_slab = 0; @@ -2735,6 +2770,18 @@ static bool kswapd_shrink_zone(struct zo zone_clear_flag(zone, ZONE_WRITEBACK); + /* + * If a zone reaches its high watermark, consider it to be no longer + * congested. It's possible there are dirty pages backed by congested + * BDIs but as pressure is relieved, speculatively avoid congestion + * waits. + */ + if (!zone->all_unreclaimable && + zone_balanced(zone, testorder, 0, classzone_idx)) { + zone_clear_flag(zone, ZONE_CONGESTED); + zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); + } + return sc->nr_scanned >= sc->nr_to_reclaim; } @@ -2870,8 +2917,6 @@ static unsigned long balance_pgdat(pg_da */ for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; - int testorder; - unsigned long balance_gap; if (!populated_zone(zone)) continue; @@ -2892,61 +2937,14 @@ static unsigned long balance_pgdat(pg_da sc.nr_reclaimed += nr_soft_reclaimed; /* - * We put equal pressure on every zone, unless - * one zone has way too many pages free - * already. The "too many pages" is defined - * as the high wmark plus a "gap" where the - * gap is either the low watermark or 1% - * of the zone, whichever is smaller. - */ - balance_gap = min(low_wmark_pages(zone), - (zone->managed_pages + - KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / - KSWAPD_ZONE_BALANCE_GAP_RATIO); - /* - * Kswapd reclaims only single pages with compaction - * enabled. Trying too hard to reclaim until contiguous - * free pages have become available can hurt performance - * by evicting too much useful data from memory. - * Do not reclaim more than needed for compaction. - */ - testorder = order; - if (IS_ENABLED(CONFIG_COMPACTION) && order && - compaction_suitable(zone, order) != - COMPACT_SKIPPED) - testorder = 0; - - if ((buffer_heads_over_limit && is_highmem_idx(i)) || - !zone_balanced(zone, testorder, - balance_gap, end_zone)) { - /* - * There should be no need to raise the - * scanning priority if enough pages are - * already being scanned that high - * watermark would be met at 100% efficiency. - */ - if (kswapd_shrink_zone(zone, &sc, lru_pages, - &nr_attempted)) - raise_priority = false; - } - - if (zone->all_unreclaimable) { - if (end_zone && end_zone == i) - end_zone--; - continue; - } - - if (zone_balanced(zone, testorder, 0, end_zone)) - /* - * If a zone reaches its high watermark, - * consider it to be no longer congested. It's - * possible there are dirty pages backed by - * congested BDIs but as pressure is relieved, - * speculatively avoid congestion waits - * or writing pages from kswapd context. - */ - zone_clear_flag(zone, ZONE_CONGESTED); - zone_clear_flag(zone, ZONE_TAIL_LRU_DIRTY); + * There should be no need to raise the scanning + * priority if enough pages are already being scanned + * that that high watermark would be met at 100% + * efficiency. + */ + if (kswapd_shrink_zone(zone, end_zone, &sc, + lru_pages, &nr_attempted)) + raise_priority = false; } /* _ Patches currently in -mm which might be from mgorman@xxxxxxx are origin.patch linux-next.patch fs-bump-inode-and-dentry-counters-to-long.patch super-fix-calculation-of-shrinkable-objects-for-small-numbers.patch dcache-convert-dentry_statnr_unused-to-per-cpu-counters.patch dentry-move-to-per-sb-lru-locks.patch dcache-remove-dentries-from-lru-before-putting-on-dispose-list.patch mm-new-shrinker-api.patch shrinker-convert-superblock-shrinkers-to-new-api.patch list-add-a-new-lru-list-type.patch inode-convert-inode-lru-list-to-generic-lru-list-code.patch dcache-convert-to-use-new-lru-list-infrastructure.patch list_lru-per-node-list-infrastructure.patch list_lru-per-node-api.patch shrinker-add-node-awareness.patch vmscan-per-node-deferred-work.patch fs-convert-inode-and-dentry-shrinking-to-be-node-aware.patch xfs-convert-buftarg-lru-to-generic-code.patch xfs-rework-buffer-dispose-list-tracking.patch xfs-convert-dquot-cache-lru-to-list_lru.patch fs-convert-fs-shrinkers-to-new-scan-count-api.patch drivers-convert-shrinkers-to-new-count-scan-api.patch i915-bail-out-earlier-when-shrinker-cannot-acquire-mutex.patch shrinker-convert-remaining-shrinkers-to-count-scan-api.patch hugepage-convert-huge-zero-page-shrinker-to-new-shrinker-api.patch shrinker-kill-old-shrink-api.patch list_lru-dynamically-adjust-node-arrays.patch zbud-add-to-mm.patch zswap-add-to-mm.patch zswap-add-documentation.patch mm-vmscan-do-not-continue-scanning-if-reclaim-was-aborted-for-compaction.patch mm-vmscan-do-not-scale-writeback-pages-when-deciding-whether-to-set-zone_writeback.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