From ac16536662137e1aed706adbe0b139cd793dc998 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Thu, 9 Aug 2007 07:51:46 -0700 Subject: [PATCH] SLUB: Trigger defragmentation from memory reclaim This patch triggers slab defragmentation from memory reclaim. The logical point for this is after slab shrinking was performed in vmscan.c. At that point the fragmentation ratio of a slab was increased because objects were freed via the LRUs. So we call kmem_cache_defrag() from there. slab_shrink() from vmscan.c is called in some contexts to do global shrinking of slabs and in others to do shrinking for a particular zone. Pass the zone to slab_shrink, so that slab_shrink can call kmem_cache_defrag() and restrict the defragmentation to the node that is under memory pressure. Reviewed-by: Rik van Riel Signed-off-by: Christoph Lameter --- fs/drop_caches.c | 2 +- include/linux/mm.h | 2 +- mm/vmscan.c | 26 +++++++++++++++++++------- 3 files changed, 21 insertions(+), 9 deletions(-) diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 59375ef..fb58e63 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -50,7 +50,7 @@ void drop_slab(void) int nr_objects; do { - nr_objects = shrink_slab(1000, GFP_KERNEL, 1000); + nr_objects = shrink_slab(1000, GFP_KERNEL, 1000, NULL); } while (nr_objects > 10); } diff --git a/include/linux/mm.h b/include/linux/mm.h index b695875..c322ae3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1206,7 +1206,7 @@ int in_gate_area_no_task(unsigned long addr); int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *, void __user *, size_t *, loff_t *); unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, - unsigned long lru_pages); + unsigned long lru_pages, struct zone *z); void drop_pagecache(void); void drop_slab(void); diff --git a/mm/vmscan.c b/mm/vmscan.c index 4046434..e07dc08 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -166,10 +166,18 @@ EXPORT_SYMBOL(unregister_shrinker); * are eligible for the caller's allocation attempt. It is used for balancing * slab reclaim versus page reclaim. * + * zone is the zone for which we are shrinking the slabs. If the intent + * is to do a global shrink then zone may be NULL. Specification of a + * zone is currently only used to limit slab defragmentation to a NUMA node. + * The performace of shrink_slab would be better (in particular under NUMA) + * if it could be targeted as a whole to the zone that is under memory + * pressure but the VFS infrastructure does not allow that at the present + * time. + * * Returns the number of slab objects which we shrunk. */ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, - unsigned long lru_pages) + unsigned long lru_pages, struct zone *zone) { struct shrinker *shrinker; unsigned long ret = 0; @@ -226,6 +234,8 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask, shrinker->nr += total_scan; } up_read(&shrinker_rwsem); + if (gfp_mask & __GFP_FS) + kmem_cache_defrag(zone ? zone_to_nid(zone) : -1); return ret; } @@ -1339,7 +1349,7 @@ static unsigned long do_try_to_free_pages(struct zone **zones, gfp_t gfp_mask, * over limit cgroups */ if (scan_global_lru(sc)) { - shrink_slab(sc->nr_scanned, gfp_mask, lru_pages); + shrink_slab(sc->nr_scanned, gfp_mask, lru_pages, NULL); if (reclaim_state) { nr_reclaimed += reclaim_state->reclaimed_slab; reclaim_state->reclaimed_slab = 0; @@ -1566,7 +1576,7 @@ loop_again: nr_reclaimed += shrink_zone(priority, zone, &sc); reclaim_state->reclaimed_slab = 0; nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL, - lru_pages); + lru_pages, zone); nr_reclaimed += reclaim_state->reclaimed_slab; total_scanned += sc.nr_scanned; if (zone_is_all_unreclaimable(zone)) @@ -1806,7 +1816,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) /* If slab caches are huge, it's better to hit them first */ while (nr_slab >= lru_pages) { reclaim_state.reclaimed_slab = 0; - shrink_slab(nr_pages, sc.gfp_mask, lru_pages); + shrink_slab(nr_pages, sc.gfp_mask, lru_pages, NULL); if (!reclaim_state.reclaimed_slab) break; @@ -1844,7 +1854,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages) reclaim_state.reclaimed_slab = 0; shrink_slab(sc.nr_scanned, sc.gfp_mask, - count_lru_pages()); + count_lru_pages(), NULL); ret += reclaim_state.reclaimed_slab; if (ret >= nr_pages) goto out; @@ -1861,7 +1871,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages) if (!ret) { do { reclaim_state.reclaimed_slab = 0; - shrink_slab(nr_pages, sc.gfp_mask, count_lru_pages()); + shrink_slab(nr_pages, sc.gfp_mask, + count_lru_pages(), NULL); ret += reclaim_state.reclaimed_slab; } while (ret < nr_pages && reclaim_state.reclaimed_slab > 0); } @@ -2024,7 +2035,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order) * Note that shrink_slab will free memory on all zones and may * take a long time. */ - while (shrink_slab(sc.nr_scanned, gfp_mask, order) && + while (shrink_slab(sc.nr_scanned, gfp_mask, order, + zone) && zone_page_state(zone, NR_SLAB_RECLAIMABLE) > slab_reclaimable - nr_pages) ; -- 1.5.4.4