From 599d0c954f91d0689c9bb421b5bc04ea02437a41 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:31 -0700 Subject: mm, vmscan: move LRU lists to node This moves the LRU lists from the zone to the node and related data such as counters, tracing, congestion tracking and writeback tracking. Unfortunately, due to reclaim and compaction retry logic, it is necessary to account for the number of LRU pages on both zone and node logic. Most reclaim logic is based on the node counters but the retry logic uses the zone counters which do not distinguish inactive and active sizes. It would be possible to leave the LRU counters on a per-zone basis but it's a heavier calculation across multiple cache lines that is much more frequent than the retry checks. Other than the LRU counters, this is mostly a mechanical patch but note that it introduces a number of anomalies. For example, the scans are per-zone but using per-node counters. We also mark a node as congested when a zone is congested. This causes weird problems that are fixed later but is easier to review. In the event that there is excessive overhead on 32-bit systems due to the nodes being on LRU then there are two potential solutions 1. Long-term isolation of highmem pages when reclaim is lowmem When pages are skipped, they are immediately added back onto the LRU list. If lowmem reclaim persisted for long periods of time, the same highmem pages get continually scanned. The idea would be that lowmem keeps those pages on a separate list until a reclaim for highmem pages arrives that splices the highmem pages back onto the LRU. It potentially could be implemented similar to the UNEVICTABLE list. That would reduce the skip rate with the potential corner case is that highmem pages have to be scanned and reclaimed to free lowmem slab pages. 2. Linear scan lowmem pages if the initial LRU shrink fails This will break LRU ordering but may be preferable and faster during memory pressure than skipping LRU pages. Link: http://lkml.kernel.org/r/1467970510-21195-4-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 82d0b98d27f8..c5278360ca66 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1586,7 +1586,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) put_page(page); list_add_tail(&page->lru, &source); move_pages--; - inc_zone_page_state(page, NR_ISOLATED_ANON + + inc_node_page_state(page, NR_ISOLATED_ANON + page_is_file_cache(page)); } else { -- cgit v1.2.3-55-g7522 From 38087d9b0360987a6db46c2c2c4ece37cd048abe Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 28 Jul 2016 15:45:49 -0700 Subject: mm, vmscan: simplify the logic deciding whether kswapd sleeps kswapd goes through some complex steps trying to figure out if it should stay awake based on the classzone_idx and the requested order. It is unnecessarily complex and passes in an invalid classzone_idx to balance_pgdat(). What matters most of all is whether a larger order has been requsted and whether kswapd successfully reclaimed at the previous order. This patch irons out the logic to check just that and the end result is less headache inducing. Link: http://lkml.kernel.org/r/1467970510-21195-10-git-send-email-mgorman@techsingularity.net Signed-off-by: Mel Gorman Acked-by: Johannes Weiner Acked-by: Vlastimil Babka Cc: Hillf Danton Cc: Joonsoo Kim Cc: Michal Hocko Cc: Minchan Kim Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ++- mm/memory_hotplug.c | 5 ++- mm/page_alloc.c | 2 +- mm/vmscan.c | 101 ++++++++++++++++++++++++------------------------- 4 files changed, 57 insertions(+), 56 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index edafdaf62e90..4062fa74526f 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -668,8 +668,9 @@ typedef struct pglist_data { wait_queue_head_t pfmemalloc_wait; struct task_struct *kswapd; /* Protected by mem_hotplug_begin/end() */ - int kswapd_max_order; - enum zone_type classzone_idx; + int kswapd_order; + enum zone_type kswapd_classzone_idx; + #ifdef CONFIG_COMPACTION int kcompactd_max_order; enum zone_type kcompactd_classzone_idx; diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index c5278360ca66..065140ecd081 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1209,9 +1209,10 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) arch_refresh_nodedata(nid, pgdat); } else { - /* Reset the nr_zones and classzone_idx to 0 before reuse */ + /* Reset the nr_zones, order and classzone_idx before reuse */ pgdat->nr_zones = 0; - pgdat->classzone_idx = 0; + pgdat->kswapd_order = 0; + pgdat->kswapd_classzone_idx = 0; } /* we can use NODE_DATA(nid) from here */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 35e2d0f9d44f..81586410c59c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6039,7 +6039,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, unsigned long end_pfn = 0; /* pg_data_t should be reset to zero when it's allocated */ - WARN_ON(pgdat->nr_zones || pgdat->classzone_idx); + WARN_ON(pgdat->nr_zones || pgdat->kswapd_classzone_idx); reset_deferred_meminit(pgdat); pgdat->node_id = nid; diff --git a/mm/vmscan.c b/mm/vmscan.c index a52167eabc96..905c60473126 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2762,7 +2762,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { - pgdat->classzone_idx = min(pgdat->classzone_idx, + pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx, (enum zone_type)ZONE_NORMAL); wake_up_interruptible(&pgdat->kswapd_wait); } @@ -3042,11 +3042,11 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, if (!populated_zone(zone)) continue; - if (zone_balanced(zone, order, classzone_idx)) - return true; + if (!zone_balanced(zone, order, classzone_idx)) + return false; } - return false; + return true; } /* @@ -3238,8 +3238,8 @@ out: return sc.order; } -static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, - int classzone_idx, int balanced_classzone_idx) +static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, + unsigned int classzone_idx) { long remaining = 0; DEFINE_WAIT(wait); @@ -3250,8 +3250,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); /* Try to sleep for a short interval */ - if (prepare_kswapd_sleep(pgdat, order, remaining, - balanced_classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) { /* * Compaction records what page blocks it recently failed to * isolate pages from and skips them in the future scanning. @@ -3264,9 +3263,20 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, * We have freed the memory, now we should compact it to make * allocation of the requested order possible. */ - wakeup_kcompactd(pgdat, order, classzone_idx); + wakeup_kcompactd(pgdat, alloc_order, classzone_idx); remaining = schedule_timeout(HZ/10); + + /* + * If woken prematurely then reset kswapd_classzone_idx and + * order. The values will either be from a wakeup request or + * the previous request that slept prematurely. + */ + if (remaining) { + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx); + pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order); + } + finish_wait(&pgdat->kswapd_wait, &wait); prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE); } @@ -3275,8 +3285,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, * After a short sleep, check if it was a premature sleep. If not, then * go fully to sleep until explicitly woken up. */ - if (prepare_kswapd_sleep(pgdat, order, remaining, - balanced_classzone_idx)) { + if (prepare_kswapd_sleep(pgdat, reclaim_order, remaining, classzone_idx)) { trace_mm_vmscan_kswapd_sleep(pgdat->node_id); /* @@ -3317,9 +3326,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, */ static int kswapd(void *p) { - unsigned long order, new_order; - int classzone_idx, new_classzone_idx; - int balanced_classzone_idx; + unsigned int alloc_order, reclaim_order, classzone_idx; pg_data_t *pgdat = (pg_data_t*)p; struct task_struct *tsk = current; @@ -3349,38 +3356,20 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - order = new_order = 0; - classzone_idx = new_classzone_idx = pgdat->nr_zones - 1; - balanced_classzone_idx = classzone_idx; + pgdat->kswapd_order = alloc_order = reclaim_order = 0; + pgdat->kswapd_classzone_idx = classzone_idx = 0; for ( ; ; ) { bool ret; - /* - * While we were reclaiming, there might have been another - * wakeup, so check the values. - */ - new_order = pgdat->kswapd_max_order; - new_classzone_idx = pgdat->classzone_idx; - pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = pgdat->nr_zones - 1; +kswapd_try_sleep: + kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order, + classzone_idx); - if (order < new_order || classzone_idx > new_classzone_idx) { - /* - * Don't sleep if someone wants a larger 'order' - * allocation or has tigher zone constraints - */ - order = new_order; - classzone_idx = new_classzone_idx; - } else { - kswapd_try_to_sleep(pgdat, order, classzone_idx, - balanced_classzone_idx); - order = pgdat->kswapd_max_order; - classzone_idx = pgdat->classzone_idx; - new_order = order; - new_classzone_idx = classzone_idx; - pgdat->kswapd_max_order = 0; - pgdat->classzone_idx = pgdat->nr_zones - 1; - } + /* Read the new order and classzone_idx */ + alloc_order = reclaim_order = pgdat->kswapd_order; + classzone_idx = pgdat->kswapd_classzone_idx; + pgdat->kswapd_order = 0; + pgdat->kswapd_classzone_idx = 0; ret = try_to_freeze(); if (kthread_should_stop()) @@ -3390,12 +3379,24 @@ static int kswapd(void *p) * We can speed up thawing tasks if we don't call balance_pgdat * after returning from the refrigerator */ - if (!ret) { - trace_mm_vmscan_kswapd_wake(pgdat->node_id, order); + if (ret) + continue; + + /* + * Reclaim begins at the requested order but if a high-order + * reclaim fails then kswapd falls back to reclaiming for + * order-0. If that happens, kswapd will consider sleeping + * for the order it finished reclaiming at (reclaim_order) + * but kcompactd is woken to compact for the original + * request (alloc_order). + */ + trace_mm_vmscan_kswapd_wake(pgdat->node_id, alloc_order); + reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx); + if (reclaim_order < alloc_order) + goto kswapd_try_sleep; - /* return value ignored until next patch */ - balance_pgdat(pgdat, order, classzone_idx); - } + alloc_order = reclaim_order = pgdat->kswapd_order; + classzone_idx = pgdat->kswapd_classzone_idx; } tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD); @@ -3418,10 +3419,8 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) return; pgdat = zone->zone_pgdat; - if (pgdat->kswapd_max_order < order) { - pgdat->kswapd_max_order = order; - pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx); - } + pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx); + pgdat->kswapd_order = max(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; if (zone_balanced(zone, order, 0)) -- cgit v1.2.3-55-g7522 From 394e31d2ceb4b9eae25bd9ed8ea8cb19a40ff181 Mon Sep 17 00:00:00 2001 From: Xishi Qiu Date: Thu, 28 Jul 2016 15:48:53 -0700 Subject: mem-hotplug: alloc new page from a nearest neighbor node when mem-offline If we offline a node, alloc the new page from a nearest neighbor node instead of the current node or other remote nodes, because re-migrate is a waste of time and the distance of the remote nodes is often very large. Also use GFP_HIGHUSER_MOVABLE to alloc new page if the zone is movable zone or highmem zone. Link: http://lkml.kernel.org/r/5795E18B.5060302@huawei.com Signed-off-by: Xishi Qiu Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Naoya Horiguchi Cc: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 38 +++++++++++++++++++++++++++++++++----- 1 file changed, 33 insertions(+), 5 deletions(-) (limited to 'mm/memory_hotplug.c') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 065140ecd081..3894b65b1555 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1548,6 +1548,37 @@ static unsigned long scan_movable_pages(unsigned long start, unsigned long end) return 0; } +static struct page *new_node_page(struct page *page, unsigned long private, + int **result) +{ + gfp_t gfp_mask = GFP_USER | __GFP_MOVABLE; + int nid = page_to_nid(page); + nodemask_t nmask = node_online_map; + struct page *new_page; + + /* + * TODO: allocate a destination hugepage from a nearest neighbor node, + * accordance with memory policy of the user process if possible. For + * now as a simple work-around, we use the next node for destination. + */ + if (PageHuge(page)) + return alloc_huge_page_node(page_hstate(compound_head(page)), + next_node_in(nid, nmask)); + + node_clear(nid, nmask); + if (PageHighMem(page) + || (zone_idx(page_zone(page)) == ZONE_MOVABLE)) + gfp_mask |= __GFP_HIGHMEM; + + new_page = __alloc_pages_nodemask(gfp_mask, 0, + node_zonelist(nid, gfp_mask), &nmask); + if (!new_page) + new_page = __alloc_pages(gfp_mask, 0, + node_zonelist(nid, gfp_mask)); + + return new_page; +} + #define NR_OFFLINE_AT_ONCE_PAGES (256) static int do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) @@ -1611,11 +1642,8 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn) goto out; } - /* - * alloc_migrate_target should be improooooved!! - * migrate_pages returns # of failed pages. - */ - ret = migrate_pages(&source, alloc_migrate_target, NULL, 0, + /* Allocate a new page from the nearest neighbor node */ + ret = migrate_pages(&source, new_node_page, NULL, 0, MIGRATE_SYNC, MR_MEMORY_HOTPLUG); if (ret) putback_movable_pages(&source); -- cgit v1.2.3-55-g7522