From 0be94bad0b601df94b8558c0cbd28f7e6633c9e8 Mon Sep 17 00:00:00 2001 From: "Srivatsa S. Bhat" Date: Tue, 11 Mar 2014 02:12:27 +0530 Subject: mm, vmstat: Fix CPU hotplug callback registration Subsystems that want to register CPU hotplug callbacks, as well as perform initialization for the CPUs that are already online, often do it as shown below: get_online_cpus(); for_each_online_cpu(cpu) init_cpu(cpu); register_cpu_notifier(&foobar_cpu_notifier); put_online_cpus(); This is wrong, since it is prone to ABBA deadlocks involving the cpu_add_remove_lock and the cpu_hotplug.lock (when running concurrently with CPU hotplug operations). Instead, the correct and race-free way of performing the callback registration is: cpu_notifier_register_begin(); for_each_online_cpu(cpu) init_cpu(cpu); /* Note the use of the double underscored version of the API */ __register_cpu_notifier(&foobar_cpu_notifier); cpu_notifier_register_done(); Fix the vmstat code in the MM subsystem by using this latter form of callback registration. Cc: Andrew Morton Cc: Johannes Weiner Cc: Cody P Schafer Cc: Toshi Kani Cc: Dave Hansen Cc: Ingo Molnar Acked-by: Christoph Lameter Acked-by: Rik van Riel Reviewed-by: Yasuaki Ishimatsu Signed-off-by: Srivatsa S. Bhat Signed-off-by: Rafael J. Wysocki --- mm/vmstat.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm/vmstat.c') diff --git a/mm/vmstat.c b/mm/vmstat.c index def5dd2fbe61..58c6f3d09735 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1292,14 +1292,14 @@ static int __init setup_vmstat(void) #ifdef CONFIG_SMP int cpu; - register_cpu_notifier(&vmstat_notifier); + cpu_notifier_register_begin(); + __register_cpu_notifier(&vmstat_notifier); - get_online_cpus(); for_each_online_cpu(cpu) { start_cpu_timer(cpu); node_set_state(cpu_to_node(cpu), N_CPU); } - put_online_cpus(); + cpu_notifier_register_done(); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); -- cgit v1.2.3 From a528910e12ec7ee203095eb1711468a66b9b60b0 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 3 Apr 2014 14:47:51 -0700 Subject: mm: thrash detection-based file cache sizing The VM maintains cached filesystem pages on two types of lists. One list holds the pages recently faulted into the cache, the other list holds pages that have been referenced repeatedly on that first list. The idea is to prefer reclaiming young pages over those that have shown to benefit from caching in the past. We call the recently usedbut ultimately was not significantly better than a FIFO policy and still thrashed cache based on eviction speed, rather than actual demand for cache. This patch solves one half of the problem by decoupling the ability to detect working set changes from the inactive list size. By maintaining a history of recently evicted file pages it can detect frequently used pages with an arbitrarily small inactive list size, and subsequently apply pressure on the active list based on actual demand for cache, not just overall eviction speed. Every zone maintains a counter that tracks inactive list aging speed. When a page is evicted, a snapshot of this counter is stored in the now-empty page cache radix tree slot. On refault, the minimum access distance of the page can be assessed, to evaluate whether the page should be part of the active list or not. This fixes the VM's blindness towards working set changes in excess of the inactive list. And it's the foundation to further improve the protection ability and reduce the minimum inactive list size of 50%. Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Reviewed-by: Bob Liu Cc: Andrea Arcangeli Cc: Christoph Hellwig Cc: Dave Chinner Cc: Greg Thelen Cc: Hugh Dickins Cc: Jan Kara Cc: KOSAKI Motohiro Cc: Luigi Semenzato Cc: Mel Gorman Cc: Metin Doslu Cc: Michel Lespinasse Cc: Ozgun Erdogan Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Ryan Mallon Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 + include/linux/swap.h | 5 + mm/Makefile | 2 +- mm/filemap.c | 61 ++++++++---- mm/swap.c | 2 + mm/vmscan.c | 24 ++++- mm/vmstat.c | 2 + mm/workingset.c | 253 +++++++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 331 insertions(+), 23 deletions(-) create mode 100644 mm/workingset.c (limited to 'mm/vmstat.c') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9b61b9bf81ac..f25db1d74a21 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -142,6 +142,8 @@ enum zone_stat_item { NUMA_LOCAL, /* allocation from local node */ NUMA_OTHER, /* allocation from other node */ #endif + WORKINGSET_REFAULT, + WORKINGSET_ACTIVATE, NR_ANON_TRANSPARENT_HUGEPAGES, NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; @@ -392,6 +394,9 @@ struct zone { spinlock_t lru_lock; struct lruvec lruvec; + /* Evictions & activations on the inactive file list */ + atomic_long_t inactive_age; + unsigned long pages_scanned; /* since last reclaim */ unsigned long flags; /* zone flags, see below */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 46ba0c6c219f..b83cf61403ed 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -260,6 +260,11 @@ struct swap_list_t { int next; /* swapfile to be used next */ }; +/* linux/mm/workingset.c */ +void *workingset_eviction(struct address_space *mapping, struct page *page); +bool workingset_refault(void *shadow); +void workingset_activation(struct page *page); + /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; diff --git a/mm/Makefile b/mm/Makefile index 310c90a09264..cdd741519ee0 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -17,7 +17,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ util.o mmzone.o vmstat.o backing-dev.o \ mm_init.o mmu_context.o percpu.o slab_common.o \ compaction.o balloon_compaction.o \ - interval_tree.o list_lru.o $(mmu-y) + interval_tree.o list_lru.o workingset.o $(mmu-y) obj-y += init-mm.o diff --git a/mm/filemap.c b/mm/filemap.c index 05c44aa44188..a603c4d7d3c9 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -469,7 +469,7 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) EXPORT_SYMBOL_GPL(replace_page_cache_page); static int page_cache_tree_insert(struct address_space *mapping, - struct page *page) + struct page *page, void **shadowp) { void **slot; int error; @@ -484,6 +484,8 @@ static int page_cache_tree_insert(struct address_space *mapping, radix_tree_replace_slot(slot, page); mapping->nrshadows--; mapping->nrpages++; + if (shadowp) + *shadowp = p; return 0; } error = radix_tree_insert(&mapping->page_tree, page->index, page); @@ -492,18 +494,10 @@ static int page_cache_tree_insert(struct address_space *mapping, return error; } -/** - * add_to_page_cache_locked - add a locked page to the pagecache - * @page: page to add - * @mapping: the page's address_space - * @offset: page index - * @gfp_mask: page allocation mode - * - * This function is used to add a page to the pagecache. It must be locked. - * This function does not add the page to the LRU. The caller must do that. - */ -int add_to_page_cache_locked(struct page *page, struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask) +static int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) { int error; @@ -526,7 +520,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, page->index = offset; spin_lock_irq(&mapping->tree_lock); - error = page_cache_tree_insert(mapping, page); + error = page_cache_tree_insert(mapping, page, shadowp); radix_tree_preload_end(); if (unlikely(error)) goto err_insert; @@ -542,16 +536,49 @@ err_insert: page_cache_release(page); return error; } + +/** + * add_to_page_cache_locked - add a locked page to the pagecache + * @page: page to add + * @mapping: the page's address_space + * @offset: page index + * @gfp_mask: page allocation mode + * + * This function is used to add a page to the pagecache. It must be locked. + * This function does not add the page to the LRU. The caller must do that. + */ +int add_to_page_cache_locked(struct page *page, struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask) +{ + return __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, NULL); +} EXPORT_SYMBOL(add_to_page_cache_locked); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask) { + void *shadow = NULL; int ret; - ret = add_to_page_cache(page, mapping, offset, gfp_mask); - if (ret == 0) - lru_cache_add_file(page); + __set_page_locked(page); + ret = __add_to_page_cache_locked(page, mapping, offset, + gfp_mask, &shadow); + if (unlikely(ret)) + __clear_page_locked(page); + else { + /* + * The page might have been evicted from cache only + * recently, in which case it should be activated like + * any other repeatedly accessed page. + */ + if (shadow && workingset_refault(shadow)) { + SetPageActive(page); + workingset_activation(page); + } else + ClearPageActive(page); + lru_cache_add(page); + } return ret; } EXPORT_SYMBOL_GPL(add_to_page_cache_lru); diff --git a/mm/swap.c b/mm/swap.c index c8048d71c642..9ce43ba4498b 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -574,6 +574,8 @@ void mark_page_accessed(struct page *page) else __lru_cache_activate_page(page); ClearPageReferenced(page); + if (page_is_file_cache(page)) + workingset_activation(page); } else if (!PageReferenced(page)) { SetPageReferenced(page); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 2a0bb8fdb259..1f56a80a7c41 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -523,7 +523,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, * Same as remove_mapping, but if the page is removed from the mapping, it * gets returned with a refcount of 0. */ -static int __remove_mapping(struct address_space *mapping, struct page *page) +static int __remove_mapping(struct address_space *mapping, struct page *page, + bool reclaimed) { BUG_ON(!PageLocked(page)); BUG_ON(mapping != page_mapping(page)); @@ -569,10 +570,23 @@ static int __remove_mapping(struct address_space *mapping, struct page *page) swapcache_free(swap, page); } else { void (*freepage)(struct page *); + void *shadow = NULL; freepage = mapping->a_ops->freepage; - - __delete_from_page_cache(page, NULL); + /* + * Remember a shadow entry for reclaimed file cache in + * order to detect refaults, thus thrashing, later on. + * + * But don't store shadows in an address space that is + * already exiting. This is not just an optizimation, + * inode reclaim needs to empty out the radix tree or + * the nodes are lost. Don't plant shadows behind its + * back. + */ + if (reclaimed && page_is_file_cache(page) && + !mapping_exiting(mapping)) + shadow = workingset_eviction(mapping, page); + __delete_from_page_cache(page, shadow); spin_unlock_irq(&mapping->tree_lock); mem_cgroup_uncharge_cache_page(page); @@ -595,7 +609,7 @@ cannot_free: */ int remove_mapping(struct address_space *mapping, struct page *page) { - if (__remove_mapping(mapping, page)) { + if (__remove_mapping(mapping, page, false)) { /* * Unfreezing the refcount with 1 rather than 2 effectively * drops the pagecache ref for us without requiring another @@ -1065,7 +1079,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, } } - if (!mapping || !__remove_mapping(mapping, page)) + if (!mapping || !__remove_mapping(mapping, page, true)) goto keep_locked; /* diff --git a/mm/vmstat.c b/mm/vmstat.c index def5dd2fbe61..843125a0e255 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -770,6 +770,8 @@ const char * const vmstat_text[] = { "numa_local", "numa_other", #endif + "workingset_refault", + "workingset_activate", "nr_anon_transparent_hugepages", "nr_free_cma", "nr_dirty_threshold", diff --git a/mm/workingset.c b/mm/workingset.c new file mode 100644 index 000000000000..8a6c7cff4923 --- /dev/null +++ b/mm/workingset.c @@ -0,0 +1,253 @@ +/* + * Workingset detection + * + * Copyright (C) 2013 Red Hat, Inc., Johannes Weiner + */ + +#include +#include +#include +#include +#include +#include +#include +#include + +/* + * Double CLOCK lists + * + * Per zone, two clock lists are maintained for file pages: the + * inactive and the active list. Freshly faulted pages start out at + * the head of the inactive list and page reclaim scans pages from the + * tail. Pages that are accessed multiple times on the inactive list + * are promoted to the active list, to protect them from reclaim, + * whereas active pages are demoted to the inactive list when the + * active list grows too big. + * + * fault ------------------------+ + * | + * +--------------+ | +-------------+ + * reclaim <- | inactive | <-+-- demotion | active | <--+ + * +--------------+ +-------------+ | + * | | + * +-------------- promotion ------------------+ + * + * + * Access frequency and refault distance + * + * A workload is thrashing when its pages are frequently used but they + * are evicted from the inactive list every time before another access + * would have promoted them to the active list. + * + * In cases where the average access distance between thrashing pages + * is bigger than the size of memory there is nothing that can be + * done - the thrashing set could never fit into memory under any + * circumstance. + * + * However, the average access distance could be bigger than the + * inactive list, yet smaller than the size of memory. In this case, + * the set could fit into memory if it weren't for the currently + * active pages - which may be used more, hopefully less frequently: + * + * +-memory available to cache-+ + * | | + * +-inactive------+-active----+ + * a b | c d e f g h i | J K L M N | + * +---------------+-----------+ + * + * It is prohibitively expensive to accurately track access frequency + * of pages. But a reasonable approximation can be made to measure + * thrashing on the inactive list, after which refaulting pages can be + * activated optimistically to compete with the existing active pages. + * + * Approximating inactive page access frequency - Observations: + * + * 1. When a page is accessed for the first time, it is added to the + * head of the inactive list, slides every existing inactive page + * towards the tail by one slot, and pushes the current tail page + * out of memory. + * + * 2. When a page is accessed for the second time, it is promoted to + * the active list, shrinking the inactive list by one slot. This + * also slides all inactive pages that were faulted into the cache + * more recently than the activated page towards the tail of the + * inactive list. + * + * Thus: + * + * 1. The sum of evictions and activations between any two points in + * time indicate the minimum number of inactive pages accessed in + * between. + * + * 2. Moving one inactive page N page slots towards the tail of the + * list requires at least N inactive page accesses. + * + * Combining these: + * + * 1. When a page is finally evicted from memory, the number of + * inactive pages accessed while the page was in cache is at least + * the number of page slots on the inactive list. + * + * 2. In addition, measuring the sum of evictions and activations (E) + * at the time of a page's eviction, and comparing it to another + * reading (R) at the time the page faults back into memory tells + * the minimum number of accesses while the page was not cached. + * This is called the refault distance. + * + * Because the first access of the page was the fault and the second + * access the refault, we combine the in-cache distance with the + * out-of-cache distance to get the complete minimum access distance + * of this page: + * + * NR_inactive + (R - E) + * + * And knowing the minimum access distance of a page, we can easily + * tell if the page would be able to stay in cache assuming all page + * slots in the cache were available: + * + * NR_inactive + (R - E) <= NR_inactive + NR_active + * + * which can be further simplified to + * + * (R - E) <= NR_active + * + * Put into words, the refault distance (out-of-cache) can be seen as + * a deficit in inactive list space (in-cache). If the inactive list + * had (R - E) more page slots, the page would not have been evicted + * in between accesses, but activated instead. And on a full system, + * the only thing eating into inactive list space is active pages. + * + * + * Activating refaulting pages + * + * All that is known about the active list is that the pages have been + * accessed more than once in the past. This means that at any given + * time there is actually a good chance that pages on the active list + * are no longer in active use. + * + * So when a refault distance of (R - E) is observed and there are at + * least (R - E) active pages, the refaulting page is activated + * optimistically in the hope that (R - E) active pages are actually + * used less frequently than the refaulting page - or even not used at + * all anymore. + * + * If this is wrong and demotion kicks in, the pages which are truly + * used more frequently will be reactivated while the less frequently + * used once will be evicted from memory. + * + * But if this is right, the stale pages will be pushed out of memory + * and the used pages get to stay in cache. + * + * + * Implementation + * + * For each zone's file LRU lists, a counter for inactive evictions + * and activations is maintained (zone->inactive_age). + * + * On eviction, a snapshot of this counter (along with some bits to + * identify the zone) is stored in the now empty page cache radix tree + * slot of the evicted page. This is called a shadow entry. + * + * On cache misses for which there are shadow entries, an eligible + * refault distance will immediately activate the refaulting page. + */ + +static void *pack_shadow(unsigned long eviction, struct zone *zone) +{ + eviction = (eviction << NODES_SHIFT) | zone_to_nid(zone); + eviction = (eviction << ZONES_SHIFT) | zone_idx(zone); + eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); + + return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); +} + +static void unpack_shadow(void *shadow, + struct zone **zone, + unsigned long *distance) +{ + unsigned long entry = (unsigned long)shadow; + unsigned long eviction; + unsigned long refault; + unsigned long mask; + int zid, nid; + + entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + zid = entry & ((1UL << ZONES_SHIFT) - 1); + entry >>= ZONES_SHIFT; + nid = entry & ((1UL << NODES_SHIFT) - 1); + entry >>= NODES_SHIFT; + eviction = entry; + + *zone = NODE_DATA(nid)->node_zones + zid; + + refault = atomic_long_read(&(*zone)->inactive_age); + mask = ~0UL >> (NODES_SHIFT + ZONES_SHIFT + + RADIX_TREE_EXCEPTIONAL_SHIFT); + /* + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. + * + * There is a special case: usually, shadow entries have a + * short lifetime and are either refaulted or reclaimed along + * with the inode before they get too old. But it is not + * impossible for the inactive_age to lap a shadow entry in + * the field, which can then can result in a false small + * refault distance, leading to a false activation should this + * old entry actually refault again. However, earlier kernels + * used to deactivate unconditionally with *every* reclaim + * invocation for the longest time, so the occasional + * inappropriate activation leading to pressure on the active + * list is not a problem. + */ + *distance = (refault - eviction) & mask; +} + +/** + * workingset_eviction - note the eviction of a page from memory + * @mapping: address space the page was backing + * @page: the page being evicted + * + * Returns a shadow entry to be stored in @mapping->page_tree in place + * of the evicted @page so that a later refault can be detected. + */ +void *workingset_eviction(struct address_space *mapping, struct page *page) +{ + struct zone *zone = page_zone(page); + unsigned long eviction; + + eviction = atomic_long_inc_return(&zone->inactive_age); + return pack_shadow(eviction, zone); +} + +/** + * workingset_refault - evaluate the refault of a previously evicted page + * @shadow: shadow entry of the evicted page + * + * Calculates and evaluates the refault distance of the previously + * evicted page in the context of the zone it was allocated in. + * + * Returns %true if the page should be activated, %false otherwise. + */ +bool workingset_refault(void *shadow) +{ + unsigned long refault_distance; + struct zone *zone; + + unpack_shadow(shadow, &zone, &refault_distance); + inc_zone_state(zone, WORKINGSET_REFAULT); + + if (refault_distance <= zone_page_state(zone, NR_ACTIVE_FILE)) { + inc_zone_state(zone, WORKINGSET_ACTIVATE); + return true; + } + return false; +} + +/** + * workingset_activation - note a page activation + * @page: page that is being activated + */ +void workingset_activation(struct page *page) +{ + atomic_long_inc(&page_zone(page)->inactive_age); +} -- cgit v1.2.3 From 449dd6984d0e47643c04c807f609dd56d48d5bcc Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 3 Apr 2014 14:47:56 -0700 Subject: mm: keep page cache radix tree nodes in check Previously, page cache radix tree nodes were freed after reclaim emptied out their page pointers. But now reclaim stores shadow entries in their place, which are only reclaimed when the inodes themselves are reclaimed. This is problematic for bigger files that are still in use after they have a significant amount of their cache reclaimed, without any of those pages actually refaulting. The shadow entries will just sit there and waste memory. In the worst case, the shadow entries will accumulate until the machine runs out of memory. To get this under control, the VM will track radix tree nodes exclusively containing shadow entries on a per-NUMA node list. Per-NUMA rather than global because we expect the radix tree nodes themselves to be allocated node-locally and we want to reduce cross-node references of otherwise independent cache workloads. A simple shrinker will then reclaim these nodes on memory pressure. A few things need to be stored in the radix tree node to implement the shadow node LRU and allow tree deletions coming from the list: 1. There is no index available that would describe the reverse path from the node up to the tree root, which is needed to perform a deletion. To solve this, encode in each node its offset inside the parent. This can be stored in the unused upper bits of the same member that stores the node's height at no extra space cost. 2. The number of shadow entries needs to be counted in addition to the regular entries, to quickly detect when the node is ready to go to the shadow node LRU list. The current entry count is an unsigned int but the maximum number of entries is 64, so a shadow counter can easily be stored in the unused upper bits. 3. Tree modification needs tree lock and tree root, which are located in the address space, so store an address_space backpointer in the node. The parent pointer of the node is in a union with the 2-word rcu_head, so the backpointer comes at no extra cost as well. 4. The node needs to be linked to an LRU list, which requires a list head inside the node. This does increase the size of the node, but it does not change the number of objects that fit into a slab page. [akpm@linux-foundation.org: export the right function] Signed-off-by: Johannes Weiner Reviewed-by: Rik van Riel Reviewed-by: Minchan Kim Cc: Andrea Arcangeli Cc: Bob Liu Cc: Christoph Hellwig Cc: Dave Chinner Cc: Greg Thelen Cc: Hugh Dickins Cc: Jan Kara Cc: KOSAKI Motohiro Cc: Luigi Semenzato Cc: Mel Gorman Cc: Metin Doslu Cc: Michel Lespinasse Cc: Ozgun Erdogan Cc: Peter Zijlstra Cc: Roman Gushchin Cc: Ryan Mallon Cc: Tejun Heo Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 8 ++- include/linux/mmzone.h | 1 + include/linux/radix-tree.h | 32 ++++++--- include/linux/swap.h | 31 +++++++++ lib/radix-tree.c | 36 ++++++---- mm/filemap.c | 90 ++++++++++++++++++++----- mm/list_lru.c | 16 ++++- mm/truncate.c | 26 +++++++- mm/vmstat.c | 1 + mm/workingset.c | 161 +++++++++++++++++++++++++++++++++++++++++++++ 10 files changed, 359 insertions(+), 43 deletions(-) (limited to 'mm/vmstat.c') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 3ce541753c88..f3434533fbf8 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -13,6 +13,8 @@ /* list_lru_walk_cb has to always return one of those */ enum lru_status { LRU_REMOVED, /* item removed from list */ + LRU_REMOVED_RETRY, /* item removed, but lock has been + dropped and reacquired */ LRU_ROTATE, /* item referenced, give another pass */ LRU_SKIP, /* item cannot be locked, skip */ LRU_RETRY, /* item not freeable. May drop the lock @@ -32,7 +34,11 @@ struct list_lru { }; void list_lru_destroy(struct list_lru *lru); -int list_lru_init(struct list_lru *lru); +int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key); +static inline int list_lru_init(struct list_lru *lru) +{ + return list_lru_init_key(lru, NULL); +} /** * list_lru_add: add an element to the lru list's tail diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index f25db1d74a21..fac5509c18f0 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -144,6 +144,7 @@ enum zone_stat_item { #endif WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_NODERECLAIM, NR_ANON_TRANSPARENT_HUGEPAGES, NR_FREE_CMA_PAGES, NR_VM_ZONE_STAT_ITEMS }; diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 13636c40bc42..33170dbd9db4 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -72,21 +72,37 @@ static inline int radix_tree_is_indirect_ptr(void *ptr) #define RADIX_TREE_TAG_LONGS \ ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG) +#define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) +#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ + RADIX_TREE_MAP_SHIFT)) + +/* Height component in node->path */ +#define RADIX_TREE_HEIGHT_SHIFT (RADIX_TREE_MAX_PATH + 1) +#define RADIX_TREE_HEIGHT_MASK ((1UL << RADIX_TREE_HEIGHT_SHIFT) - 1) + +/* Internally used bits of node->count */ +#define RADIX_TREE_COUNT_SHIFT (RADIX_TREE_MAP_SHIFT + 1) +#define RADIX_TREE_COUNT_MASK ((1UL << RADIX_TREE_COUNT_SHIFT) - 1) + struct radix_tree_node { - unsigned int height; /* Height from the bottom */ + unsigned int path; /* Offset in parent & height from the bottom */ unsigned int count; union { - struct radix_tree_node *parent; /* Used when ascending tree */ - struct rcu_head rcu_head; /* Used when freeing node */ + struct { + /* Used when ascending tree */ + struct radix_tree_node *parent; + /* For tree user */ + void *private_data; + }; + /* Used when freeing node */ + struct rcu_head rcu_head; }; + /* For tree user */ + struct list_head private_list; void __rcu *slots[RADIX_TREE_MAP_SIZE]; unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; }; -#define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) -#define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ - RADIX_TREE_MAP_SHIFT)) - /* root tags are stored in gfp_mask, shifted by __GFP_BITS_SHIFT */ struct radix_tree_root { unsigned int height; @@ -251,7 +267,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void ***slotp); void *radix_tree_lookup(struct radix_tree_root *, unsigned long); void **radix_tree_lookup_slot(struct radix_tree_root *, unsigned long); -bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index, +bool __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node); void *radix_tree_delete_item(struct radix_tree_root *, unsigned long, void *); void *radix_tree_delete(struct radix_tree_root *, unsigned long); diff --git a/include/linux/swap.h b/include/linux/swap.h index b83cf61403ed..350711560753 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -264,6 +264,37 @@ struct swap_list_t { void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); +extern struct list_lru workingset_shadow_nodes; + +static inline unsigned int workingset_node_pages(struct radix_tree_node *node) +{ + return node->count & RADIX_TREE_COUNT_MASK; +} + +static inline void workingset_node_pages_inc(struct radix_tree_node *node) +{ + node->count++; +} + +static inline void workingset_node_pages_dec(struct radix_tree_node *node) +{ + node->count--; +} + +static inline unsigned int workingset_node_shadows(struct radix_tree_node *node) +{ + return node->count >> RADIX_TREE_COUNT_SHIFT; +} + +static inline void workingset_node_shadows_inc(struct radix_tree_node *node) +{ + node->count += 1U << RADIX_TREE_COUNT_SHIFT; +} + +static inline void workingset_node_shadows_dec(struct radix_tree_node *node) +{ + node->count -= 1U << RADIX_TREE_COUNT_SHIFT; +} /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; diff --git a/lib/radix-tree.c b/lib/radix-tree.c index d60be40c111b..9599aa72d7a0 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -342,7 +342,8 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index) /* Increase the height. */ newheight = root->height+1; - node->height = newheight; + BUG_ON(newheight & ~RADIX_TREE_HEIGHT_MASK); + node->path = newheight; node->count = 1; node->parent = NULL; slot = root->rnode; @@ -400,11 +401,12 @@ int __radix_tree_create(struct radix_tree_root *root, unsigned long index, /* Have to add a child node. */ if (!(slot = radix_tree_node_alloc(root))) return -ENOMEM; - slot->height = height; + slot->path = height; slot->parent = node; if (node) { rcu_assign_pointer(node->slots[offset], slot); node->count++; + slot->path |= offset << RADIX_TREE_HEIGHT_SHIFT; } else rcu_assign_pointer(root->rnode, ptr_to_indirect(slot)); } @@ -498,7 +500,7 @@ void *__radix_tree_lookup(struct radix_tree_root *root, unsigned long index, } node = indirect_to_ptr(node); - height = node->height; + height = node->path & RADIX_TREE_HEIGHT_MASK; if (index > radix_tree_maxindex(height)) return NULL; @@ -704,7 +706,7 @@ int radix_tree_tag_get(struct radix_tree_root *root, return (index == 0); node = indirect_to_ptr(node); - height = node->height; + height = node->path & RADIX_TREE_HEIGHT_MASK; if (index > radix_tree_maxindex(height)) return 0; @@ -741,7 +743,7 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, { unsigned shift, tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *rnode, *node; - unsigned long index, offset; + unsigned long index, offset, height; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; @@ -772,7 +774,8 @@ void **radix_tree_next_chunk(struct radix_tree_root *root, return NULL; restart: - shift = (rnode->height - 1) * RADIX_TREE_MAP_SHIFT; + height = rnode->path & RADIX_TREE_HEIGHT_MASK; + shift = (height - 1) * RADIX_TREE_MAP_SHIFT; offset = index >> shift; /* Index outside of the tree */ @@ -1142,7 +1145,7 @@ static unsigned long __locate(struct radix_tree_node *slot, void *item, unsigned int shift, height; unsigned long i; - height = slot->height; + height = slot->path & RADIX_TREE_HEIGHT_MASK; shift = (height-1) * RADIX_TREE_MAP_SHIFT; for ( ; height > 1; height--) { @@ -1205,7 +1208,8 @@ unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item) } node = indirect_to_ptr(node); - max_index = radix_tree_maxindex(node->height); + max_index = radix_tree_maxindex(node->path & + RADIX_TREE_HEIGHT_MASK); if (cur_index > max_index) { rcu_read_unlock(); break; @@ -1301,7 +1305,7 @@ static inline void radix_tree_shrink(struct radix_tree_root *root) * * Returns %true if @node was freed, %false otherwise. */ -bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index, +bool __radix_tree_delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; @@ -1320,9 +1324,10 @@ bool __radix_tree_delete_node(struct radix_tree_root *root, unsigned long index, parent = node->parent; if (parent) { - index >>= RADIX_TREE_MAP_SHIFT; + unsigned int offset; - parent->slots[index & RADIX_TREE_MAP_MASK] = NULL; + offset = node->path >> RADIX_TREE_HEIGHT_SHIFT; + parent->slots[offset] = NULL; parent->count--; } else { root_tag_clear_all(root); @@ -1386,7 +1391,7 @@ void *radix_tree_delete_item(struct radix_tree_root *root, node->slots[offset] = NULL; node->count--; - __radix_tree_delete_node(root, index, node); + __radix_tree_delete_node(root, node); return entry; } @@ -1419,9 +1424,12 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag) EXPORT_SYMBOL(radix_tree_tagged); static void -radix_tree_node_ctor(void *node) +radix_tree_node_ctor(void *arg) { - memset(node, 0, sizeof(struct radix_tree_node)); + struct radix_tree_node *node = arg; + + memset(node, 0, sizeof(*node)); + INIT_LIST_HEAD(&node->private_list); } static __init unsigned long __maxindex(unsigned int height) diff --git a/mm/filemap.c b/mm/filemap.c index a603c4d7d3c9..d6df3bacb0fb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -110,11 +110,17 @@ static void page_cache_tree_delete(struct address_space *mapping, struct page *page, void *shadow) { - if (shadow) { - void **slot; + struct radix_tree_node *node; + unsigned long index; + unsigned int offset; + unsigned int tag; + void **slot; - slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); - radix_tree_replace_slot(slot, shadow); + VM_BUG_ON(!PageLocked(page)); + + __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); + + if (shadow) { mapping->nrshadows++; /* * Make sure the nrshadows update is committed before @@ -123,9 +129,45 @@ static void page_cache_tree_delete(struct address_space *mapping, * same time and miss a shadow entry. */ smp_wmb(); - } else - radix_tree_delete(&mapping->page_tree, page->index); + } mapping->nrpages--; + + if (!node) { + /* Clear direct pointer tags in root node */ + mapping->page_tree.gfp_mask &= __GFP_BITS_MASK; + radix_tree_replace_slot(slot, shadow); + return; + } + + /* Clear tree tags for the removed page */ + index = page->index; + offset = index & RADIX_TREE_MAP_MASK; + for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { + if (test_bit(offset, node->tags[tag])) + radix_tree_tag_clear(&mapping->page_tree, index, tag); + } + + /* Delete page, swap shadow entry */ + radix_tree_replace_slot(slot, shadow); + workingset_node_pages_dec(node); + if (shadow) + workingset_node_shadows_inc(node); + else + if (__radix_tree_delete_node(&mapping->page_tree, node)) + return; + + /* + * Track node that only contains shadow entries. + * + * Avoid acquiring the list_lru lock if already tracked. The + * list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_pages(node) && + list_empty(&node->private_list)) { + node->private_data = mapping; + list_lru_add(&workingset_shadow_nodes, &node->private_list); + } } /* @@ -471,27 +513,43 @@ EXPORT_SYMBOL_GPL(replace_page_cache_page); static int page_cache_tree_insert(struct address_space *mapping, struct page *page, void **shadowp) { + struct radix_tree_node *node; void **slot; int error; - slot = radix_tree_lookup_slot(&mapping->page_tree, page->index); - if (slot) { + error = __radix_tree_create(&mapping->page_tree, page->index, + &node, &slot); + if (error) + return error; + if (*slot) { void *p; p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); if (!radix_tree_exceptional_entry(p)) return -EEXIST; - radix_tree_replace_slot(slot, page); - mapping->nrshadows--; - mapping->nrpages++; if (shadowp) *shadowp = p; - return 0; + mapping->nrshadows--; + if (node) + workingset_node_shadows_dec(node); } - error = radix_tree_insert(&mapping->page_tree, page->index, page); - if (!error) - mapping->nrpages++; - return error; + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + if (node) { + workingset_node_pages_inc(node); + /* + * Don't track node that contains actual pages. + * + * Avoid acquiring the list_lru lock if already + * untracked. The list_empty() test is safe as + * node->private_list is protected by + * mapping->tree_lock. + */ + if (!list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + } + return 0; } static int __add_to_page_cache_locked(struct page *page, diff --git a/mm/list_lru.c b/mm/list_lru.c index 72f9decb0104..f1a0db194173 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -87,11 +87,20 @@ restart: ret = isolate(item, &nlru->lock, cb_arg); switch (ret) { + case LRU_REMOVED_RETRY: + assert_spin_locked(&nlru->lock); case LRU_REMOVED: if (--nlru->nr_items == 0) node_clear(nid, lru->active_nodes); WARN_ON_ONCE(nlru->nr_items < 0); isolated++; + /* + * If the lru lock has been dropped, our list + * traversal is now invalid and so we have to + * restart from scratch. + */ + if (ret == LRU_REMOVED_RETRY) + goto restart; break; case LRU_ROTATE: list_move_tail(item, &nlru->list); @@ -103,6 +112,7 @@ restart: * The lru lock has been dropped, our list traversal is * now invalid and so we have to restart from scratch. */ + assert_spin_locked(&nlru->lock); goto restart; default: BUG(); @@ -114,7 +124,7 @@ restart: } EXPORT_SYMBOL_GPL(list_lru_walk_node); -int list_lru_init(struct list_lru *lru) +int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key) { int i; size_t size = sizeof(*lru->node) * nr_node_ids; @@ -126,12 +136,14 @@ int list_lru_init(struct list_lru *lru) nodes_clear(lru->active_nodes); for (i = 0; i < nr_node_ids; i++) { spin_lock_init(&lru->node[i].lock); + if (key) + lockdep_set_class(&lru->node[i].lock, key); INIT_LIST_HEAD(&lru->node[i].list); lru->node[i].nr_items = 0; } return 0; } -EXPORT_SYMBOL_GPL(list_lru_init); +EXPORT_SYMBOL_GPL(list_lru_init_key); void list_lru_destroy(struct list_lru *lru) { diff --git a/mm/truncate.c b/mm/truncate.c index 0db9258319f0..e5cc39ab0751 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -25,6 +25,9 @@ static void clear_exceptional_entry(struct address_space *mapping, pgoff_t index, void *entry) { + struct radix_tree_node *node; + void **slot; + /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; @@ -35,8 +38,27 @@ static void clear_exceptional_entry(struct address_space *mapping, * without the tree itself locked. These unlocked entries * need verification under the tree lock. */ - if (radix_tree_delete_item(&mapping->page_tree, index, entry) == entry) - mapping->nrshadows--; + if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + radix_tree_replace_slot(slot, NULL); + mapping->nrshadows--; + if (!node) + goto unlock; + workingset_node_shadows_dec(node); + /* + * Don't track node without shadow entries. + * + * Avoid acquiring the list_lru lock if already untracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && + !list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, &node->private_list); + __radix_tree_delete_node(&mapping->page_tree, node); +unlock: spin_unlock_irq(&mapping->tree_lock); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 843125a0e255..f3155d51acfd 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -772,6 +772,7 @@ const char * const vmstat_text[] = { #endif "workingset_refault", "workingset_activate", + "workingset_nodereclaim", "nr_anon_transparent_hugepages", "nr_free_cma", "nr_dirty_threshold", diff --git a/mm/workingset.c b/mm/workingset.c index 8a6c7cff4923..f7216fa7da27 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -251,3 +251,164 @@ void workingset_activation(struct page *page) { atomic_long_inc(&page_zone(page)->inactive_age); } + +/* + * Shadow entries reflect the share of the working set that does not + * fit into memory, so their number depends on the access pattern of + * the workload. In most cases, they will refault or get reclaimed + * along with the inode, but a (malicious) workload that streams + * through files with a total size several times that of available + * memory, while preventing the inodes from being reclaimed, can + * create excessive amounts of shadow nodes. To keep a lid on this, + * track shadow nodes and reclaim them when they grow way past the + * point where they would still be useful. + */ + +struct list_lru workingset_shadow_nodes; + +static unsigned long count_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long shadow_nodes; + unsigned long max_nodes; + unsigned long pages; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid); + local_irq_enable(); + + pages = node_present_pages(sc->nid); + /* + * Active cache pages are limited to 50% of memory, and shadow + * entries that represent a refault distance bigger than that + * do not have any effect. Limit the number of shadow nodes + * such that shadow entries do not exceed the number of active + * cache pages, assuming a worst-case node population density + * of 1/8th on average. + * + * On 64-bit with 7 radix_tree_nodes per page and 64 slots + * each, this will reclaim shadow entries when they consume + * ~2% of available memory: + * + * PAGE_SIZE / radix_tree_nodes / node_entries / PAGE_SIZE + */ + max_nodes = pages >> (1 + RADIX_TREE_MAP_SHIFT - 3); + + if (shadow_nodes <= max_nodes) + return 0; + + return shadow_nodes - max_nodes; +} + +static enum lru_status shadow_lru_isolate(struct list_head *item, + spinlock_t *lru_lock, + void *arg) +{ + struct address_space *mapping; + struct radix_tree_node *node; + unsigned int i; + int ret; + + /* + * Page cache insertions and deletions synchroneously maintain + * the shadow node LRU under the mapping->tree_lock and the + * lru_lock. Because the page cache tree is emptied before + * the inode can be destroyed, holding the lru_lock pins any + * address_space that has radix tree nodes on the LRU. + * + * We can then safely transition to the mapping->tree_lock to + * pin only the address_space of the particular node we want + * to reclaim, take the node off-LRU, and drop the lru_lock. + */ + + node = container_of(item, struct radix_tree_node, private_list); + mapping = node->private_data; + + /* Coming from the list, invert the lock order */ + if (!spin_trylock(&mapping->tree_lock)) { + spin_unlock(lru_lock); + ret = LRU_RETRY; + goto out; + } + + list_del_init(item); + spin_unlock(lru_lock); + + /* + * The nodes should only contain one or more shadow entries, + * no pages, so we expect to be able to remove them all and + * delete and free the empty node afterwards. + */ + + BUG_ON(!node->count); + BUG_ON(node->count & RADIX_TREE_COUNT_MASK); + + for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { + if (node->slots[i]) { + BUG_ON(!radix_tree_exceptional_entry(node->slots[i])); + node->slots[i] = NULL; + BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT)); + node->count -= 1U << RADIX_TREE_COUNT_SHIFT; + BUG_ON(!mapping->nrshadows); + mapping->nrshadows--; + } + } + BUG_ON(node->count); + inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM); + if (!__radix_tree_delete_node(&mapping->page_tree, node)) + BUG(); + + spin_unlock(&mapping->tree_lock); + ret = LRU_REMOVED_RETRY; +out: + local_irq_enable(); + cond_resched(); + local_irq_disable(); + spin_lock(lru_lock); + return ret; +} + +static unsigned long scan_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) +{ + unsigned long ret; + + /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ + local_irq_disable(); + ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid, + shadow_lru_isolate, NULL, &sc->nr_to_scan); + local_irq_enable(); + return ret; +} + +static struct shrinker workingset_shadow_shrinker = { + .count_objects = count_shadow_nodes, + .scan_objects = scan_shadow_nodes, + .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, +}; + +/* + * Our list_lru->lock is IRQ-safe as it nests inside the IRQ-safe + * mapping->tree_lock. + */ +static struct lock_class_key shadow_nodes_key; + +static int __init workingset_init(void) +{ + int ret; + + ret = list_lru_init_key(&workingset_shadow_nodes, &shadow_nodes_key); + if (ret) + goto err; + ret = register_shrinker(&workingset_shadow_shrinker); + if (ret) + goto err_list_lru; + return 0; +err_list_lru: + list_lru_destroy(&workingset_shadow_nodes); +err: + return ret; +} +module_init(workingset_init); -- cgit v1.2.3 From 5509a5d27b971a90b940e148ca9ca53312e4fa7a Mon Sep 17 00:00:00 2001 From: Dave Hansen Date: Thu, 3 Apr 2014 14:48:19 -0700 Subject: drop_caches: add some documentation and info message There is plenty of anecdotal evidence and a load of blog posts suggesting that using "drop_caches" periodically keeps your system running in "tip top shape". Perhaps adding some kernel documentation will increase the amount of accurate data on its use. If we are not shrinking caches effectively, then we have real bugs. Using drop_caches will simply mask the bugs and make them harder to find, but certainly does not fix them, nor is it an appropriate "workaround" to limit the size of the caches. On the contrary, there have been bug reports on issues that turned out to be misguided use of cache dropping. Dropping caches is a very drastic and disruptive operation that is good for debugging and running tests, but if it creates bug reports from production use, kernel developers should be aware of its use. Add a bit more documentation about it, a syslog message to track down abusers, and vmstat drop counters to help analyze problem reports. [akpm@linux-foundation.org: checkpatch fixes] [hannes@cmpxchg.org: add runtime suppression control] Signed-off-by: Dave Hansen Signed-off-by: Michal Hocko Acked-by: KOSAKI Motohiro Acked-by: KAMEZAWA Hiroyuki Signed-off-by: Johannes Weiner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/sysctl/vm.txt | 33 +++++++++++++++++++++++++++------ fs/drop_caches.c | 16 ++++++++++++++-- include/linux/vm_event_item.h | 1 + kernel/sysctl.c | 4 ++-- mm/vmstat.c | 3 +++ 5 files changed, 47 insertions(+), 10 deletions(-) (limited to 'mm/vmstat.c') diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt index d614a9b6a280..dd9d0e33b443 100644 --- a/Documentation/sysctl/vm.txt +++ b/Documentation/sysctl/vm.txt @@ -175,18 +175,39 @@ Setting this to zero disables periodic writeback altogether. drop_caches -Writing to this will cause the kernel to drop clean caches, dentries and -inodes from memory, causing that memory to become free. +Writing to this will cause the kernel to drop clean caches, as well as +reclaimable slab objects like dentries and inodes. Once dropped, their +memory becomes free. To free pagecache: echo 1 > /proc/sys/vm/drop_caches -To free dentries and inodes: +To free reclaimable slab objects (includes dentries and inodes): echo 2 > /proc/sys/vm/drop_caches -To free pagecache, dentries and inodes: +To free slab objects and pagecache: echo 3 > /proc/sys/vm/drop_caches -As this is a non-destructive operation and dirty objects are not freeable, the -user should run `sync' first. +This is a non-destructive operation and will not free any dirty objects. +To increase the number of objects freed by this operation, the user may run +`sync' prior to writing to /proc/sys/vm/drop_caches. This will minimize the +number of dirty objects on the system and create more candidates to be +dropped. + +This file is not a means to control the growth of the various kernel caches +(inodes, dentries, pagecache, etc...) These objects are automatically +reclaimed by the kernel when memory is needed elsewhere on the system. + +Use of this file can cause performance problems. Since it discards cached +objects, it may cost a significant amount of I/O and CPU to recreate the +dropped objects, especially if they were under heavy use. Because of this, +use outside of a testing or debugging environment is not recommended. + +You may see informational messages in your kernel log when this file is +used: + + cat (1234): drop_caches: 3 + +These are informational only. They do not mean that anything is wrong +with your system. To disable them, echo 4 (bit 3) into drop_caches. ============================================================== diff --git a/fs/drop_caches.c b/fs/drop_caches.c index 9fd702f5bfb2..9280202e488c 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -59,10 +59,22 @@ int drop_caches_sysctl_handler(ctl_table *table, int write, if (ret) return ret; if (write) { - if (sysctl_drop_caches & 1) + static int stfu; + + if (sysctl_drop_caches & 1) { iterate_supers(drop_pagecache_sb, NULL); - if (sysctl_drop_caches & 2) + count_vm_event(DROP_PAGECACHE); + } + if (sysctl_drop_caches & 2) { drop_slab(); + count_vm_event(DROP_SLAB); + } + if (!stfu) { + pr_info("%s (%d): drop_caches: %d\n", + current->comm, task_pid_nr(current), + sysctl_drop_caches); + } + stfu |= sysctl_drop_caches & 4; } return 0; } diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 3a712e2e7d76..486c3972c0be 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -37,6 +37,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL, KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY, PAGEOUTRUN, ALLOCSTALL, PGROTATED, + DROP_PAGECACHE, DROP_SLAB, #ifdef CONFIG_NUMA_BALANCING NUMA_PTE_UPDATES, NUMA_HUGE_PTE_UPDATES, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 09d2e2413605..5c14b547882e 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -123,7 +123,7 @@ static int __maybe_unused neg_one = -1; static int zero; static int __maybe_unused one = 1; static int __maybe_unused two = 2; -static int __maybe_unused three = 3; +static int __maybe_unused four = 4; static unsigned long one_ul = 1; static int one_hundred = 100; #ifdef CONFIG_PRINTK @@ -1264,7 +1264,7 @@ static struct ctl_table vm_table[] = { .mode = 0644, .proc_handler = drop_caches_sysctl_handler, .extra1 = &one, - .extra2 = &three, + .extra2 = &four, }, #ifdef CONFIG_COMPACTION { diff --git a/mm/vmstat.c b/mm/vmstat.c index f3155d51acfd..197b4c4a9587 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -813,6 +813,9 @@ const char * const vmstat_text[] = { "pgrotated", + "drop_pagecache", + "drop_slab", + #ifdef CONFIG_NUMA_BALANCING "numa_pte_updates", "numa_huge_pte_updates", -- cgit v1.2.3