Subject: + memcg-get-rid-of-soft-limit-tree-infrastructure.patch added to -mm tree To: mhocko@xxxxxxx,bsingharora@xxxxxxxxx,glommer@xxxxxxxxxx,gthelen@xxxxxxxxxx,hannes@xxxxxxxxxxx,hughd@xxxxxxxxxx,kamezawa.hiroyu@xxxxxxxxxxxxxx,kosaki.motohiro@xxxxxxxxxxxxxx,tj@xxxxxxxxxx,walken@xxxxxxxxxx,yinghan@xxxxxxxxxx From: akpm@xxxxxxxxxxxxxxxxxxxx Date: Tue, 30 Jul 2013 15:33:54 -0700 The patch titled Subject: memcg: get rid of soft-limit tree infrastructure has been added to the -mm tree. Its filename is memcg-get-rid-of-soft-limit-tree-infrastructure.patch This patch should soon appear at http://ozlabs.org/~akpm/mmots/broken-out/memcg-get-rid-of-soft-limit-tree-infrastructure.patch and later at http://ozlabs.org/~akpm/mmotm/broken-out/memcg-get-rid-of-soft-limit-tree-infrastructure.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** The -mm tree is included into linux-next and is updated there every 3-4 working days ------------------------------------------------------ From: Michal Hocko <mhocko@xxxxxxx> Subject: memcg: get rid of soft-limit tree infrastructure Now that the soft limit is integrated to the reclaim directly the whole soft-limit tree infrastructure is not needed anymore. Rip it out. Signed-off-by: Michal Hocko <mhocko@xxxxxxx> Reviewed-by: Glauber Costa <glommer@xxxxxxxxxx> Reviewed-by: Tejun Heo <tj@xxxxxxxxxx> Cc: Balbir Singh <bsingharora@xxxxxxxxx> Cc: Greg Thelen <gthelen@xxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Johannes Weiner <hannes@xxxxxxxxxxx> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@xxxxxxxxxxxxxx> Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> Cc: Michel Lespinasse <walken@xxxxxxxxxx> Cc: Ying Han <yinghan@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/memcontrol.c | 265 ---------------------------------------------- 1 file changed, 2 insertions(+), 263 deletions(-) diff -puN mm/memcontrol.c~memcg-get-rid-of-soft-limit-tree-infrastructure mm/memcontrol.c --- a/mm/memcontrol.c~memcg-get-rid-of-soft-limit-tree-infrastructure +++ a/mm/memcontrol.c @@ -39,7 +39,6 @@ #include <linux/limits.h> #include <linux/export.h> #include <linux/mutex.h> -#include <linux/rbtree.h> #include <linux/slab.h> #include <linux/swap.h> #include <linux/swapops.h> @@ -139,7 +138,6 @@ static const char * const mem_cgroup_lru */ enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, - MEM_CGROUP_TARGET_SOFTLIMIT, MEM_CGROUP_TARGET_NUMAINFO, MEM_CGROUP_NTARGETS, }; @@ -175,10 +173,6 @@ struct mem_cgroup_per_zone { struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1]; - struct rb_node tree_node; /* RB tree node */ - unsigned long long usage_in_excess;/* Set to the value by which */ - /* the soft limit is exceeded*/ - bool on_tree; struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; @@ -187,26 +181,6 @@ struct mem_cgroup_per_node { struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; }; -/* - * Cgroups above their limits are maintained in a RB-Tree, independent of - * their hierarchy representation - */ - -struct mem_cgroup_tree_per_zone { - struct rb_root rb_root; - spinlock_t lock; -}; - -struct mem_cgroup_tree_per_node { - struct mem_cgroup_tree_per_zone rb_tree_per_zone[MAX_NR_ZONES]; -}; - -struct mem_cgroup_tree { - struct mem_cgroup_tree_per_node *rb_tree_per_node[MAX_NUMNODES]; -}; - -static struct mem_cgroup_tree soft_limit_tree __read_mostly; - struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; u64 threshold; @@ -444,7 +418,6 @@ static bool move_file(void) * limit reclaim to prevent infinite loops, if they ever occur. */ #define MEM_CGROUP_MAX_RECLAIM_LOOPS 100 -#define MEM_CGROUP_MAX_SOFT_LIMIT_RECLAIM_LOOPS 2 enum charge_type { MEM_CGROUP_CHARGE_TYPE_CACHE = 0, @@ -672,164 +645,6 @@ page_cgroup_zoneinfo(struct mem_cgroup * return mem_cgroup_zoneinfo(memcg, nid, zid); } -static struct mem_cgroup_tree_per_zone * -soft_limit_tree_node_zone(int nid, int zid) -{ - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; -} - -static struct mem_cgroup_tree_per_zone * -soft_limit_tree_from_page(struct page *page) -{ - int nid = page_to_nid(page); - int zid = page_zonenum(page); - - return &soft_limit_tree.rb_tree_per_node[nid]->rb_tree_per_zone[zid]; -} - -static void -__mem_cgroup_insert_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz, - unsigned long long new_usage_in_excess) -{ - struct rb_node **p = &mctz->rb_root.rb_node; - struct rb_node *parent = NULL; - struct mem_cgroup_per_zone *mz_node; - - if (mz->on_tree) - return; - - mz->usage_in_excess = new_usage_in_excess; - if (!mz->usage_in_excess) - return; - while (*p) { - parent = *p; - mz_node = rb_entry(parent, struct mem_cgroup_per_zone, - tree_node); - if (mz->usage_in_excess < mz_node->usage_in_excess) - p = &(*p)->rb_left; - /* - * We can't avoid mem cgroups that are over their soft - * limit by the same amount - */ - else if (mz->usage_in_excess >= mz_node->usage_in_excess) - p = &(*p)->rb_right; - } - rb_link_node(&mz->tree_node, parent, p); - rb_insert_color(&mz->tree_node, &mctz->rb_root); - mz->on_tree = true; -} - -static void -__mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) -{ - if (!mz->on_tree) - return; - rb_erase(&mz->tree_node, &mctz->rb_root); - mz->on_tree = false; -} - -static void -mem_cgroup_remove_exceeded(struct mem_cgroup *memcg, - struct mem_cgroup_per_zone *mz, - struct mem_cgroup_tree_per_zone *mctz) -{ - spin_lock(&mctz->lock); - __mem_cgroup_remove_exceeded(memcg, mz, mctz); - spin_unlock(&mctz->lock); -} - - -static void mem_cgroup_update_tree(struct mem_cgroup *memcg, struct page *page) -{ - unsigned long long excess; - struct mem_cgroup_per_zone *mz; - struct mem_cgroup_tree_per_zone *mctz; - int nid = page_to_nid(page); - int zid = page_zonenum(page); - mctz = soft_limit_tree_from_page(page); - - /* - * Necessary to update all ancestors when hierarchy is used. - * because their event counter is not touched. - */ - for (; memcg; memcg = parent_mem_cgroup(memcg)) { - mz = mem_cgroup_zoneinfo(memcg, nid, zid); - excess = res_counter_soft_limit_excess(&memcg->res); - /* - * We have to update the tree if mz is on RB-tree or - * mem is over its softlimit. - */ - if (excess || mz->on_tree) { - spin_lock(&mctz->lock); - /* if on-tree, remove it */ - if (mz->on_tree) - __mem_cgroup_remove_exceeded(memcg, mz, mctz); - /* - * Insert again. mz->usage_in_excess will be updated. - * If excess is 0, no tree ops. - */ - __mem_cgroup_insert_exceeded(memcg, mz, mctz, excess); - spin_unlock(&mctz->lock); - } - } -} - -static void mem_cgroup_remove_from_trees(struct mem_cgroup *memcg) -{ - int node, zone; - struct mem_cgroup_per_zone *mz; - struct mem_cgroup_tree_per_zone *mctz; - - for_each_node(node) { - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - mz = mem_cgroup_zoneinfo(memcg, node, zone); - mctz = soft_limit_tree_node_zone(node, zone); - mem_cgroup_remove_exceeded(memcg, mz, mctz); - } - } -} - -static struct mem_cgroup_per_zone * -__mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) -{ - struct rb_node *rightmost = NULL; - struct mem_cgroup_per_zone *mz; - -retry: - mz = NULL; - rightmost = rb_last(&mctz->rb_root); - if (!rightmost) - goto done; /* Nothing to reclaim from */ - - mz = rb_entry(rightmost, struct mem_cgroup_per_zone, tree_node); - /* - * Remove the node now but someone else can add it back, - * we will to add it back at the end of reclaim to its correct - * position in the tree. - */ - __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); - if (!res_counter_soft_limit_excess(&mz->memcg->res) || - !css_tryget(&mz->memcg->css)) - goto retry; -done: - return mz; -} - -static struct mem_cgroup_per_zone * -mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz) -{ - struct mem_cgroup_per_zone *mz; - - spin_lock(&mctz->lock); - mz = __mem_cgroup_largest_soft_limit_node(mctz); - spin_unlock(&mctz->lock); - return mz; -} - /* * Implementation Note: reading percpu statistics for memcg. * @@ -988,9 +803,6 @@ static bool mem_cgroup_event_ratelimit(s case MEM_CGROUP_TARGET_THRESH: next = val + THRESHOLDS_EVENTS_TARGET; break; - case MEM_CGROUP_TARGET_SOFTLIMIT: - next = val + SOFTLIMIT_EVENTS_TARGET; - break; case MEM_CGROUP_TARGET_NUMAINFO: next = val + NUMAINFO_EVENTS_TARGET; break; @@ -1013,11 +825,8 @@ static void memcg_check_events(struct me /* threshold event is triggered in finer grain than soft limit */ if (unlikely(mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_THRESH))) { - bool do_softlimit; bool do_numainfo __maybe_unused; - do_softlimit = mem_cgroup_event_ratelimit(memcg, - MEM_CGROUP_TARGET_SOFTLIMIT); #if MAX_NUMNODES > 1 do_numainfo = mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_NUMAINFO); @@ -1025,8 +834,6 @@ static void memcg_check_events(struct me preempt_enable(); mem_cgroup_threshold(memcg); - if (unlikely(do_softlimit)) - mem_cgroup_update_tree(memcg, page); #if MAX_NUMNODES > 1 if (unlikely(do_numainfo)) atomic_inc(&memcg->numainfo_events); @@ -1886,6 +1693,7 @@ static unsigned long mem_cgroup_reclaim( return total; } +#if MAX_NUMNODES > 1 /** * test_mem_cgroup_node_reclaimable * @memcg: the target memcg @@ -1908,7 +1716,6 @@ static bool test_mem_cgroup_node_reclaim return false; } -#if MAX_NUMNODES > 1 /* * Always updating the nodemask is not very good - even if we have an empty @@ -1976,51 +1783,12 @@ int mem_cgroup_select_victim_node(struct return node; } -/* - * Check all nodes whether it contains reclaimable pages or not. - * For quick scan, we make use of scan_nodes. This will allow us to skip - * unused nodes. But scan_nodes is lazily updated and may not cotain - * enough new information. We need to do double check. - */ -static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) -{ - int nid; - - /* - * quick check...making use of scan_node. - * We can skip unused nodes. - */ - if (!nodes_empty(memcg->scan_nodes)) { - for (nid = first_node(memcg->scan_nodes); - nid < MAX_NUMNODES; - nid = next_node(nid, memcg->scan_nodes)) { - - if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) - return true; - } - } - /* - * Check rest of nodes. - */ - for_each_node_state(nid, N_MEMORY) { - if (node_isset(nid, memcg->scan_nodes)) - continue; - if (test_mem_cgroup_node_reclaimable(memcg, nid, noswap)) - return true; - } - return false; -} - #else int mem_cgroup_select_victim_node(struct mem_cgroup *memcg) { return 0; } -static bool mem_cgroup_reclaimable(struct mem_cgroup *memcg, bool noswap) -{ - return test_mem_cgroup_node_reclaimable(memcg, 0, noswap); -} #endif /* @@ -2895,9 +2663,7 @@ static void __mem_cgroup_commit_charge(s unlock_page_cgroup(pc); /* - * "charge_statistics" updated event counter. Then, check it. - * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. - * if they exceeds softlimit. + * "charge_statistics" updated event counter. */ memcg_check_events(memcg, page); } @@ -5984,8 +5750,6 @@ static int alloc_mem_cgroup_per_zone_inf for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; lruvec_init(&mz->lruvec); - mz->usage_in_excess = 0; - mz->on_tree = false; mz->memcg = memcg; } memcg->nodeinfo[node] = pn; @@ -6041,7 +5805,6 @@ static void __mem_cgroup_free(struct mem int node; size_t size = memcg_size(); - mem_cgroup_remove_from_trees(memcg); free_css_id(&mem_cgroup_subsys, &memcg->css); for_each_node(node) @@ -6078,29 +5841,6 @@ struct mem_cgroup *parent_mem_cgroup(str } EXPORT_SYMBOL(parent_mem_cgroup); -static void __init mem_cgroup_soft_limit_tree_init(void) -{ - struct mem_cgroup_tree_per_node *rtpn; - struct mem_cgroup_tree_per_zone *rtpz; - int tmp, node, zone; - - for_each_node(node) { - tmp = node; - if (!node_state(node, N_NORMAL_MEMORY)) - tmp = -1; - rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); - BUG_ON(!rtpn); - - soft_limit_tree.rb_tree_per_node[node] = rtpn; - - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - rtpz = &rtpn->rb_tree_per_zone[zone]; - rtpz->rb_root = RB_ROOT; - spin_lock_init(&rtpz->lock); - } - } -} - static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup *cont) { @@ -6883,7 +6623,6 @@ static int __init mem_cgroup_init(void) { hotcpu_notifier(memcg_cpu_hotplug_callback, 0); enable_swap_cgroup(); - mem_cgroup_soft_limit_tree_init(); memcg_stock_init(); return 0; } _ Patches currently in -mm which might be from mhocko@xxxxxxx are vmpressure-change-vmpressure-sr_lock-to-spinlock.patch vmpressure-do-not-check-for-pending-work-to-prevent-from-new-work.patch vmpressure-make-sure-there-are-no-events-queued-after-memcg-is-offlined.patch vmpressure-make-sure-there-are-no-events-queued-after-memcg-is-offlined-checkpatch-fixes.patch include-linux-schedh-dont-use-task-pid-tgid-in-same_thread_group-has_group_leader_pid.patch watchdog-update-watchdog-attributes-atomically.patch watchdog-update-watchdog_tresh-properly.patch mm-fix-potential-null-pointer-dereference.patch mm-hugetlb-move-up-the-code-which-check-availability-of-free-huge-page.patch mm-hugetlb-trivial-commenting-fix.patch mm-hugetlb-clean-up-alloc_huge_page.patch mm-hugetlb-fix-and-clean-up-node-iteration-code-to-alloc-or-free.patch mm-hugetlb-remove-redundant-list_empty-check-in-gather_surplus_pages.patch mm-hugetlb-do-not-use-a-page-in-page-cache-for-cow-optimization.patch mm-hugetlb-add-vm_noreserve-check-in-vma_has_reserves.patch mm-hugetlb-remove-decrement_hugepage_resv_vma.patch mm-hugetlb-decrement-reserve-count-if-vm_noreserve-alloc-page-cache.patch memcg-remove-redundant-code-in-mem_cgroup_force_empty_write.patch memcg-vmscan-integrate-soft-reclaim-tighter-with-zone-shrinking-code.patch memcg-get-rid-of-soft-limit-tree-infrastructure.patch vmscan-memcg-do-softlimit-reclaim-also-for-targeted-reclaim.patch memcg-enhance-memcg-iterator-to-support-predicates.patch memcg-track-children-in-soft-limit-excess-to-improve-soft-limit.patch memcg-vmscan-do-not-attempt-soft-limit-reclaim-if-it-would-not-scan-anything.patch memcg-track-all-children-over-limit-in-the-root.patch memcg-vmscan-do-not-fall-into-reclaim-all-pass-too-quickly.patch memcg-trivial-cleanups.patch linux-next.patch inode-convert-inode-lru-list-to-generic-lru-list-code-inode-move-inode-to-a-different-list-inside-lock.patch list_lru-per-node-list-infrastructure-fix-broken-lru_retry-behaviour.patch list_lru-remove-special-case-function-list_lru_dispose_all.patch xfs-convert-dquot-cache-lru-to-list_lru-fix-dquot-isolation-hang.patch list_lru-dynamically-adjust-node-arrays-super-fix-for-destroy-lrus.patch staging-lustre-ldlm-convert-to-shrinkers-to-count-scan-api.patch staging-lustre-obdclass-convert-lu_object-shrinker-to-count-scan-api.patch staging-lustre-ptlrpc-convert-to-new-shrinker-api.patch staging-lustre-libcfs-cleanup-linux-memh.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