From patchwork Thu Apr 14 23:32:32 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Waiman Long X-Patchwork-Id: 8843791 Return-Path: X-Original-To: patchwork-linux-fsdevel@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork2.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork2.web.kernel.org (Postfix) with ESMTP id 09D1AC0553 for ; Thu, 14 Apr 2016 23:33:59 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 852DC20270 for ; Thu, 14 Apr 2016 23:33:57 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id D9B4B202EB for ; Thu, 14 Apr 2016 23:33:55 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752948AbcDNXdn (ORCPT ); Thu, 14 Apr 2016 19:33:43 -0400 Received: from g2t4621.austin.hp.com ([15.73.212.80]:41582 "EHLO g2t4621.austin.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752728AbcDNXdf (ORCPT ); Thu, 14 Apr 2016 19:33:35 -0400 Received: from g2t4689.austin.hpicorp.net (g2t4689.austin.hpicorp.net [15.94.10.175]) by g2t4621.austin.hp.com (Postfix) with ESMTP id ACB11C9; Thu, 14 Apr 2016 23:33:33 +0000 (UTC) Received: from RHEL65.localdomain (unknown [16.214.207.13]) by g2t4689.austin.hpicorp.net (Postfix) with ESMTP id 0065435; Thu, 14 Apr 2016 23:33:31 +0000 (UTC) From: Waiman Long To: Alexander Viro , Jan Kara , Jeff Layton , "J. Bruce Fields" , Tejun Heo , Christoph Lameter Cc: linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org, Ingo Molnar , Peter Zijlstra , Andi Kleen , Dave Chinner , Boqun Feng , Scott J Norton , Douglas Hatch , Waiman Long Subject: [PATCH 5/5] vfs: Use dlock list for superblock's inode list Date: Thu, 14 Apr 2016 19:32:32 -0400 Message-Id: <1460676752-57010-6-git-send-email-Waiman.Long@hpe.com> X-Mailer: git-send-email 1.7.1 In-Reply-To: <1460676752-57010-1-git-send-email-Waiman.Long@hpe.com> References: <1460676752-57010-1-git-send-email-Waiman.Long@hpe.com> Sender: linux-fsdevel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-fsdevel@vger.kernel.org X-Spam-Status: No, score=-7.9 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP When many threads are trying to add or delete inode to or from a superblock's s_inodes list, spinlock contention on the list can become a performance bottleneck. This patch changes the s_inodes field to become a dlock list which is a distributed set of lists with per-list spinlocks. As a result, the following superblock inode list (sb->s_inodes) iteration functions in vfs are also being modified: 1. iterate_bdevs() 2. drop_pagecache_sb() 3. wait_sb_inodes() 4. evict_inodes() 5. invalidate_inodes() 6. fsnotify_unmount_inodes() 7. add_dquot_ref() 8. remove_dquot_ref() With an exit microbenchmark that creates a large number of threads, attachs many inodes to them and then exits. The runtimes of that microbenchmark with 1000 threads before and after the patch on a 4-socket Intel E7-4820 v3 system (40 cores, 80 threads) were as follows: Kernel Elapsed Time System Time ------ ------------ ----------- Vanilla 4.5-rc4 65.29s 82m14s Patched 4.5-rc4 22.81s 23m03s Before the patch, spinlock contention at the inode_sb_list_add() function at the startup phase and the inode_sb_list_del() function at the exit phase were about 79% and 93% of total CPU time respectively (as measured by perf). After the patch, the percpu_list_add() function consumed only about 0.04% of CPU time at startup phase. The percpu_list_del() function consumed about 0.4% of CPU time at exit phase. There were still some spinlock contention, but they happened elsewhere. Signed-off-by: Waiman Long Reviewed-by: Jan Kara --- fs/block_dev.c | 13 +++++++------ fs/drop_caches.c | 10 +++++----- fs/fs-writeback.c | 13 +++++++------ fs/inode.c | 36 +++++++++++++++--------------------- fs/notify/inode_mark.c | 10 +++++----- fs/quota/dquot.c | 16 ++++++++-------- fs/super.c | 7 ++++--- include/linux/fs.h | 8 ++++---- 8 files changed, 55 insertions(+), 58 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index 20a2c02..967d746 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1884,11 +1884,13 @@ EXPORT_SYMBOL(__invalidate_device); void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) { struct inode *inode, *old_inode = NULL; + DEFINE_DLOCK_LIST_STATE(state); - spin_lock(&blockdev_superblock->s_inode_list_lock); - list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) { - struct address_space *mapping = inode->i_mapping; + while (dlock_list_iterate(blockdev_superblock->s_inodes, &state)) { + struct address_space *mapping; + inode = list_entry(state.curr, struct inode, i_sb_list); + mapping = inode->i_mapping; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) || mapping->nrpages == 0) { @@ -1897,7 +1899,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) } __iget(inode); spin_unlock(&inode->i_lock); - spin_unlock(&blockdev_superblock->s_inode_list_lock); + spin_unlock(state.lock); /* * We hold a reference to 'inode' so it couldn't have been * removed from s_inodes list while we dropped the @@ -1911,8 +1913,7 @@ void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg) func(I_BDEV(inode), arg); - spin_lock(&blockdev_superblock->s_inode_list_lock); + spin_lock(state.lock); } - spin_unlock(&blockdev_superblock->s_inode_list_lock); iput(old_inode); } diff --git a/fs/drop_caches.c b/fs/drop_caches.c index d72d52b..26b6c68 100644 --- a/fs/drop_caches.c +++ b/fs/drop_caches.c @@ -16,9 +16,10 @@ int sysctl_drop_caches; static void drop_pagecache_sb(struct super_block *sb, void *unused) { struct inode *inode, *toput_inode = NULL; + DEFINE_DLOCK_LIST_STATE(state); - spin_lock(&sb->s_inode_list_lock); - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + while (dlock_list_iterate(sb->s_inodes, &state)) { + inode = list_entry(state.curr, struct inode, i_sb_list); spin_lock(&inode->i_lock); if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || (inode->i_mapping->nrpages == 0)) { @@ -27,15 +28,14 @@ static void drop_pagecache_sb(struct super_block *sb, void *unused) } __iget(inode); spin_unlock(&inode->i_lock); - spin_unlock(&sb->s_inode_list_lock); + spin_unlock(state.lock); invalidate_mapping_pages(inode->i_mapping, 0, -1); iput(toput_inode); toput_inode = inode; - spin_lock(&sb->s_inode_list_lock); + spin_lock(state.lock); } - spin_unlock(&sb->s_inode_list_lock); iput(toput_inode); } diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index 592cea5..3378ea9 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -2154,6 +2154,7 @@ EXPORT_SYMBOL(__mark_inode_dirty); static void wait_sb_inodes(struct super_block *sb) { struct inode *inode, *old_inode = NULL; + DEFINE_DLOCK_LIST_STATE(state); /* * We need to be protected against the filesystem going from @@ -2162,7 +2163,6 @@ static void wait_sb_inodes(struct super_block *sb) WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); - spin_lock(&sb->s_inode_list_lock); /* * Data integrity sync. Must wait for all pages under writeback, @@ -2171,9 +2171,11 @@ static void wait_sb_inodes(struct super_block *sb) * In which case, the inode may not be on the dirty list, but * we still have to wait for that writeout. */ - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { - struct address_space *mapping = inode->i_mapping; + while (dlock_list_iterate(sb->s_inodes, &state)) { + struct address_space *mapping; + inode = list_entry(state.curr, struct inode, i_sb_list); + mapping = inode->i_mapping; spin_lock(&inode->i_lock); if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || (mapping->nrpages == 0)) { @@ -2182,7 +2184,7 @@ static void wait_sb_inodes(struct super_block *sb) } __iget(inode); spin_unlock(&inode->i_lock); - spin_unlock(&sb->s_inode_list_lock); + spin_unlock(state.lock); /* * We hold a reference to 'inode' so it couldn't have been @@ -2204,9 +2206,8 @@ static void wait_sb_inodes(struct super_block *sb) cond_resched(); - spin_lock(&sb->s_inode_list_lock); + spin_lock(state.lock); } - spin_unlock(&sb->s_inode_list_lock); iput(old_inode); mutex_unlock(&sb->s_sync_lock); } diff --git a/fs/inode.c b/fs/inode.c index c9cbea8..9b6084d 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -28,7 +28,7 @@ * inode->i_state, inode->i_hash, __iget() * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru - * inode->i_sb->s_inode_list_lock protects: + * inode->i_sb->s_inodes->lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list @@ -37,7 +37,7 @@ * * Lock ordering: * - * inode->i_sb->s_inode_list_lock + * inode->i_sb->s_inodes->lock * inode->i_lock * Inode LRU list locks * @@ -45,7 +45,7 @@ * inode->i_lock * * inode_hash_lock - * inode->i_sb->s_inode_list_lock + * inode->i_sb->s_inodes->lock * inode->i_lock * * iunique_lock @@ -430,19 +430,14 @@ static void inode_lru_list_del(struct inode *inode) */ void inode_sb_list_add(struct inode *inode) { - spin_lock(&inode->i_sb->s_inode_list_lock); - list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); - spin_unlock(&inode->i_sb->s_inode_list_lock); + dlock_list_add(&inode->i_sb_list, inode->i_sb->s_inodes); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { - if (!list_empty(&inode->i_sb_list)) { - spin_lock(&inode->i_sb->s_inode_list_lock); - list_del_init(&inode->i_sb_list); - spin_unlock(&inode->i_sb->s_inode_list_lock); - } + if (!list_empty(&inode->i_sb_list.list)) + dlock_list_del(&inode->i_sb_list); } static unsigned long hash(struct super_block *sb, unsigned long hashval) @@ -597,11 +592,13 @@ static void dispose_list(struct list_head *head) void evict_inodes(struct super_block *sb) { struct inode *inode; + struct dlock_list_state state; LIST_HEAD(dispose); again: - spin_lock(&sb->s_inode_list_lock); - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + init_dlock_list_state(&state); + while (dlock_list_iterate(sb->s_inodes, &state)) { + inode = list_entry(state.curr, struct inode, i_sb_list); if (atomic_read(&inode->i_count)) continue; @@ -622,13 +619,12 @@ again: * bit so we don't livelock. */ if (need_resched()) { - spin_unlock(&sb->s_inode_list_lock); + spin_unlock(state.lock); cond_resched(); dispose_list(&dispose); goto again; } } - spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } @@ -648,9 +644,10 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) int busy = 0; struct inode *inode; LIST_HEAD(dispose); + DEFINE_DLOCK_LIST_STATE(state); - spin_lock(&sb->s_inode_list_lock); - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + while (dlock_list_iterate(sb->s_inodes, &state)) { + inode = list_entry(state.curr, struct inode, i_sb_list); spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); @@ -672,7 +669,6 @@ int invalidate_inodes(struct super_block *sb, bool kill_dirty) spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); } - spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); @@ -887,7 +883,7 @@ struct inode *new_inode_pseudo(struct super_block *sb) spin_lock(&inode->i_lock); inode->i_state = 0; spin_unlock(&inode->i_lock); - INIT_LIST_HEAD(&inode->i_sb_list); + init_dlock_list_node(&inode->i_sb_list); } return inode; } @@ -908,8 +904,6 @@ struct inode *new_inode(struct super_block *sb) { struct inode *inode; - spin_lock_prefetch(&sb->s_inode_list_lock); - inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index a364524..2639522 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -151,14 +151,15 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, void fsnotify_unmount_inodes(struct super_block *sb) { struct inode *inode, *iput_inode = NULL; + DEFINE_DLOCK_LIST_STATE(state); - spin_lock(&sb->s_inode_list_lock); - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + while (dlock_list_iterate(sb->s_inodes, &state)) { /* * We cannot __iget() an inode in state I_FREEING, * I_WILL_FREE, or I_NEW which is fine because by that point * the inode cannot have any associated watches. */ + inode = list_entry(state.curr, struct inode, i_sb_list); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); @@ -178,7 +179,7 @@ void fsnotify_unmount_inodes(struct super_block *sb) __iget(inode); spin_unlock(&inode->i_lock); - spin_unlock(&sb->s_inode_list_lock); + spin_unlock(state.lock); if (iput_inode) iput(iput_inode); @@ -190,9 +191,8 @@ void fsnotify_unmount_inodes(struct super_block *sb) iput_inode = inode; - spin_lock(&sb->s_inode_list_lock); + spin_lock(state.lock); } - spin_unlock(&sb->s_inode_list_lock); if (iput_inode) iput(iput_inode); diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index ff21980..cb13619 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -936,12 +936,13 @@ static int dqinit_needed(struct inode *inode, int type) static void add_dquot_ref(struct super_block *sb, int type) { struct inode *inode, *old_inode = NULL; + DEFINE_DLOCK_LIST_STATE(state); #ifdef CONFIG_QUOTA_DEBUG int reserved = 0; #endif - spin_lock(&sb->s_inode_list_lock); - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + while (dlock_list_iterate(sb->s_inodes, &state)) { + inode = list_entry(state.curr, struct inode, i_sb_list); spin_lock(&inode->i_lock); if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) || !atomic_read(&inode->i_writecount) || @@ -951,7 +952,7 @@ static void add_dquot_ref(struct super_block *sb, int type) } __iget(inode); spin_unlock(&inode->i_lock); - spin_unlock(&sb->s_inode_list_lock); + spin_unlock(state.lock); #ifdef CONFIG_QUOTA_DEBUG if (unlikely(inode_get_rsv_space(inode) > 0)) @@ -969,9 +970,8 @@ static void add_dquot_ref(struct super_block *sb, int type) * later. */ old_inode = inode; - spin_lock(&sb->s_inode_list_lock); + spin_lock(state.lock); } - spin_unlock(&sb->s_inode_list_lock); iput(old_inode); #ifdef CONFIG_QUOTA_DEBUG @@ -1039,15 +1039,16 @@ static void remove_dquot_ref(struct super_block *sb, int type, { struct inode *inode; int reserved = 0; + DEFINE_DLOCK_LIST_STATE(state); - spin_lock(&sb->s_inode_list_lock); - list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { + while (dlock_list_iterate(sb->s_inodes, &state)) { /* * We have to scan also I_NEW inodes because they can already * have quota pointer initialized. Luckily, we need to touch * only quota pointers and these have separate locking * (dq_data_lock). */ + inode = list_entry(state.curr, struct inode, i_sb_list); spin_lock(&dq_data_lock); if (!IS_NOQUOTA(inode)) { if (unlikely(inode_get_rsv_space(inode) > 0)) @@ -1056,7 +1057,6 @@ static void remove_dquot_ref(struct super_block *sb, int type, } spin_unlock(&dq_data_lock); } - spin_unlock(&sb->s_inode_list_lock); #ifdef CONFIG_QUOTA_DEBUG if (reserved) { printk(KERN_WARNING "VFS (%s): Writes happened after quota" diff --git a/fs/super.c b/fs/super.c index 74914b1..6c167d3 100644 --- a/fs/super.c +++ b/fs/super.c @@ -163,6 +163,7 @@ static void destroy_super(struct super_block *s) { list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); + free_dlock_list_head(&s->s_inodes); security_sb_free(s); WARN_ON(!list_empty(&s->s_mounts)); kfree(s->s_subtype); @@ -204,9 +205,9 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags) INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_anon); mutex_init(&s->s_sync_lock); - INIT_LIST_HEAD(&s->s_inodes); - spin_lock_init(&s->s_inode_list_lock); + if (init_dlock_list_head(&s->s_inodes)) + goto fail; if (list_lru_init_memcg(&s->s_dentry_lru)) goto fail; if (list_lru_init_memcg(&s->s_inode_lru)) @@ -427,7 +428,7 @@ void generic_shutdown_super(struct super_block *sb) if (sop->put_super) sop->put_super(sb); - if (!list_empty(&sb->s_inodes)) { + if (!dlock_list_empty(sb->s_inodes)) { printk("VFS: Busy inodes after unmount of %s. " "Self-destruct in 5 seconds. Have a nice day...\n", sb->s_id); diff --git a/include/linux/fs.h b/include/linux/fs.h index 70e61b5..d22b213 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -32,6 +32,7 @@ #include #include #include +#include #include #include @@ -651,7 +652,7 @@ struct inode { u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ - struct list_head i_sb_list; + struct dlock_list_node i_sb_list; union { struct hlist_head i_dentry; struct rcu_head i_rcu; @@ -1416,9 +1417,8 @@ struct super_block { */ int s_stack_depth; - /* s_inode_list_lock protects s_inodes */ - spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; - struct list_head s_inodes; /* all inodes */ + /* The percpu locks protect s_inodes */ + struct dlock_list_head __percpu *s_inodes; /* all inodes */ }; extern struct timespec current_fs_time(struct super_block *sb);