sync: serialise per-superblock sync operations

When competing sync(2) calls walk the same filesystem, they need to
walk the list of inodes on the superblock to find all the inodes
that we need to wait for IO completion on. However, when multiple
wait_sb_inodes() calls do this at the same time, they contend on the
the inode_sb_list_lock and the contention causes system wide
slowdowns. In effect, concurrent sync(2) calls can take longer and
burn more CPU than if they were serialised.

Stop the worst of the contention by adding a per-sb mutex to wrap
around wait_sb_inodes() so that we only execute one sync(2) IO
completion walk per superblock superblock at a time and hence avoid
contention being triggered by concurrent sync(2) calls.

Signed-off-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Dave Chinner <dchinner@redhat.com>

diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index f45bf876579f39a0db10a154da1dd428c28a1cf5..3c974442bdf0edb2f7614c6ec2869d03e26a2193 100644 (file)
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -2114,6 +2114,15 @@ out_unlock_inode:
 }
 EXPORT_SYMBOL(__mark_inode_dirty);
 
+/*
+ * The @s_sync_lock is used to serialise concurrent sync operations
+ * to avoid lock contention problems with concurrent wait_sb_inodes() calls.
+ * Concurrent callers will block on the s_sync_lock rather than doing contending
+ * walks. The queueing maintains sync(2) required behaviour as all the IO that
+ * has been issued up to the time this function is enter is guaranteed to be
+ * completed by the time we have gained the lock and waited for all IO that is
+ * in progress regardless of the order callers are granted the lock.
+ */
 static void wait_sb_inodes(struct super_block *sb)
 {
        struct inode *inode, *old_inode = NULL;
@@ -2124,6 +2133,7 @@ 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);
 
        /*
@@ -2165,6 +2175,7 @@ static void wait_sb_inodes(struct super_block *sb)
        }
        spin_unlock(&sb->s_inode_list_lock);
        iput(old_inode);
+       mutex_unlock(&sb->s_sync_lock);
 }
 
 static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,

diff --git a/fs/super.c b/fs/super.c
index c808183554a22b16fbdce88293c4ffa9b2f03933..fd427ec0b372df1231b2a4b017d2ffe59a7284ea 100644 (file)
--- a/fs/super.c
+++ b/fs/super.c
@@ -190,6 +190,7 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
        s->s_flags = 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);
 

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 09bbd38485f98759c316330b143a9760c8faadfb..82dfc5519b4b5f3245f5ac0b946fe270ca38ac6c 100644 (file)
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1375,6 +1375,8 @@ struct super_block {
        struct list_lru         s_inode_lru ____cacheline_aligned_in_smp;
        struct rcu_head         rcu;
 
+       struct mutex            s_sync_lock;    /* sync serialisation lock */
+
        /*
         * Indicates how deep in a filesystem stack this SB is
         */