btrfs: run delayed iput at unlink time

We have been seeing issues in production where a cleaner script will end
up unlinking a bunch of files that have pending iputs.  This means they
will get their final iput's run at btrfs-cleaner time and thus are not
throttled, which impacts the workload.

Since we are unlinking these files we can just drop the delayed iput at
unlink time.  We are already holding a reference to the inode so this
will not be the final iput and thus is completely safe to do at this
point.  Doing this means we are more likely to be doing the final iput
at unlink time, and thus will get the IO charged to the caller and get
throttled appropriately without affecting the main workload.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 89b9535cda19c056d8089e1bdd0bcda65540f661..525790a38f6d3ec2314bf6bb43b038c4fc444680 100644 (file)
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3295,6 +3295,28 @@ void btrfs_add_delayed_iput(struct inode *inode)
                wake_up_process(fs_info->cleaner_kthread);
 }
 
+static void run_delayed_iput_locked(struct btrfs_fs_info *fs_info,
+                                   struct btrfs_inode *inode)
+{
+       list_del_init(&inode->delayed_iput);
+       spin_unlock(&fs_info->delayed_iput_lock);
+       iput(&inode->vfs_inode);
+       if (atomic_dec_and_test(&fs_info->nr_delayed_iputs))
+               wake_up(&fs_info->delayed_iputs_wait);
+       spin_lock(&fs_info->delayed_iput_lock);
+}
+
+static void btrfs_run_delayed_iput(struct btrfs_fs_info *fs_info,
+                                  struct btrfs_inode *inode)
+{
+       if (!list_empty(&inode->delayed_iput)) {
+               spin_lock(&fs_info->delayed_iput_lock);
+               if (!list_empty(&inode->delayed_iput))
+                       run_delayed_iput_locked(fs_info, inode);
+               spin_unlock(&fs_info->delayed_iput_lock);
+       }
+}
+
 void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
 {
 
@@ -3304,12 +3326,7 @@ void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
 
                inode = list_first_entry(&fs_info->delayed_iputs,
                                struct btrfs_inode, delayed_iput);
-               list_del_init(&inode->delayed_iput);
-               spin_unlock(&fs_info->delayed_iput_lock);
-               iput(&inode->vfs_inode);
-               if (atomic_dec_and_test(&fs_info->nr_delayed_iputs))
-                       wake_up(&fs_info->delayed_iputs_wait);
-               spin_lock(&fs_info->delayed_iput_lock);
+               run_delayed_iput_locked(fs_info, inode);
        }
        spin_unlock(&fs_info->delayed_iput_lock);
 }
@@ -4014,6 +4031,17 @@ skip_backref:
                ret = 0;
        else if (ret)
                btrfs_abort_transaction(trans, ret);
+
+       /*
+        * If we have a pending delayed iput we could end up with the final iput
+        * being run in btrfs-cleaner context.  If we have enough of these built
+        * up we can end up burning a lot of time in btrfs-cleaner without any
+        * way to throttle the unlinks.  Since we're currently holding a ref on
+        * the inode we can run the delayed iput here without any issues as the
+        * final iput won't be done until after we drop the ref we're currently
+        * holding.
+        */
+       btrfs_run_delayed_iput(fs_info, inode);
 err:
        btrfs_free_path(path);
        if (ret)