Btrfs: process the delayed reference queue in clusters

The delayed reference queue maintains pending operations that need to
be done to the extent allocation tree.  These are processed by
finding records in the tree that are not currently being processed one at
a time.

This is slow because it uses lots of time searching through the rbtree
and because it creates lock contention on the extent allocation tree
when lots of different procs are running delayed refs at the same time.

This commit changes things to grab a cluster of refs for processing,
using a cursor into the rbtree as the starting point of the next search.
This way we walk smoothly through the rbtree.

Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 17 insertions, 8 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index f94c2ad8996c..903edab3659a 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -68,7 +68,10 @@ static noinline int join_transaction(struct btrfs_root *root)
 
                 cur_trans->delayed_refs.root.rb_node = NULL;
                 cur_trans->delayed_refs.num_entries = 0;
+                cur_trans->delayed_refs.num_heads_ready = 0;
+                cur_trans->delayed_refs.num_heads = 0;
                 cur_trans->delayed_refs.flushing = 0;
+                cur_trans->delayed_refs.run_delayed_start = 0;
                 spin_lock_init(&cur_trans->delayed_refs.lock);
 
                 INIT_LIST_HEAD(&cur_trans->pending_snapshots);
@@ -287,13 +290,19 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
         struct btrfs_transaction *cur_trans;
         struct btrfs_fs_info *info = root->fs_info;
-
-        if (trans->delayed_ref_updates &&
-            (trans->transaction->delayed_refs.flushing ||
-            trans->transaction->delayed_refs.num_entries > 16384)) {
-                btrfs_run_delayed_refs(trans, root, trans->delayed_ref_updates);
-        } else if (trans->transaction->delayed_refs.num_entries > 64) {
-                wake_up_process(root->fs_info->transaction_kthread);
+        int count = 0;
+
+        while (count < 4) {
+                unsigned long cur = trans->delayed_ref_updates;
+                trans->delayed_ref_updates = 0;
+                if (cur &&
+                    trans->transaction->delayed_refs.num_heads_ready > 64) {
+                        trans->delayed_ref_updates = 0;
+                        btrfs_run_delayed_refs(trans, root, cur);
+                } else {
+                        break;
+                }
+                count++;
         }
 
         mutex_lock(&info->trans_mutex);
@@ -929,7 +938,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
          */
         trans->transaction->delayed_refs.flushing = 1;
 
-        ret = btrfs_run_delayed_refs(trans, root, (u64)-1);
+        ret = btrfs_run_delayed_refs(trans, root, 0);
         BUG_ON(ret);
 
         INIT_LIST_HEAD(&dirty_fs_roots);