Btrfs: avoid taking the trans_mutex in btrfs_end_transaction

I've been working on making our O_DIRECT latency not suck and I noticed we were
taking the trans_mutex in btrfs_end_transaction.  So to do this we convert
num_writers and use_count to atomic_t's and just decrement them in
btrfs_end_transaction.  Instead of deleting the transaction from the trans list
in put_transaction we do that in btrfs_commit_transaction() since that's the
only time it actually needs to be removed from the list.  Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a272bfd..ef6865c 100644 (file)
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3136,7 +3136,7 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
                btrfs_destroy_pinned_extent(root,
                                            root->fs_info->pinned_extents);
 
-               t->use_count = 0;
+               atomic_set(&t->use_count, 0);
                list_del_init(&t->list);
                memset(t, 0, sizeof(*t));
                kmem_cache_free(btrfs_transaction_cachep, t);

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 4583008..c571734 100644 (file)
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -32,10 +32,8 @@
 
 static noinline void put_transaction(struct btrfs_transaction *transaction)
 {
-       WARN_ON(transaction->use_count == 0);
-       transaction->use_count--;
-       if (transaction->use_count == 0) {
-               list_del_init(&transaction->list);
+       WARN_ON(atomic_read(&transaction->use_count) == 0);
+       if (atomic_dec_and_test(&transaction->use_count)) {
                memset(transaction, 0, sizeof(*transaction));
                kmem_cache_free(btrfs_transaction_cachep, transaction);
        }
@@ -60,14 +58,14 @@ static noinline int join_transaction(struct btrfs_root *root)
                if (!cur_trans)
                        return -ENOMEM;
                root->fs_info->generation++;
-               cur_trans->num_writers = 1;
+               atomic_set(&cur_trans->num_writers, 1);
                cur_trans->num_joined = 0;
                cur_trans->transid = root->fs_info->generation;
                init_waitqueue_head(&cur_trans->writer_wait);
                init_waitqueue_head(&cur_trans->commit_wait);
                cur_trans->in_commit = 0;
                cur_trans->blocked = 0;
-               cur_trans->use_count = 1;
+               atomic_set(&cur_trans->use_count, 1);
                cur_trans->commit_done = 0;
                cur_trans->start_time = get_seconds();
 
@@ -88,7 +86,7 @@ static noinline int join_transaction(struct btrfs_root *root)
                root->fs_info->running_transaction = cur_trans;
                spin_unlock(&root->fs_info->new_trans_lock);
        } else {
-               cur_trans->num_writers++;
+               atomic_inc(&cur_trans->num_writers);
                cur_trans->num_joined++;
        }
 
@@ -145,7 +143,7 @@ static void wait_current_trans(struct btrfs_root *root)
        cur_trans = root->fs_info->running_transaction;
        if (cur_trans && cur_trans->blocked) {
                DEFINE_WAIT(wait);
-               cur_trans->use_count++;
+               atomic_inc(&cur_trans->use_count);
                while (1) {
                        prepare_to_wait(&root->fs_info->transaction_wait, &wait,
                                        TASK_UNINTERRUPTIBLE);
@@ -205,7 +203,7 @@ again:
        }
 
        cur_trans = root->fs_info->running_transaction;
-       cur_trans->use_count++;
+       atomic_inc(&cur_trans->use_count);
        if (type != TRANS_JOIN_NOLOCK)
                mutex_unlock(&root->fs_info->trans_mutex);
 
@@ -336,7 +334,7 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
                        goto out_unlock;  /* nothing committing|committed */
        }
 
-       cur_trans->use_count++;
+       atomic_inc(&cur_trans->use_count);
        mutex_unlock(&root->fs_info->trans_mutex);
 
        wait_for_commit(root, cur_trans);
@@ -466,18 +464,14 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
                        wake_up_process(info->transaction_kthread);
        }
 
-       if (lock)
-               mutex_lock(&info->trans_mutex);
        WARN_ON(cur_trans != info->running_transaction);
-       WARN_ON(cur_trans->num_writers < 1);
-       cur_trans->num_writers--;
+       WARN_ON(atomic_read(&cur_trans->num_writers) < 1);
+       atomic_dec(&cur_trans->num_writers);
 
        smp_mb();
        if (waitqueue_active(&cur_trans->writer_wait))
                wake_up(&cur_trans->writer_wait);
        put_transaction(cur_trans);
-       if (lock)
-               mutex_unlock(&info->trans_mutex);
 
        if (current->journal_info == trans)
                current->journal_info = NULL;
@@ -1187,7 +1181,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
        /* take transaction reference */
        mutex_lock(&root->fs_info->trans_mutex);
        cur_trans = trans->transaction;
-       cur_trans->use_count++;
+       atomic_inc(&cur_trans->use_count);
        mutex_unlock(&root->fs_info->trans_mutex);
 
        btrfs_end_transaction(trans, root);
@@ -1246,7 +1240,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
        mutex_lock(&root->fs_info->trans_mutex);
        if (cur_trans->in_commit) {
-               cur_trans->use_count++;
+               atomic_inc(&cur_trans->use_count);
                mutex_unlock(&root->fs_info->trans_mutex);
                btrfs_end_transaction(trans, root);
 
@@ -1268,7 +1262,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                prev_trans = list_entry(cur_trans->list.prev,
                                        struct btrfs_transaction, list);
                if (!prev_trans->commit_done) {
-                       prev_trans->use_count++;
+                       atomic_inc(&prev_trans->use_count);
                        mutex_unlock(&root->fs_info->trans_mutex);
 
                        wait_for_commit(root, prev_trans);
@@ -1309,14 +1303,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                                TASK_UNINTERRUPTIBLE);
 
                smp_mb();
-               if (cur_trans->num_writers > 1)
+               if (atomic_read(&cur_trans->num_writers) > 1)
                        schedule_timeout(MAX_SCHEDULE_TIMEOUT);
                else if (should_grow)
                        schedule_timeout(1);
 
                mutex_lock(&root->fs_info->trans_mutex);
                finish_wait(&cur_trans->writer_wait, &wait);
-       } while (cur_trans->num_writers > 1 ||
+       } while (atomic_read(&cur_trans->num_writers) > 1 ||
                 (should_grow && cur_trans->num_joined != joined));
 
        ret = create_pending_snapshots(trans, root->fs_info);
@@ -1403,6 +1397,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
        wake_up(&cur_trans->commit_wait);
 
+       list_del_init(&cur_trans->list);
        put_transaction(cur_trans);
        put_transaction(cur_trans);
 

diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 229a594..e441acc 100644 (file)
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -27,11 +27,11 @@ struct btrfs_transaction {
         * total writers in this transaction, it must be zero before the
         * transaction can end
         */
-       unsigned long num_writers;
+       atomic_t num_writers;
 
        unsigned long num_joined;
        int in_commit;
-       int use_count;
+       atomic_t use_count;
        int commit_done;
        int blocked;
        struct list_head list;