Btrfs: avoid ENOSPC errors in btrfs_dirty_inode

btrfs_dirty_inode tries to sneak in without much waiting or
space reservation, mostly for performance reasons.  This
usually works well but can cause problems when there are
many many writers.

When btrfs_update_inode fails with ENOSPC, we fallback
to a slower btrfs_start_transaction call that will reserve
some space.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
This commit is contained in:
Chris Mason 2010-05-26 11:02:00 -04:00
parent 3f7c579c41
commit 94b604429a
1 changed files with 11 additions and 3 deletions

View File

@ -4308,10 +4308,18 @@ void btrfs_dirty_inode(struct inode *inode)
btrfs_set_trans_block_group(trans, inode);
ret = btrfs_update_inode(trans, root, inode);
if (ret)
printk(KERN_ERR"btrfs: fail to dirty inode %lu error %d\n",
inode->i_ino, ret);
if (ret && ret == -ENOSPC) {
/* whoops, lets try again with the full transaction */
btrfs_end_transaction(trans, root);
trans = btrfs_start_transaction(root, 1);
btrfs_set_trans_block_group(trans, inode);
ret = btrfs_update_inode(trans, root, inode);
if (ret) {
printk(KERN_ERR"btrfs: fail to dirty inode %lu error %d\n",
inode->i_ino, ret);
}
}
btrfs_end_transaction(trans, root);
}