Browse Source

ceph: wake up writer if vmtruncate work get blocked

To write data, the writer first acquires the i_mutex, then try getting
caps. The writer may sleep while holding the i_mutex. If the MDS revokes
Fb cap in this case, vmtruncate work can't do its job because i_mutex
is locked. We should wake up the writer and let it truncate the pages.

Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Yan, Zheng 12 years ago
parent
commit
85ce127a9a
1 changed files with 8 additions and 1 deletions
  1. 8 1
      fs/ceph/inode.c

+ 8 - 1
fs/ceph/inode.c

@@ -1465,7 +1465,14 @@ static void ceph_vmtruncate_work(struct work_struct *work)
 	struct inode *inode = &ci->vfs_inode;
 
 	dout("vmtruncate_work %p\n", inode);
-	mutex_lock(&inode->i_mutex);
+	if (!mutex_trylock(&inode->i_mutex)) {
+		/*
+		 * the i_mutex can be hold by a writer who is waiting for
+		 * caps. wake up waiters, they will do pending vmtruncate.
+		 */
+		wake_up_all(&ci->i_cap_wq);
+		mutex_lock(&inode->i_mutex);
+	}
 	__ceph_do_pending_vmtruncate(inode);
 	mutex_unlock(&inode->i_mutex);
 	iput(inode);