1 files changed, 20 insertions, 3 deletions

diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 295d56454e8b..0a42ae96dca7 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1544,9 +1544,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
         /* we need to run complete recovery for offline orphan slots */
         ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
 
-        mlog(ML_NOTICE, "Recovering node %d from slot %d on device (%u,%u)\n",
-             node_num, slot_num,
-             MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
+        printk(KERN_NOTICE "ocfs2: Begin replay journal (node %d, slot %d) on "\
+               "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev),
+               MINOR(osb->sb->s_dev));
 
         OCFS2_I(inode)->ip_clusters = le32_to_cpu(fe->i_clusters);
 
@@ -1601,6 +1601,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
 
         jbd2_journal_destroy(journal);
 
+        printk(KERN_NOTICE "ocfs2: End replay journal (node %d, slot %d) on "\
+               "device (%u,%u)\n", node_num, slot_num, MAJOR(osb->sb->s_dev),
+               MINOR(osb->sb->s_dev));
 done:
         /* drop the lock on this nodes journal */
         if (got_lock)
@@ -1808,6 +1811,20 @@ static inline unsigned long ocfs2_orphan_scan_timeout(void)
  * every slot, queuing a recovery of the slot on the ocfs2_wq thread. This
  * is done to catch any orphans that are left over in orphan directories.
  *
+ * It scans all slots, even ones that are in use. It does so to handle the
+ * case described below:
+ *
+ *   Node 1 has an inode it was using. The dentry went away due to memory
+ *   pressure.  Node 1 closes the inode, but it's on the free list. The node
+ *   has the open lock.
+ *   Node 2 unlinks the inode. It grabs the dentry lock to notify others,
+ *   but node 1 has no dentry and doesn't get the message. It trylocks the
+ *   open lock, sees that another node has a PR, and does nothing.
+ *   Later node 2 runs its orphan dir. It igets the inode, trylocks the
+ *   open lock, sees the PR still, and does nothing.
+ *   Basically, we have to trigger an orphan iput on node 1. The only way
+ *   for this to happen is if node 1 runs node 2's orphan dir.
+ *
  * ocfs2_queue_orphan_scan gets called every ORPHAN_SCAN_SCHEDULE_TIMEOUT
  * seconds.  It gets an EX lock on os_lockres and checks sequence number
  * stored in LVB. If the sequence number has changed, it means some other