ocfs2: Cache system inodes of other slots.

Durring orphan scan, if we are slot 0, and we are replaying
orphan_dir:0001, the general process is that for every file
in this dir:
1. we will iget orphan_dir:0001, since there is no inode for it.
   we will have to create an inode and read it from the disk.
2. do the normal work, such as delete_inode and remove it from
   the dir if it is allowed.
3. call iput orphan_dir:0001 when we are done. In this case,
   since we have no dcache for this inode, i_count will
   reach 0, and VFS will have to call clear_inode and in
   ocfs2_clear_inode we will checkpoint the inode which will let
   ocfs2_cmt and journald begin to work.
4. We loop back to 1 for the next file.

So you see, actually for every deleted file, we have to read the
orphan dir from the disk and checkpoint the journal. It is very
time consuming and cause a lot of journal checkpoint I/O.
A better solution is that we can have another reference for these
inodes in ocfs2_super. So if there is no other race among
nodes(which will let dlmglue to checkpoint the inode), for step 3,
clear_inode won't be called and for step 1, we may only need to
read the inode for the 1st time. This is a big win for us.

So this patch will try to cache system inodes of other slots so
that we will have one more reference for these inodes and avoid
the extra inode read and journal checkpoint.

Signed-off-by: Tao Ma <tao.ma@oracle.com>
Signed-off-by: Joel Becker <joel.becker@oracle.com>

1 files changed, 49 insertions, 11 deletions

diff --git a/fs/ocfs2/sysfile.c b/fs/ocfs2/sysfile.c
index bfe7190..902efb2 100644
--- a/fs/ocfs2/sysfile.c
+++ b/fs/ocfs2/sysfile.c
@@ -44,11 +44,6 @@ static struct inode * _ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 						   int type,
 						   u32 slot);
 
-static inline int is_global_system_inode(int type);
-static inline int is_in_system_inode_array(struct ocfs2_super *osb,
-					   int type,
-					   u32 slot);
-
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key ocfs2_sysfile_cluster_lock_key[NUM_SYSTEM_INODES];
 #endif
@@ -59,11 +54,52 @@ static inline int is_global_system_inode(int type)
 		type <= OCFS2_LAST_GLOBAL_SYSTEM_INODE;
 }
 
-static inline int is_in_system_inode_array(struct ocfs2_super *osb,
-					   int type,
-					   u32 slot)
+static struct inode **get_local_system_inode(struct ocfs2_super *osb,
+					     int type,
+					     u32 slot)
 {
-	return slot == osb->slot_num || is_global_system_inode(type);
+	int index;
+	struct inode **local_system_inodes, **free = NULL;
+
+	BUG_ON(slot == OCFS2_INVALID_SLOT);
+	BUG_ON(type < OCFS2_FIRST_LOCAL_SYSTEM_INODE ||
+	       type > OCFS2_LAST_LOCAL_SYSTEM_INODE);
+
+	spin_lock(&osb->osb_lock);
+	local_system_inodes = osb->local_system_inodes;
+	spin_unlock(&osb->osb_lock);
+
+	if (unlikely(!local_system_inodes)) {
+		local_system_inodes = kzalloc(sizeof(struct inode *) *
+					      NUM_LOCAL_SYSTEM_INODES *
+					      osb->max_slots,
+					      GFP_NOFS);
+		if (!local_system_inodes) {
+			mlog_errno(-ENOMEM);
+			/*
+			 * return NULL here so that ocfs2_get_sytem_file_inodes
+			 * will try to create an inode and use it. We will try
+			 * to initialize local_system_inodes next time.
+			 */
+			return NULL;
+		}
+
+		spin_lock(&osb->osb_lock);
+		if (osb->local_system_inodes) {
+			/* Someone has initialized it for us. */
+			free = local_system_inodes;
+			local_system_inodes = osb->local_system_inodes;
+		} else
+			osb->local_system_inodes = local_system_inodes;
+		spin_unlock(&osb->osb_lock);
+		if (unlikely(free))
+			kfree(free);
+	}
+
+	index = (slot * NUM_LOCAL_SYSTEM_INODES) +
+		(type - OCFS2_FIRST_LOCAL_SYSTEM_INODE);
+
+	return &local_system_inodes[index];
 }
 
 struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
@@ -74,8 +110,10 @@ struct inode *ocfs2_get_system_file_inode(struct ocfs2_super *osb,
 	struct inode **arr = NULL;
 
 	/* avoid the lookup if cached in local system file array */
-	if (is_in_system_inode_array(osb, type, slot))
-		arr = &(osb->system_inodes[type]);
+	if (is_global_system_inode(type)) {
+		arr = &(osb->global_system_inodes[type]);
+	} else
+		arr = get_local_system_inode(osb, type, slot);
 
 	if (arr && ((inode = *arr) != NULL)) {
 		/* get a ref in addition to the array ref */