---

yaml
---
r: 128962
b: refs/heads/master
c: d352ac6
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 9a5e1ea1e1e539e244a54afffc330fc368376ab9
+refs/heads/master: d352ac68148b69937d39ca5d48bcc4478e118dbf

trunk/fs/btrfs/Makefile

@@ -4,7 +4,7 @@ ifneq ($(KERNELRELEASE),)
 obj-m  := btrfs.o
 btrfs-y := super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   file-item.o inode-item.o inode-map.o disk-io.o \
-	   transaction.o bit-radix.o inode.o file.o tree-defrag.o \
+	   transaction.o inode.o file.o tree-defrag.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
 	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
 	   ref-cache.o export.o tree-log.o acl.o free-space-cache.o

trunk/fs/btrfs/async-thread.c

@@ -231,17 +231,25 @@ static struct btrfs_worker_thread *next_worker(struct btrfs_workers *workers)
 
 	/*
 	 * if we pick a busy task, move the task to the end of the list.
-	 * hopefully this will keep things somewhat evenly balanced
+	 * hopefully this will keep things somewhat evenly balanced.
+	 * Do the move in batches based on the sequence number.  This groups
+	 * requests submitted at roughly the same time onto the same worker.
 	 */
 	next = workers->worker_list.next;
 	worker = list_entry(next, struct btrfs_worker_thread, worker_list);
 	atomic_inc(&worker->num_pending);
 	worker->sequence++;
+
 	if (worker->sequence % workers->idle_thresh == 0)
 		list_move_tail(next, &workers->worker_list);
 	return worker;
 }
 
+/*
+ * selects a worker thread to take the next job.  This will either find
+ * an idle worker, start a new worker up to the max count, or just return
+ * one of the existing busy workers.
+ */
 static struct btrfs_worker_thread *find_worker(struct btrfs_workers *workers)
 {
 	struct btrfs_worker_thread *worker;

trunk/fs/btrfs/async-thread.h

@@ -63,14 +63,17 @@ struct btrfs_workers {
 	/* once a worker has this many requests or fewer, it is idle */
 	int idle_thresh;
 
-	/* list with all the work threads */
+	/* list with all the work threads.  The workers on the idle thread
+	 * may be actively servicing jobs, but they haven't yet hit the
+	 * idle thresh limit above.
+	 */
 	struct list_head worker_list;
 	struct list_head idle_list;
 
 	/* lock for finding the next worker thread to queue on */
 	spinlock_t lock;
 
-	/* extra name for this worker */
+	/* extra name for this worker, used for current->name */
 	char *name;
 };
 

trunk/fs/btrfs/btrfs_inode.h

@@ -25,27 +25,58 @@
 
 /* in memory btrfs inode */
 struct btrfs_inode {
+	/* which subvolume this inode belongs to */
 	struct btrfs_root *root;
+
+	/* the block group preferred for allocations.  This pointer is buggy
+	 * and needs to be replaced with a bytenr instead
+	 */
 	struct btrfs_block_group_cache *block_group;
+
+	/* key used to find this inode on disk.  This is used by the code
+	 * to read in roots of subvolumes
+	 */
 	struct btrfs_key location;
+
+	/* the extent_tree has caches of all the extent mappings to disk */
 	struct extent_map_tree extent_tree;
+
+	/* the io_tree does range state (DIRTY, LOCKED etc) */
 	struct extent_io_tree io_tree;
+
+	/* special utility tree used to record which mirrors have already been
+	 * tried when checksums fail for a given block
+	 */
 	struct extent_io_tree io_failure_tree;
+
+	/* held while inserting checksums to avoid races */
 	struct mutex csum_mutex;
+
+	/* held while inesrting or deleting extents from files */
 	struct mutex extent_mutex;
+
+	/* held while logging the inode in tree-log.c */
 	struct mutex log_mutex;
-	struct inode vfs_inode;
+
+	/* used to order data wrt metadata */
 	struct btrfs_ordered_inode_tree ordered_tree;
 
+	/* standard acl pointers */
 	struct posix_acl *i_acl;
 	struct posix_acl *i_default_acl;
 
 	/* for keeping track of orphaned inodes */
 	struct list_head i_orphan;
 
+	/* list of all the delalloc inodes in the FS.  There are times we need
+	 * to write all the delalloc pages to disk, and this list is used
+	 * to walk them all.
+	 */
 	struct list_head delalloc_inodes;
 
-	/* full 64 bit generation number */
+	/* full 64 bit generation number, struct vfs_inode doesn't have a big
+	 * enough field for this.
+	 */
 	u64 generation;
 
 	/*
@@ -57,17 +88,34 @@ struct btrfs_inode {
 	 */
 	u64 logged_trans;
 
-	/* trans that last made a change that should be fully fsync'd */
+	/*
+	 * trans that last made a change that should be fully fsync'd.  This
+	 * gets reset to zero each time the inode is logged
+	 */
 	u64 log_dirty_trans;
+
+	/* total number of bytes pending delalloc, used by stat to calc the
+	 * real block usage of the file
+	 */
 	u64 delalloc_bytes;
+
+	/*
+	 * the size of the file stored in the metadata on disk.  data=ordered
+	 * means the in-memory i_size might be larger than the size on disk
+	 * because not all the blocks are written yet.
+	 */
 	u64 disk_i_size;
+
+	/* flags field from the on disk inode */
 	u32 flags;
 
 	/*
 	 * if this is a directory then index_cnt is the counter for the index
 	 * number for new files that are created
 	 */
 	u64 index_cnt;
+
+	struct inode vfs_inode;
 };
 
 static inline struct btrfs_inode *BTRFS_I(struct inode *inode)

trunk/fs/btrfs/crc32c.h

@@ -1,3 +1,21 @@
+/*
+ * Copyright (C) 2008 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
 #ifndef __BTRFS_CRC32C__
 #define __BTRFS_CRC32C__
 #include <asm/byteorder.h>