diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6c91a510c965..7ae4666103c0 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -532,6 +532,7 @@ struct btrfs_fs_info {
 	 */
 	struct btrfs_workers workers;
 	struct btrfs_workers endio_workers;
+	int thread_pool_size;
 
 #if LINUX_VERSION_CODE <= KERNEL_VERSION(2,6,18)
 	struct work_struct trans_work;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 98ff4fbcb386..c6a710a668cb 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1117,6 +1117,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 					      GFP_NOFS);
 	int ret;
 	int err = -EINVAL;
+
 	struct btrfs_super_block *disk_super;
 
 	if (!extent_root || !tree_root || !fs_info) {
@@ -1148,6 +1149,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	fs_info->btree_inode = new_inode(sb);
 	fs_info->btree_inode->i_ino = 1;
 	fs_info->btree_inode->i_nlink = 1;
+	fs_info->thread_pool_size = min(num_online_cpus() + 2, 8);
 
 	sb->s_blocksize = 4096;
 	sb->s_blocksize_bits = blksize_bits(4096);
@@ -1195,19 +1197,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->trans_mutex);
 	mutex_init(&fs_info->fs_mutex);
 
-	/* we need to start all the end_io workers up front because the
-	 * queue work function gets called at interrupt time.  The endio
-	 * workers don't normally start IO, so some number of them <= the
-	 * number of cpus is fine.  They handle checksumming after a read.
-	 *
-	 * The other worker threads do start IO, so the max is larger than
-	 * the number of CPUs.  FIXME, tune this for huge machines
-	 */
-	btrfs_init_workers(&fs_info->workers, num_online_cpus() * 2);
-	btrfs_init_workers(&fs_info->endio_workers, num_online_cpus());
-	btrfs_start_workers(&fs_info->workers, 1);
-	btrfs_start_workers(&fs_info->endio_workers, num_online_cpus());
-
 #if 0
 	ret = add_hasher(fs_info, "crc32c");
 	if (ret) {
@@ -1238,6 +1227,17 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	if (err)
 		goto fail_sb_buffer;
 
+	/*
+	 * we need to start all the end_io workers up front because the
+	 * queue work function gets called at interrupt time, and so it
+	 * cannot dynamically grow.
+	 */
+	btrfs_init_workers(&fs_info->workers, fs_info->thread_pool_size);
+	btrfs_init_workers(&fs_info->endio_workers, fs_info->thread_pool_size);
+	btrfs_start_workers(&fs_info->workers, 1);
+	btrfs_start_workers(&fs_info->endio_workers, fs_info->thread_pool_size);
+
+
 	err = -EINVAL;
 	if (btrfs_super_num_devices(disk_super) > fs_devices->open_devices) {
 		printk("Btrfs: wanted %llu devices, but found %llu\n",
@@ -1341,10 +1341,10 @@ fail_sys_array:
 	mutex_unlock(&fs_info->fs_mutex);
 fail_sb_buffer:
 	extent_io_tree_empty_lru(&BTRFS_I(fs_info->btree_inode)->io_tree);
-fail_iput:
-	iput(fs_info->btree_inode);
 	btrfs_stop_workers(&fs_info->workers);
 	btrfs_stop_workers(&fs_info->endio_workers);
+fail_iput:
+	iput(fs_info->btree_inode);
 fail:
 	btrfs_close_devices(fs_info->fs_devices);
 	btrfs_mapping_tree_free(&fs_info->mapping_tree);
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index f3274befd46a..196d0e280b19 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -67,7 +67,7 @@ static void btrfs_put_super (struct super_block * sb)
 enum {
 	Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow,
 	Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier,
-	Opt_ssd, Opt_err,
+	Opt_ssd, Opt_thread_pool, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -80,6 +80,7 @@ static match_table_t tokens = {
 	{Opt_max_extent, "max_extent=%s"},
 	{Opt_max_inline, "max_inline=%s"},
 	{Opt_alloc_start, "alloc_start=%s"},
+	{Opt_thread_pool, "thread_pool=%d"},
 	{Opt_ssd, "ssd"},
 	{Opt_err, NULL}
 };
@@ -118,6 +119,7 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 	struct btrfs_fs_info *info = root->fs_info;
 	substring_t args[MAX_OPT_ARGS];
 	char *p, *num;
+	int intarg;
 
 	if (!options)
 		return 0;
@@ -166,6 +168,15 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 			printk(KERN_INFO "btrfs: turning off barriers\n");
 			btrfs_set_opt(info->mount_opt, NOBARRIER);
 			break;
+		case Opt_thread_pool:
+			intarg = 0;
+			match_int(&args[0], &intarg);
+			if (intarg) {
+				info->thread_pool_size = intarg;
+				printk(KERN_INFO "btrfs: thread pool %d\n",
+				       info->thread_pool_size);
+			}
+			break;
 		case Opt_max_extent:
 			num = match_strdup(&args[0]);
 			if (num) {