Illumos 4873 - zvol unmap calls can take a very long time for larger datasets

4873 zvol unmap calls can take a very long time for larger datasets
Author: Alex Reece <alex@delphix.com>
Reviewed by: George Wilson <george@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Paul Dagnelie <paul.dagnelie@delphix.com>
Reviewed by: Basil Crow <basil.crow@delphix.com>
Reviewed by: Dan McDonald <danmcd@omniti.com>
Approved by: Robert Mustacchi <rm@joyent.com>

References:
  https://www.illumos.org/issues/4873
  https://github.com/illumos/illumos-gate/commit/0f6d88a

Porting Notes:

dbuf_free_range():
  - reduce stack usage using kmem_alloc()
  - the sorted AVL tree will handle the spill block case correctly
    without all the special handling in the for() loop

Ported-by: Chris Dunlop <chris@onthe.net.au>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>

include/sys/avl.h

@@ -23,6 +23,10 @@
  * Use is subject to license terms.
  */
 
+/*
+ * Copyright (c) 2014 by Delphix. All rights reserved.
+ */
+
 #ifndef	_AVL_H
 #define	_AVL_H
 
@@ -259,6 +263,11 @@ extern boolean_t avl_update(avl_tree_t *, void *);
 extern boolean_t avl_update_lt(avl_tree_t *, void *);
 extern boolean_t avl_update_gt(avl_tree_t *, void *);
 
+/*
+ * Swaps the contents of the two trees.
+ */
+extern void avl_swap(avl_tree_t *tree1, avl_tree_t *tree2);
+
 /*
  * Return the number of nodes in the tree
  */

include/sys/dbuf.h

@@ -20,7 +20,7 @@
  */
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2013 by Delphix. All rights reserved.
+ * Copyright (c) 2012, 2014 by Delphix. All rights reserved.
  * Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
  */
 
@@ -213,11 +213,14 @@ typedef struct dmu_buf_impl {
 	/* pointer to most recent dirty record for this buffer */
 	dbuf_dirty_record_t *db_last_dirty;
 
+	/* Creation time of dbuf (see comment in dbuf_compare). */
+	hrtime_t db_creation;
+
 	/*
 	 * Our link on the owner dnodes's dn_dbufs list.
 	 * Protected by its dn_dbufs_mtx.
 	 */
-	list_node_t db_link;
+	avl_node_t db_link;
 
 	/* Data which is unique to data (leaf) blocks: */
 

include/sys/dnode.h

@@ -233,7 +233,7 @@ typedef struct dnode {
 	refcount_t dn_holds;
 
 	kmutex_t dn_dbufs_mtx;
-	list_t dn_dbufs;		/* descendent dbufs */
+	avl_tree_t dn_dbufs;		/* descendent dbufs */
 
 	/* protected by dn_struct_rwlock */
 	struct dmu_buf_impl *dn_bonus;	/* bonus buffer dbuf */