9486 reduce memory used by device removal on fragmented pools

Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed by: Tim Chase <tim@chase2k.com>
Approved by: Robert Mustacchi <rm@joyent.com>

usr/src/uts/common/fs/zfs/range_tree.c

@@ -298,15 +298,14 @@ range_tree_remove(void *arg, uint64_t start, uint64_t size)
 static range_seg_t *
 range_tree_find_impl(range_tree_t *rt, uint64_t start, uint64_t size)
 {
-	avl_index_t where;
 	range_seg_t rsearch;
 	uint64_t end = start + size;
 
 	VERIFY(size != 0);
 
 	rsearch.rs_start = start;
 	rsearch.rs_end = end;
-	return (avl_find(&rt->rt_root, &rsearch, &where));
+	return (avl_find(&rt->rt_root, &rsearch, NULL));
 }
 
 static range_seg_t *
@@ -407,3 +406,23 @@ range_tree_is_empty(range_tree_t *rt)
 	ASSERT(rt != NULL);
 	return (range_tree_space(rt) == 0);
 }
+
+uint64_t
+range_tree_min(range_tree_t *rt)
+{
+	range_seg_t *rs = avl_first(&rt->rt_root);
+	return (rs != NULL ? rs->rs_start : 0);
+}
+
+uint64_t
+range_tree_max(range_tree_t *rt)
+{
+	range_seg_t *rs = avl_last(&rt->rt_root);
+	return (rs != NULL ? rs->rs_end : 0);
+}
+
+uint64_t
+range_tree_span(range_tree_t *rt)
+{
+	return (range_tree_max(rt) - range_tree_min(rt));
+}

usr/src/uts/common/fs/zfs/sys/range_tree.h

@@ -86,6 +86,9 @@ boolean_t range_tree_is_empty(range_tree_t *rt);
 void range_tree_verify(range_tree_t *rt, uint64_t start, uint64_t size);
 void range_tree_swap(range_tree_t **rtsrc, range_tree_t **rtdst);
 void range_tree_stat_verify(range_tree_t *rt);
+uint64_t range_tree_min(range_tree_t *rt);
+uint64_t range_tree_max(range_tree_t *rt);
+uint64_t range_tree_span(range_tree_t *rt);
 
 void range_tree_add(void *arg, uint64_t start, uint64_t size);
 void range_tree_remove(void *arg, uint64_t start, uint64_t size);

usr/src/uts/common/fs/zfs/sys/vdev_removal.h

@@ -86,6 +86,9 @@ extern void spa_vdev_remove_suspend(spa_t *);
 extern int spa_vdev_remove_cancel(spa_t *);
 extern void spa_vdev_removal_destroy(spa_vdev_removal_t *svr);
 
+extern int vdev_removal_max_span;
+extern int zfs_remove_max_segment;
+
 #ifdef	__cplusplus
 }
 #endif

usr/src/uts/common/fs/zfs/vdev_label.c

@@ -33,15 +33,15 @@
  *	1. Uniquely identify this device as part of a ZFS pool and confirm its
  *	   identity within the pool.
  *
- * 	2. Verify that all the devices given in a configuration are present
+ *	2. Verify that all the devices given in a configuration are present
  *         within the pool.
  *
- * 	3. Determine the uberblock for the pool.
+ *	3. Determine the uberblock for the pool.
  *
- * 	4. In case of an import operation, determine the configuration of the
+ *	4. In case of an import operation, determine the configuration of the
  *         toplevel vdev of which it is a part.
  *
- * 	5. If an import operation cannot find all the devices in the pool,
+ *	5. If an import operation cannot find all the devices in the pool,
  *         provide enough information to the administrator to determine which
  *         devices are missing.
  *
@@ -77,9 +77,9 @@
  * In order to identify which labels are valid, the labels are written in the
  * following manner:
  *
- * 	1. For each vdev, update 'L1' to the new label
- * 	2. Update the uberblock
- * 	3. For each vdev, update 'L2' to the new label
+ *	1. For each vdev, update 'L1' to the new label
+ *	2. Update the uberblock
+ *	3. For each vdev, update 'L2' to the new label
  *
  * Given arbitrary failure, we can determine the correct label to use based on
  * the transaction group.  If we fail after updating L1 but before updating the
@@ -117,19 +117,19 @@
  *
  * The nvlist describing the pool and vdev contains the following elements:
  *
- * 	version		ZFS on-disk version
- * 	name		Pool name
- * 	state		Pool state
- * 	txg		Transaction group in which this label was written
- * 	pool_guid	Unique identifier for this pool
- * 	vdev_tree	An nvlist describing vdev tree.
+ *	version		ZFS on-disk version
+ *	name		Pool name
+ *	state		Pool state
+ *	txg		Transaction group in which this label was written
+ *	pool_guid	Unique identifier for this pool
+ *	vdev_tree	An nvlist describing vdev tree.
  *	features_for_read
  *			An nvlist of the features necessary for reading the MOS.
  *
  * Each leaf device label also contains the following:
  *
- * 	top_guid	Unique ID for top-level vdev in which this is contained
- * 	guid		Unique ID for the leaf vdev
+ *	top_guid	Unique ID for top-level vdev in which this is contained
+ *	guid		Unique ID for the leaf vdev
  *
  * The 'vs' configuration follows the format described in 'spa_config.c'.
  */
@@ -390,22 +390,33 @@ vdev_config_generate(spa_t *spa, vdev_t *vd, boolean_t getstats,
 			 * histograms.
 			 */
 			uint64_t seg_count = 0;
+			uint64_t to_alloc = vd->vdev_stat.vs_alloc;
 
 			/*
 			 * There are the same number of allocated segments
 			 * as free segments, so we will have at least one
-			 * entry per free segment.
+			 * entry per free segment.  However, small free
+			 * segments (smaller than vdev_removal_max_span)
+			 * will be combined with adjacent allocated segments
+			 * as a single mapping.
 			 */
 			for (int i = 0; i < RANGE_TREE_HISTOGRAM_SIZE; i++) {
-				seg_count += vd->vdev_mg->mg_histogram[i];
+				if (1ULL << (i + 1) < vdev_removal_max_span) {
+					to_alloc +=
+					    vd->vdev_mg->mg_histogram[i] <<
+					    i + 1;
+				} else {
+					seg_count +=
+					    vd->vdev_mg->mg_histogram[i];
+				}
 			}
 
 			/*
-			 * The maximum length of a mapping is SPA_MAXBLOCKSIZE,
-			 * so we need at least one entry per SPA_MAXBLOCKSIZE
-			 * of allocated data.
+			 * The maximum length of a mapping is
+			 * zfs_remove_max_segment, so we need at least one entry
+			 * per zfs_remove_max_segment of allocated data.
 			 */
-			seg_count += vd->vdev_stat.vs_alloc / SPA_MAXBLOCKSIZE;
+			seg_count += to_alloc / zfs_remove_max_segment;
 
 			fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_SIZE,
 			    seg_count *