MFC r329732: MFV r329502: 7614 zfs device evacuation/removal

illumos/illumos-gate@5cabbc6b49070407fb9610cfe73d4c0e0dea3e77

https://www.illumos.org/issues/7614:
This project allows top-level vdevs to be removed from the storage pool with
“zpool remove”, reducing the total amount of storage in the pool. This
operation copies all allocated regions of the device to be removed onto other
devices, recording the mapping from old to new location. After the removal is
complete, read and free operations to the removed (now “indirect”) vdev must
be remapped and performed at the new location on disk. The indirect mapping
table is kept in memory whenever the pool is loaded, so there is minimal
performance overhead when doing operations on the indirect vdev.

The size of the in-memory mapping table will be reduced when its entries
become “obsolete” because they are no longer used by any block pointers in
the pool. An entry becomes obsolete when all the blocks that use it are
freed. An entry can also become obsolete when all the snapshots that
reference it are deleted, and the block pointers that reference it have been
“remapped” in all filesystems/zvols (and clones). Whenever an indirect block
is written, all the block pointers in it will be “remapped” to their new
(concrete) locations if possible. This process can be accelerated by using
the “zfs remap” command to proactively rewrite all indirect blocks that
reference indirect (removed) vdevs.

Note that when a device is removed, we do not verify the checksum of the data
that is copied. This makes the process much faster, but if it were used on
redundant vdevs (i.e. mirror or raidz vdevs), it would be possible to copy
the wrong data, when we have the correct data on e.g. the other side of the
mirror. Therefore, mirror and raidz devices can not be removed.

Reviewed by: Alex Reece <alex@delphix.com>
Reviewed by: George Wilson <george.wilson@delphix.com>
Reviewed by: John Kennedy <john.kennedy@delphix.com>
Reviewed by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Richard Laager <rlaager@wiktel.com>
Reviewed by: Tim Chase <tim@chase2k.com>
Approved by: Garrett D'Amore <garrett@damore.org>
Author: Prashanth Sreenivasa <pks@delphix.com>

4 files changed, 932 insertions, 89 deletions

diff --git a/cddl/contrib/opensolaris/cmd/zdb/zdb.c b/cddl/contrib/opensolaris/cmd/zdb/zdb.c
index 82d0a32..41afcd0 100644
--- a/cddl/contrib/opensolaris/cmd/zdb/zdb.c
+++ b/cddl/contrib/opensolaris/cmd/zdb/zdb.c
@@ -21,7 +21,7 @@
 
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2016 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
  * Copyright (c) 2014 Integros [integros.com]
  * Copyright 2017 Nexenta Systems, Inc.
  */
@@ -77,8 +77,10 @@
 	dmu_ot[(idx)].ot_name : DMU_OT_IS_VALID(idx) ?	\
 	dmu_ot_byteswap[DMU_OT_BYTESWAP(idx)].ob_name : "UNKNOWN")
 #define	ZDB_OT_TYPE(idx) ((idx) < DMU_OT_NUMTYPES ? (idx) :		\
-	(((idx) == DMU_OTN_ZAP_DATA || (idx) == DMU_OTN_ZAP_METADATA) ?	\
-	DMU_OT_ZAP_OTHER : DMU_OT_NUMTYPES))
+	(idx) == DMU_OTN_ZAP_DATA || (idx) == DMU_OTN_ZAP_METADATA ?	\
+	DMU_OT_ZAP_OTHER : \
+	(idx) == DMU_OTN_UINT64_DATA || (idx) == DMU_OTN_UINT64_METADATA ? \
+	DMU_OT_UINT64_OTHER : DMU_OT_NUMTYPES)
 
 #ifndef lint
 extern int reference_tracking_enable;
@@ -667,8 +669,8 @@ get_metaslab_refcount(vdev_t *vd)
 {
 	int refcount = 0;
 
-	if (vd->vdev_top == vd && !vd->vdev_removing) {
-		for (unsigned m = 0; m < vd->vdev_ms_count; m++) {
+	if (vd->vdev_top == vd) {
+		for (uint64_t m = 0; m < vd->vdev_ms_count; m++) {
 			space_map_t *sm = vd->vdev_ms[m]->ms_sm;
 
 			if (sm != NULL &&
@@ -683,6 +685,45 @@ get_metaslab_refcount(vdev_t *vd)
 }
 
 static int
+get_obsolete_refcount(vdev_t *vd)
+{
+	int refcount = 0;
+
+	uint64_t obsolete_sm_obj = vdev_obsolete_sm_object(vd);
+	if (vd->vdev_top == vd && obsolete_sm_obj != 0) {
+		dmu_object_info_t doi;
+		VERIFY0(dmu_object_info(vd->vdev_spa->spa_meta_objset,
+		    obsolete_sm_obj, &doi));
+		if (doi.doi_bonus_size == sizeof (space_map_phys_t)) {
+			refcount++;
+		}
+	} else {
+		ASSERT3P(vd->vdev_obsolete_sm, ==, NULL);
+		ASSERT3U(obsolete_sm_obj, ==, 0);
+	}
+	for (unsigned c = 0; c < vd->vdev_children; c++) {
+		refcount += get_obsolete_refcount(vd->vdev_child[c]);
+	}
+
+	return (refcount);
+}
+
+static int
+get_prev_obsolete_spacemap_refcount(spa_t *spa)
+{
+	uint64_t prev_obj =
+	    spa->spa_condensing_indirect_phys.scip_prev_obsolete_sm_object;
+	if (prev_obj != 0) {
+		dmu_object_info_t doi;
+		VERIFY0(dmu_object_info(spa->spa_meta_objset, prev_obj, &doi));
+		if (doi.doi_bonus_size == sizeof (space_map_phys_t)) {
+			return (1);
+		}
+	}
+	return (0);
+}
+
+static int
 verify_spacemap_refcounts(spa_t *spa)
 {
 	uint64_t expected_refcount = 0;
@@ -693,6 +734,8 @@ verify_spacemap_refcounts(spa_t *spa)
 	    &expected_refcount);
 	actual_refcount = get_dtl_refcount(spa->spa_root_vdev);
 	actual_refcount += get_metaslab_refcount(spa->spa_root_vdev);
+	actual_refcount += get_obsolete_refcount(spa->spa_root_vdev);
+	actual_refcount += get_prev_obsolete_spacemap_refcount(spa);
 
 	if (expected_refcount != actual_refcount) {
 		(void) printf("space map refcount mismatch: expected %lld != "
@@ -708,12 +751,19 @@ static void
 dump_spacemap(objset_t *os, space_map_t *sm)
 {
 	uint64_t alloc, offset, entry;
-	const char *ddata[] = { "ALLOC", "FREE", "CONDENSE", "INVALID",
-			    "INVALID", "INVALID", "INVALID", "INVALID" };
+	char *ddata[] = { "ALLOC", "FREE", "CONDENSE", "INVALID",
+	    "INVALID", "INVALID", "INVALID", "INVALID" };
 
 	if (sm == NULL)
 		return;
 
+	(void) printf("space map object %llu:\n",
+	    (longlong_t)sm->sm_phys->smp_object);
+	(void) printf("  smp_objsize = 0x%llx\n",
+	    (longlong_t)sm->sm_phys->smp_objsize);
+	(void) printf("  smp_alloc = 0x%llx\n",
+	    (longlong_t)sm->sm_phys->smp_alloc);
+
 	/*
 	 * Print out the freelist entries in both encoded and decoded form.
 	 */
@@ -818,9 +868,7 @@ dump_metaslab(metaslab_t *msp)
 	if (dump_opt['d'] > 5 || dump_opt['m'] > 3) {
 		ASSERT(msp->ms_size == (1ULL << vd->vdev_ms_shift));
 
-		mutex_enter(&msp->ms_lock);
 		dump_spacemap(spa->spa_meta_objset, msp->ms_sm);
-		mutex_exit(&msp->ms_lock);
 	}
 }
 
@@ -878,6 +926,78 @@ dump_metaslab_groups(spa_t *spa)
 }
 
 static void
+print_vdev_indirect(vdev_t *vd)
+{
+	vdev_indirect_config_t *vic = &vd->vdev_indirect_config;
+	vdev_indirect_mapping_t *vim = vd->vdev_indirect_mapping;
+	vdev_indirect_births_t *vib = vd->vdev_indirect_births;
+
+	if (vim == NULL) {
+		ASSERT3P(vib, ==, NULL);
+		return;
+	}
+
+	ASSERT3U(vdev_indirect_mapping_object(vim), ==,
+	    vic->vic_mapping_object);
+	ASSERT3U(vdev_indirect_births_object(vib), ==,
+	    vic->vic_births_object);
+
+	(void) printf("indirect births obj %llu:\n",
+	    (longlong_t)vic->vic_births_object);
+	(void) printf("    vib_count = %llu\n",
+	    (longlong_t)vdev_indirect_births_count(vib));
+	for (uint64_t i = 0; i < vdev_indirect_births_count(vib); i++) {
+		vdev_indirect_birth_entry_phys_t *cur_vibe =
+		    &vib->vib_entries[i];
+		(void) printf("\toffset %llx -> txg %llu\n",
+		    (longlong_t)cur_vibe->vibe_offset,
+		    (longlong_t)cur_vibe->vibe_phys_birth_txg);
+	}
+	(void) printf("\n");
+
+	(void) printf("indirect mapping obj %llu:\n",
+	    (longlong_t)vic->vic_mapping_object);
+	(void) printf("    vim_max_offset = 0x%llx\n",
+	    (longlong_t)vdev_indirect_mapping_max_offset(vim));
+	(void) printf("    vim_bytes_mapped = 0x%llx\n",
+	    (longlong_t)vdev_indirect_mapping_bytes_mapped(vim));
+	(void) printf("    vim_count = %llu\n",
+	    (longlong_t)vdev_indirect_mapping_num_entries(vim));
+
+	if (dump_opt['d'] <= 5 && dump_opt['m'] <= 3)
+		return;
+
+	uint32_t *counts = vdev_indirect_mapping_load_obsolete_counts(vim);
+
+	for (uint64_t i = 0; i < vdev_indirect_mapping_num_entries(vim); i++) {
+		vdev_indirect_mapping_entry_phys_t *vimep =
+		    &vim->vim_entries[i];
+		(void) printf("\t<%llx:%llx:%llx> -> "
+		    "<%llx:%llx:%llx> (%x obsolete)\n",
+		    (longlong_t)vd->vdev_id,
+		    (longlong_t)DVA_MAPPING_GET_SRC_OFFSET(vimep),
+		    (longlong_t)DVA_GET_ASIZE(&vimep->vimep_dst),
+		    (longlong_t)DVA_GET_VDEV(&vimep->vimep_dst),
+		    (longlong_t)DVA_GET_OFFSET(&vimep->vimep_dst),
+		    (longlong_t)DVA_GET_ASIZE(&vimep->vimep_dst),
+		    counts[i]);
+	}
+	(void) printf("\n");
+
+	uint64_t obsolete_sm_object = vdev_obsolete_sm_object(vd);
+	if (obsolete_sm_object != 0) {
+		objset_t *mos = vd->vdev_spa->spa_meta_objset;
+		(void) printf("obsolete space map object %llu:\n",
+		    (u_longlong_t)obsolete_sm_object);
+		ASSERT(vd->vdev_obsolete_sm != NULL);
+		ASSERT3U(space_map_object(vd->vdev_obsolete_sm), ==,
+		    obsolete_sm_object);
+		dump_spacemap(mos, vd->vdev_obsolete_sm);
+		(void) printf("\n");
+	}
+}
+
+static void
 dump_metaslabs(spa_t *spa)
 {
 	vdev_t *vd, *rvd = spa->spa_root_vdev;
@@ -913,6 +1033,8 @@ dump_metaslabs(spa_t *spa)
 		vd = rvd->vdev_child[c];
 		print_vdev_metaslab_header(vd);
 
+		print_vdev_indirect(vd);
+
 		for (m = 0; m < vd->vdev_ms_count; m++)
 			dump_metaslab(vd->vdev_ms[m]);
 		(void) printf("\n");
@@ -1090,9 +1212,7 @@ dump_dtl(vdev_t *vd, int indent)
 			continue;
 		(void) snprintf(prefix, sizeof (prefix), "\t%*s%s",
 		    indent + 2, "", name[t]);
-		mutex_enter(rt->rt_lock);
 		range_tree_walk(rt, dump_dtl_seg, prefix);
-		mutex_exit(rt->rt_lock);
 		if (dump_opt['d'] > 5 && vd->vdev_children == 0)
 			dump_spacemap(spa->spa_meta_objset, vd->vdev_dtl_sm);
 	}
@@ -2107,8 +2227,15 @@ dump_dir(objset_t *os)
 	if (dump_opt['i'] != 0 || verbosity >= 2)
 		dump_intent_log(dmu_objset_zil(os));
 
-	if (dmu_objset_ds(os) != NULL)
-		dump_deadlist(&dmu_objset_ds(os)->ds_deadlist);
+	if (dmu_objset_ds(os) != NULL) {
+		dsl_dataset_t *ds = dmu_objset_ds(os);
+		dump_deadlist(&ds->ds_deadlist);
+
+		if (dsl_dataset_remap_deadlist_exists(ds)) {
+			(void) printf("ds_remap_deadlist:\n");
+			dump_deadlist(&ds->ds_remap_deadlist);
+		}
+	}
 
 	if (verbosity < 2)
 		return;
@@ -2452,6 +2579,7 @@ dump_label(const char *dev)
 }
 
 static uint64_t dataset_feature_count[SPA_FEATURES];
+static uint64_t remap_deadlist_count = 0;
 
 /*ARGSUSED*/
 static int
@@ -2472,6 +2600,10 @@ dump_one_dir(const char *dsname, void *arg)
 		dataset_feature_count[f]++;
 	}
 
+	if (dsl_dataset_remap_deadlist_exists(dmu_objset_ds(os))) {
+		remap_deadlist_count++;
+	}
+
 	dump_dir(os);
 	close_objset(os, FTAG);
 	fuid_table_destroy();
@@ -2511,6 +2643,7 @@ static const char *zdb_ot_extname[] = {
 
 typedef struct zdb_cb {
 	zdb_blkstats_t	zcb_type[ZB_TOTAL + 1][ZDB_OT_TOTAL + 1];
+	uint64_t	zcb_removing_size;
 	uint64_t	zcb_dedup_asize;
 	uint64_t	zcb_dedup_blocks;
 	uint64_t	zcb_embedded_blocks[NUM_BP_EMBEDDED_TYPES];
@@ -2523,6 +2656,7 @@ typedef struct zdb_cb {
 	int		zcb_readfails;
 	int		zcb_haderrors;
 	spa_t		*zcb_spa;
+	uint32_t	**zcb_vd_obsolete_counts;
 } zdb_cb_t;
 
 static void
@@ -2797,12 +2931,208 @@ zdb_ddt_leak_init(spa_t *spa, zdb_cb_t *zcb)
 	ASSERT(error == ENOENT);
 }
 
+/* ARGSUSED */
+static void
+claim_segment_impl_cb(uint64_t inner_offset, vdev_t *vd, uint64_t offset,
+    uint64_t size, void *arg)
+{
+	/*
+	 * This callback was called through a remap from
+	 * a device being removed. Therefore, the vdev that
+	 * this callback is applied to is a concrete
+	 * vdev.
+	 */
+	ASSERT(vdev_is_concrete(vd));
+
+	VERIFY0(metaslab_claim_impl(vd, offset, size,
+	    spa_first_txg(vd->vdev_spa)));
+}
+
+static void
+claim_segment_cb(void *arg, uint64_t offset, uint64_t size)
+{
+	vdev_t *vd = arg;
+
+	vdev_indirect_ops.vdev_op_remap(vd, offset, size,
+	    claim_segment_impl_cb, NULL);
+}
+
+/*
+ * After accounting for all allocated blocks that are directly referenced,
+ * we might have missed a reference to a block from a partially complete
+ * (and thus unused) indirect mapping object. We perform a secondary pass
+ * through the metaslabs we have already mapped and claim the destination
+ * blocks.
+ */
+static void
+zdb_claim_removing(spa_t *spa, zdb_cb_t *zcb)
+{
+	if (spa->spa_vdev_removal == NULL)
+		return;
+
+	spa_config_enter(spa, SCL_CONFIG, FTAG, RW_READER);
+
+	spa_vdev_removal_t *svr = spa->spa_vdev_removal;
+	vdev_t *vd = svr->svr_vdev;
+	vdev_indirect_mapping_t *vim = vd->vdev_indirect_mapping;
+
+	for (uint64_t msi = 0; msi < vd->vdev_ms_count; msi++) {
+		metaslab_t *msp = vd->vdev_ms[msi];
+
+		if (msp->ms_start >= vdev_indirect_mapping_max_offset(vim))
+			break;
+
+		ASSERT0(range_tree_space(svr->svr_allocd_segs));
+
+		if (msp->ms_sm != NULL) {
+			VERIFY0(space_map_load(msp->ms_sm,
+			    svr->svr_allocd_segs, SM_ALLOC));
+
+			/*
+			 * Clear everything past what has been synced,
+			 * because we have not allocated mappings for it yet.
+			 */
+			range_tree_clear(svr->svr_allocd_segs,
+			    vdev_indirect_mapping_max_offset(vim),
+			    msp->ms_sm->sm_start + msp->ms_sm->sm_size -
+			    vdev_indirect_mapping_max_offset(vim));
+		}
+
+		zcb->zcb_removing_size +=
+		    range_tree_space(svr->svr_allocd_segs);
+		range_tree_vacate(svr->svr_allocd_segs, claim_segment_cb, vd);
+	}
+
+	spa_config_exit(spa, SCL_CONFIG, FTAG);
+}
+
+/*
+ * vm_idxp is an in-out parameter which (for indirect vdevs) is the
+ * index in vim_entries that has the first entry in this metaslab.  On
+ * return, it will be set to the first entry after this metaslab.
+ */
+static void
+zdb_leak_init_ms(metaslab_t *msp, uint64_t *vim_idxp)
+{
+	metaslab_group_t *mg = msp->ms_group;
+	vdev_t *vd = mg->mg_vd;
+	vdev_t *rvd = vd->vdev_spa->spa_root_vdev;
+
+	mutex_enter(&msp->ms_lock);
+	metaslab_unload(msp);
+
+	/*
+	 * We don't want to spend the CPU manipulating the size-ordered
+	 * tree, so clear the range_tree ops.
+	 */
+	msp->ms_tree->rt_ops = NULL;
+
+	(void) fprintf(stderr,
+	    "\rloading vdev %llu of %llu, metaslab %llu of %llu ...",
+	    (longlong_t)vd->vdev_id,
+	    (longlong_t)rvd->vdev_children,
+	    (longlong_t)msp->ms_id,
+	    (longlong_t)vd->vdev_ms_count);
+
+	/*
+	 * For leak detection, we overload the metaslab ms_tree to
+	 * contain allocated segments instead of free segments. As a
+	 * result, we can't use the normal metaslab_load/unload
+	 * interfaces.
+	 */
+	if (vd->vdev_ops == &vdev_indirect_ops) {
+		vdev_indirect_mapping_t *vim = vd->vdev_indirect_mapping;
+		for (; *vim_idxp < vdev_indirect_mapping_num_entries(vim);
+		    (*vim_idxp)++) {
+			vdev_indirect_mapping_entry_phys_t *vimep =
+			    &vim->vim_entries[*vim_idxp];
+			uint64_t ent_offset = DVA_MAPPING_GET_SRC_OFFSET(vimep);
+			uint64_t ent_len = DVA_GET_ASIZE(&vimep->vimep_dst);
+			ASSERT3U(ent_offset, >=, msp->ms_start);
+			if (ent_offset >= msp->ms_start + msp->ms_size)
+				break;
+
+			/*
+			 * Mappings do not cross metaslab boundaries,
+			 * because we create them by walking the metaslabs.
+			 */
+			ASSERT3U(ent_offset + ent_len, <=,
+			    msp->ms_start + msp->ms_size);
+			range_tree_add(msp->ms_tree, ent_offset, ent_len);
+		}
+	} else if (msp->ms_sm != NULL) {
+		VERIFY0(space_map_load(msp->ms_sm, msp->ms_tree, SM_ALLOC));
+	}
+
+	if (!msp->ms_loaded) {
+		msp->ms_loaded = B_TRUE;
+	}
+	mutex_exit(&msp->ms_lock);
+}
+
+/* ARGSUSED */
+static int
+increment_indirect_mapping_cb(void *arg, const blkptr_t *bp, dmu_tx_t *tx)
+{
+	zdb_cb_t *zcb = arg;
+	spa_t *spa = zcb->zcb_spa;
+	vdev_t *vd;
+	const dva_t *dva = &bp->blk_dva[0];
+
+	ASSERT(!dump_opt['L']);
+	ASSERT3U(BP_GET_NDVAS(bp), ==, 1);
+
+	spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
+	vd = vdev_lookup_top(zcb->zcb_spa, DVA_GET_VDEV(dva));
+	ASSERT3P(vd, !=, NULL);
+	spa_config_exit(spa, SCL_VDEV, FTAG);
+
+	ASSERT(vd->vdev_indirect_config.vic_mapping_object != 0);
+	ASSERT3P(zcb->zcb_vd_obsolete_counts[vd->vdev_id], !=, NULL);
+
+	vdev_indirect_mapping_increment_obsolete_count(
+	    vd->vdev_indirect_mapping,
+	    DVA_GET_OFFSET(dva), DVA_GET_ASIZE(dva),
+	    zcb->zcb_vd_obsolete_counts[vd->vdev_id]);
+
+	return (0);
+}
+
+static uint32_t *
+zdb_load_obsolete_counts(vdev_t *vd)
+{
+	vdev_indirect_mapping_t *vim = vd->vdev_indirect_mapping;
+	spa_t *spa = vd->vdev_spa;
+	spa_condensing_indirect_phys_t *scip =
+	    &spa->spa_condensing_indirect_phys;
+	uint32_t *counts;
+
+	EQUIV(vdev_obsolete_sm_object(vd) != 0, vd->vdev_obsolete_sm != NULL);
+	counts = vdev_indirect_mapping_load_obsolete_counts(vim);
+	if (vd->vdev_obsolete_sm != NULL) {
+		vdev_indirect_mapping_load_obsolete_spacemap(vim, counts,
+		    vd->vdev_obsolete_sm);
+	}
+	if (scip->scip_vdev == vd->vdev_id &&
+	    scip->scip_prev_obsolete_sm_object != 0) {
+		space_map_t *prev_obsolete_sm = NULL;
+		VERIFY0(space_map_open(&prev_obsolete_sm, spa->spa_meta_objset,
+		    scip->scip_prev_obsolete_sm_object, 0, vd->vdev_asize, 0));
+		space_map_update(prev_obsolete_sm);
+		vdev_indirect_mapping_load_obsolete_spacemap(vim, counts,
+		    prev_obsolete_sm);
+		space_map_close(prev_obsolete_sm);
+	}
+	return (counts);
+}
+
 static void
 zdb_leak_init(spa_t *spa, zdb_cb_t *zcb)
 {
 	zcb->zcb_spa = spa;
 
 	if (!dump_opt['L']) {
+		dsl_pool_t *dp = spa->spa_dsl_pool;
 		vdev_t *rvd = spa->spa_root_vdev;
 
 		/*
@@ -2813,50 +3143,51 @@ zdb_leak_init(spa_t *spa, zdb_cb_t *zcb)
 		spa->spa_normal_class->mc_ops = &zdb_metaslab_ops;
 		spa->spa_log_class->mc_ops = &zdb_metaslab_ops;
 
+		zcb->zcb_vd_obsolete_counts =
+		    umem_zalloc(rvd->vdev_children * sizeof (uint32_t *),
+		    UMEM_NOFAIL);
+
+
 		for (uint64_t c = 0; c < rvd->vdev_children; c++) {
 			vdev_t *vd = rvd->vdev_child[c];
-			metaslab_group_t *mg = vd->vdev_mg;
-			for (uint64_t m = 0; m < vd->vdev_ms_count; m++) {
-				metaslab_t *msp = vd->vdev_ms[m];
-				ASSERT3P(msp->ms_group, ==, mg);
-				mutex_enter(&msp->ms_lock);
-				metaslab_unload(msp);
+			uint64_t vim_idx = 0;
+
+			ASSERT3U(c, ==, vd->vdev_id);
+
+			/*
+			 * Note: we don't check for mapping leaks on
+			 * removing vdevs because their ms_tree's are
+			 * used to look for leaks in allocated space.
+			 */
+			if (vd->vdev_ops == &vdev_indirect_ops) {
+				zcb->zcb_vd_obsolete_counts[c] =
+				    zdb_load_obsolete_counts(vd);
 
 				/*
-				 * For leak detection, we overload the metaslab
-				 * ms_tree to contain allocated segments
-				 * instead of free segments. As a result,
-				 * we can't use the normal metaslab_load/unload
-				 * interfaces.
+				 * Normally, indirect vdevs don't have any
+				 * metaslabs.  We want to set them up for
+				 * zio_claim().
 				 */
-				if (msp->ms_sm != NULL) {
-					(void) fprintf(stderr,
-					    "\rloading space map for "
-					    "vdev %llu of %llu, "
-					    "metaslab %llu of %llu ...",
-					    (longlong_t)c,
-					    (longlong_t)rvd->vdev_children,
-					    (longlong_t)m,
-					    (longlong_t)vd->vdev_ms_count);
-
-					/*
-					 * We don't want to spend the CPU
-					 * manipulating the size-ordered
-					 * tree, so clear the range_tree
-					 * ops.
-					 */
-					msp->ms_tree->rt_ops = NULL;
-					VERIFY0(space_map_load(msp->ms_sm,
-					    msp->ms_tree, SM_ALLOC));
-
-					if (!msp->ms_loaded) {
-						msp->ms_loaded = B_TRUE;
-					}
-				}
-				mutex_exit(&msp->ms_lock);
+				VERIFY0(vdev_metaslab_init(vd, 0));
+			}
+
+			for (uint64_t m = 0; m < vd->vdev_ms_count; m++) {
+				zdb_leak_init_ms(vd->vdev_ms[m], &vim_idx);
+			}
+			if (vd->vdev_ops == &vdev_indirect_ops) {
+				ASSERT3U(vim_idx, ==,
+				    vdev_indirect_mapping_num_entries(
+				    vd->vdev_indirect_mapping));
 			}
 		}
 		(void) fprintf(stderr, "\n");
+
+		if (bpobj_is_open(&dp->dp_obsolete_bpobj)) {
+			ASSERT(spa_feature_is_enabled(spa,
+			    SPA_FEATURE_DEVICE_REMOVAL));
+			(void) bpobj_iterate_nofree(&dp->dp_obsolete_bpobj,
+			    increment_indirect_mapping_cb, zcb, NULL);
+		}
 	}
 
 	spa_config_enter(spa, SCL_CONFIG, FTAG, RW_READER);
@@ -2866,18 +3197,93 @@ zdb_leak_init(spa_t *spa, zdb_cb_t *zcb)
 	spa_config_exit(spa, SCL_CONFIG, FTAG);
 }
 
-static void
-zdb_leak_fini(spa_t *spa)
+static boolean_t
+zdb_check_for_obsolete_leaks(vdev_t *vd, zdb_cb_t *zcb)
+{
+	boolean_t leaks = B_FALSE;
+	vdev_indirect_mapping_t *vim = vd->vdev_indirect_mapping;
+	uint64_t total_leaked = 0;
+
+	ASSERT(vim != NULL);
+
+	for (uint64_t i = 0; i < vdev_indirect_mapping_num_entries(vim); i++) {
+		vdev_indirect_mapping_entry_phys_t *vimep =
+		    &vim->vim_entries[i];
+		uint64_t obsolete_bytes = 0;
+		uint64_t offset = DVA_MAPPING_GET_SRC_OFFSET(vimep);
+		metaslab_t *msp = vd->vdev_ms[offset >> vd->vdev_ms_shift];
+
+		/*
+		 * This is not very efficient but it's easy to
+		 * verify correctness.
+		 */
+		for (uint64_t inner_offset = 0;
+		    inner_offset < DVA_GET_ASIZE(&vimep->vimep_dst);
+		    inner_offset += 1 << vd->vdev_ashift) {
+			if (range_tree_contains(msp->ms_tree,
+			    offset + inner_offset, 1 << vd->vdev_ashift)) {
+				obsolete_bytes += 1 << vd->vdev_ashift;
+			}
+		}
+
+		int64_t bytes_leaked = obsolete_bytes -
+		    zcb->zcb_vd_obsolete_counts[vd->vdev_id][i];
+		ASSERT3U(DVA_GET_ASIZE(&vimep->vimep_dst), >=,
+		    zcb->zcb_vd_obsolete_counts[vd->vdev_id][i]);
+		if (bytes_leaked != 0 &&
+		    (vdev_obsolete_counts_are_precise(vd) ||
+		    dump_opt['d'] >= 5)) {
+			(void) printf("obsolete indirect mapping count "
+			    "mismatch on %llu:%llx:%llx : %llx bytes leaked\n",
+			    (u_longlong_t)vd->vdev_id,
+			    (u_longlong_t)DVA_MAPPING_GET_SRC_OFFSET(vimep),
+			    (u_longlong_t)DVA_GET_ASIZE(&vimep->vimep_dst),
+			    (u_longlong_t)bytes_leaked);
+		}
+		total_leaked += ABS(bytes_leaked);
+	}
+
+	if (!vdev_obsolete_counts_are_precise(vd) && total_leaked > 0) {
+		int pct_leaked = total_leaked * 100 /
+		    vdev_indirect_mapping_bytes_mapped(vim);
+		(void) printf("cannot verify obsolete indirect mapping "
+		    "counts of vdev %llu because precise feature was not "
+		    "enabled when it was removed: %d%% (%llx bytes) of mapping"
+		    "unreferenced\n",
+		    (u_longlong_t)vd->vdev_id, pct_leaked,
+		    (u_longlong_t)total_leaked);
+	} else if (total_leaked > 0) {
+		(void) printf("obsolete indirect mapping count mismatch "
+		    "for vdev %llu -- %llx total bytes mismatched\n",
+		    (u_longlong_t)vd->vdev_id,
+		    (u_longlong_t)total_leaked);
+		leaks |= B_TRUE;
+	}
+
+	vdev_indirect_mapping_free_obsolete_counts(vim,
+	    zcb->zcb_vd_obsolete_counts[vd->vdev_id]);
+	zcb->zcb_vd_obsolete_counts[vd->vdev_id] = NULL;
+
+	return (leaks);
+}
+
+static boolean_t
+zdb_leak_fini(spa_t *spa, zdb_cb_t *zcb)
 {
+	boolean_t leaks = B_FALSE;
 	if (!dump_opt['L']) {
 		vdev_t *rvd = spa->spa_root_vdev;
 		for (unsigned c = 0; c < rvd->vdev_children; c++) {
 			vdev_t *vd = rvd->vdev_child[c];
 			metaslab_group_t *mg = vd->vdev_mg;
-			for (unsigned m = 0; m < vd->vdev_ms_count; m++) {
+
+			if (zcb->zcb_vd_obsolete_counts[c] != NULL) {
+				leaks |= zdb_check_for_obsolete_leaks(vd, zcb);
+			}
+
+			for (uint64_t m = 0; m < vd->vdev_ms_count; m++) {
 				metaslab_t *msp = vd->vdev_ms[m];
 				ASSERT3P(mg, ==, msp->ms_group);
-				mutex_enter(&msp->ms_lock);
 
 				/*
 				 * The ms_tree has been overloaded to
@@ -2887,18 +3293,30 @@ zdb_leak_fini(spa_t *spa)
 				 * represents an allocated block that we
 				 * did not claim during the traversal.
 				 * Claimed blocks would have been removed
-				 * from the ms_tree.
+				 * from the ms_tree.  For indirect vdevs,
+				 * space remaining in the tree represents
+				 * parts of the mapping that are not
+				 * referenced, which is not a bug.
 				 */
-				range_tree_vacate(msp->ms_tree, zdb_leak, vd);
+				if (vd->vdev_ops == &vdev_indirect_ops) {
+					range_tree_vacate(msp->ms_tree,
+					    NULL, NULL);
+				} else {
+					range_tree_vacate(msp->ms_tree,
+					    zdb_leak, vd);
+				}
 
 				if (msp->ms_loaded) {
 					msp->ms_loaded = B_FALSE;
 				}
-
-				mutex_exit(&msp->ms_lock);
 			}
 		}
+
+		umem_free(zcb->zcb_vd_obsolete_counts,
+		    rvd->vdev_children * sizeof (uint32_t *));
+		zcb->zcb_vd_obsolete_counts = NULL;
 	}
+	return (leaks);
 }
 
 /* ARGSUSED */
@@ -2949,10 +3367,14 @@ dump_block_stats(spa_t *spa)
 	 */
 	(void) bpobj_iterate_nofree(&spa->spa_deferred_bpobj,
 	    count_block_cb, &zcb, NULL);
+
 	if (spa_version(spa) >= SPA_VERSION_DEADLISTS) {
 		(void) bpobj_iterate_nofree(&spa->spa_dsl_pool->dp_free_bpobj,
 		    count_block_cb, &zcb, NULL);
 	}
+
+	zdb_claim_removing(spa, &zcb);
+
 	if (spa_feature_is_active(spa, SPA_FEATURE_ASYNC_DESTROY)) {
 		VERIFY3U(0, ==, bptree_iterate(spa->spa_meta_objset,
 		    spa->spa_dsl_pool->dp_bptree_obj, B_FALSE, count_block_cb,
@@ -2994,7 +3416,7 @@ dump_block_stats(spa_t *spa)
 	/*
 	 * Report any leaked segments.
 	 */
-	zdb_leak_fini(spa);
+	leaks |= zdb_leak_fini(spa, &zcb);
 
 	tzb = &zcb.zcb_type[ZB_TOTAL][ZDB_OT_TOTAL];
 
@@ -3002,7 +3424,8 @@ dump_block_stats(spa_t *spa)
 	norm_space = metaslab_class_get_space(spa_normal_class(spa));
 
 	total_alloc = norm_alloc + metaslab_class_get_alloc(spa_log_class(spa));
-	total_found = tzb->zb_asize - zcb.zcb_dedup_asize;
+	total_found = tzb->zb_asize - zcb.zcb_dedup_asize +
+	    zcb.zcb_removing_size;
 
 	if (total_found == total_alloc) {
 		if (!dump_opt['L'])
@@ -3069,6 +3492,24 @@ dump_block_stats(spa_t *spa)
 		    (longlong_t)tzb->zb_ditto_samevdev);
 	}
 
+	for (uint64_t v = 0; v < spa->spa_root_vdev->vdev_children; v++) {
+		vdev_t *vd = spa->spa_root_vdev->vdev_child[v];
+		vdev_indirect_mapping_t *vim = vd->vdev_indirect_mapping;
+
+		if (vim == NULL) {
+			continue;
+		}
+
+		char mem[32];
+		zdb_nicenum(vdev_indirect_mapping_num_entries(vim),
+		    mem, vdev_indirect_mapping_size(vim));
+
+		(void) printf("\tindirect vdev id %llu has %llu segments "
+		    "(%s in memory)\n",
+		    (longlong_t)vd->vdev_id,
+		    (longlong_t)vdev_indirect_mapping_num_entries(vim), mem);
+	}
+
 	if (dump_opt['b'] >= 2) {
 		int l, t, level;
 		(void) printf("\nBlocks\tLSIZE\tPSIZE\tASIZE"
@@ -3275,6 +3716,124 @@ dump_simulated_ddt(spa_t *spa)
 	dump_dedup_ratio(&dds_total);
 }
 
+static int
+verify_device_removal_feature_counts(spa_t *spa)
+{
+	uint64_t dr_feature_refcount = 0;
+	uint64_t oc_feature_refcount = 0;
+	uint64_t indirect_vdev_count = 0;
+	uint64_t precise_vdev_count = 0;
+	uint64_t obsolete_counts_object_count = 0;
+	uint64_t obsolete_sm_count = 0;
+	uint64_t obsolete_counts_count = 0;
+	uint64_t scip_count = 0;
+	uint64_t obsolete_bpobj_count = 0;
+	int ret = 0;
+
+	spa_condensing_indirect_phys_t *scip =
+	    &spa->spa_condensing_indirect_phys;
+	if (scip->scip_next_mapping_object != 0) {
+		vdev_t *vd = spa->spa_root_vdev->vdev_child[scip->scip_vdev];
+		ASSERT(scip->scip_prev_obsolete_sm_object != 0);
+		ASSERT3P(vd->vdev_ops, ==, &vdev_indirect_ops);
+
+		(void) printf("Condensing indirect vdev %llu: new mapping "
+		    "object %llu, prev obsolete sm %llu\n",
+		    (u_longlong_t)scip->scip_vdev,
+		    (u_longlong_t)scip->scip_next_mapping_object,
+		    (u_longlong_t)scip->scip_prev_obsolete_sm_object);
+		if (scip->scip_prev_obsolete_sm_object != 0) {
+			space_map_t *prev_obsolete_sm = NULL;
+			VERIFY0(space_map_open(&prev_obsolete_sm,
+			    spa->spa_meta_objset,
+			    scip->scip_prev_obsolete_sm_object,
+			    0, vd->vdev_asize, 0));
+			space_map_update(prev_obsolete_sm);
+			dump_spacemap(spa->spa_meta_objset, prev_obsolete_sm);
+			(void) printf("\n");
+			space_map_close(prev_obsolete_sm);
+		}
+
+		scip_count += 2;
+	}
+
+	for (uint64_t i = 0; i < spa->spa_root_vdev->vdev_children; i++) {
+		vdev_t *vd = spa->spa_root_vdev->vdev_child[i];
+		vdev_indirect_config_t *vic = &vd->vdev_indirect_config;
+
+		if (vic->vic_mapping_object != 0) {
+			ASSERT(vd->vdev_ops == &vdev_indirect_ops ||
+			    vd->vdev_removing);
+			indirect_vdev_count++;
+
+			if (vd->vdev_indirect_mapping->vim_havecounts) {
+				obsolete_counts_count++;
+			}
+		}
+		if (vdev_obsolete_counts_are_precise(vd)) {
+			ASSERT(vic->vic_mapping_object != 0);
+			precise_vdev_count++;
+		}
+		if (vdev_obsolete_sm_object(vd) != 0) {
+			ASSERT(vic->vic_mapping_object != 0);
+			obsolete_sm_count++;
+		}
+	}
+
+	(void) feature_get_refcount(spa,
+	    &spa_feature_table[SPA_FEATURE_DEVICE_REMOVAL],
+	    &dr_feature_refcount);
+	(void) feature_get_refcount(spa,
+	    &spa_feature_table[SPA_FEATURE_OBSOLETE_COUNTS],
+	    &oc_feature_refcount);
+
+	if (dr_feature_refcount != indirect_vdev_count) {
+		ret = 1;
+		(void) printf("Number of indirect vdevs (%llu) " \
+		    "does not match feature count (%llu)\n",
+		    (u_longlong_t)indirect_vdev_count,
+		    (u_longlong_t)dr_feature_refcount);
+	} else {
+		(void) printf("Verified device_removal feature refcount " \
+		    "of %llu is correct\n",
+		    (u_longlong_t)dr_feature_refcount);
+	}
+
+	if (zap_contains(spa_meta_objset(spa), DMU_POOL_DIRECTORY_OBJECT,
+	    DMU_POOL_OBSOLETE_BPOBJ) == 0) {
+		obsolete_bpobj_count++;
+	}
+
+
+	obsolete_counts_object_count = precise_vdev_count;
+	obsolete_counts_object_count += obsolete_sm_count;
+	obsolete_counts_object_count += obsolete_counts_count;
+	obsolete_counts_object_count += scip_count;
+	obsolete_counts_object_count += obsolete_bpobj_count;
+	obsolete_counts_object_count += remap_deadlist_count;
+
+	if (oc_feature_refcount != obsolete_counts_object_count) {
+		ret = 1;
+		(void) printf("Number of obsolete counts objects (%llu) " \
+		    "does not match feature count (%llu)\n",
+		    (u_longlong_t)obsolete_counts_object_count,
+		    (u_longlong_t)oc_feature_refcount);
+		(void) printf("pv:%llu os:%llu oc:%llu sc:%llu "
+		    "ob:%llu rd:%llu\n",
+		    (u_longlong_t)precise_vdev_count,
+		    (u_longlong_t)obsolete_sm_count,
+		    (u_longlong_t)obsolete_counts_count,
+		    (u_longlong_t)scip_count,
+		    (u_longlong_t)obsolete_bpobj_count,
+		    (u_longlong_t)remap_deadlist_count);
+	} else {
+		(void) printf("Verified indirect_refcount feature refcount " \
+		    "of %llu is correct\n",
+		    (u_longlong_t)oc_feature_refcount);
+	}
+	return (ret);
+}
+
 static void
 dump_zpool(spa_t *spa)
 {
@@ -3308,18 +3867,24 @@ dump_zpool(spa_t *spa)
 	if (dump_opt['d'] || dump_opt['i']) {
 		dump_dir(dp->dp_meta_objset);
 		if (dump_opt['d'] >= 3) {
+			dsl_pool_t *dp = spa->spa_dsl_pool;
 			dump_full_bpobj(&spa->spa_deferred_bpobj,
 			    "Deferred frees", 0);
 			if (spa_version(spa) >= SPA_VERSION_DEADLISTS) {
-				dump_full_bpobj(
-				    &spa->spa_dsl_pool->dp_free_bpobj,
+				dump_full_bpobj(&dp->dp_free_bpobj,
 				    "Pool snapshot frees", 0);
 			}
+			if (bpobj_is_open(&dp->dp_obsolete_bpobj)) {
+				ASSERT(spa_feature_is_enabled(spa,
+				    SPA_FEATURE_DEVICE_REMOVAL));
+				dump_full_bpobj(&dp->dp_obsolete_bpobj,
+				    "Pool obsolete blocks", 0);
+			}
 
 			if (spa_feature_is_active(spa,
 			    SPA_FEATURE_ASYNC_DESTROY)) {
 				dump_bptree(spa->spa_meta_objset,
-				    spa->spa_dsl_pool->dp_bptree_obj,
+				    dp->dp_bptree_obj,
 				    "Pool dataset frees");
 			}
 			dump_dtl(spa->spa_root_vdev, 0);
@@ -3351,6 +3916,10 @@ dump_zpool(spa_t *spa)
 				    (longlong_t)refcount);
 			}
 		}
+
+		if (rc == 0) {
+			rc = verify_device_removal_feature_counts(spa);
+		}
 	}
 	if (rc == 0 && (dump_opt['b'] || dump_opt['c']))
 		rc = dump_block_stats(spa);
@@ -3661,7 +4230,8 @@ zdb_read_block(char *thing, spa_t *spa)
 		    psize, ZIO_TYPE_READ, ZIO_PRIORITY_SYNC_READ,
 		    ZIO_FLAG_DONT_CACHE | ZIO_FLAG_DONT_QUEUE |
 		    ZIO_FLAG_DONT_PROPAGATE | ZIO_FLAG_DONT_RETRY |
-		    ZIO_FLAG_CANFAIL | ZIO_FLAG_RAW, NULL, NULL));
+		    ZIO_FLAG_CANFAIL | ZIO_FLAG_RAW | ZIO_FLAG_OPTIONAL,
+		    NULL, NULL));
 	}
 
 	error = zio_wait(zio);
diff --git a/cddl/contrib/opensolaris/cmd/zfs/zfs_main.c b/cddl/contrib/opensolaris/cmd/zfs/zfs_main.c
index be4df07..7939bce 100644
--- a/cddl/contrib/opensolaris/cmd/zfs/zfs_main.c
+++ b/cddl/contrib/opensolaris/cmd/zfs/zfs_main.c
@@ -112,6 +112,7 @@ static int zfs_do_diff(int argc, char **argv);
 static int zfs_do_jail(int argc, char **argv);
 static int zfs_do_unjail(int argc, char **argv);
 static int zfs_do_bookmark(int argc, char **argv);
+static int zfs_do_remap(int argc, char **argv);
 static int zfs_do_channel_program(int argc, char **argv);
 
 /*
@@ -161,6 +162,7 @@ typedef enum {
 	HELP_HOLDS,
 	HELP_RELEASE,
 	HELP_DIFF,
+	HELP_REMAP,
 	HELP_BOOKMARK,
 	HELP_CHANNEL_PROGRAM,
 } zfs_help_t;
@@ -220,6 +222,7 @@ static zfs_command_t command_table[] = {
 	{ NULL },
 	{ "jail",	zfs_do_jail,		HELP_JAIL		},
 	{ "unjail",	zfs_do_unjail,		HELP_UNJAIL		},
+	{ "remap",	zfs_do_remap,		HELP_REMAP		},
 };
 
 #define	NCOMMAND	(sizeof (command_table) / sizeof (command_table[0]))
@@ -342,6 +345,8 @@ get_usage(zfs_help_t idx)
 	case HELP_DIFF:
 		return (gettext("\tdiff [-FHt] <snapshot> "
 		    "[snapshot|filesystem]\n"));
+	case HELP_REMAP:
+		return (gettext("\tremap <filesystem | volume>\n"));
 	case HELP_BOOKMARK:
 		return (gettext("\tbookmark <snapshot> <bookmark>\n"));
 	case HELP_CHANNEL_PROGRAM:
@@ -4170,6 +4175,7 @@ zfs_do_receive(int argc, char **argv)
 #define	ZFS_DELEG_PERM_RELEASE		"release"
 #define	ZFS_DELEG_PERM_DIFF		"diff"
 #define	ZFS_DELEG_PERM_BOOKMARK		"bookmark"
+#define	ZFS_DELEG_PERM_REMAP		"remap"
 
 #define	ZFS_NUM_DELEG_NOTES ZFS_DELEG_NOTE_NONE
 
@@ -4190,6 +4196,7 @@ static zfs_deleg_perm_tab_t zfs_deleg_perm_tbl[] = {
 	{ ZFS_DELEG_PERM_SHARE, ZFS_DELEG_NOTE_SHARE },
 	{ ZFS_DELEG_PERM_SNAPSHOT, ZFS_DELEG_NOTE_SNAPSHOT },
 	{ ZFS_DELEG_PERM_BOOKMARK, ZFS_DELEG_NOTE_BOOKMARK },
+	{ ZFS_DELEG_PERM_REMAP, ZFS_DELEG_NOTE_REMAP },
 
 	{ ZFS_DELEG_PERM_GROUPQUOTA, ZFS_DELEG_NOTE_GROUPQUOTA },
 	{ ZFS_DELEG_PERM_GROUPUSED, ZFS_DELEG_NOTE_GROUPUSED },
@@ -6978,7 +6985,7 @@ zfs_do_diff(int argc, char **argv)
 
 	if (argc < 1) {
 		(void) fprintf(stderr,
-		gettext("must provide at least one snapshot name\n"));
+		    gettext("must provide at least one snapshot name\n"));
 		usage(B_FALSE);
 	}
 
@@ -7019,6 +7026,22 @@ zfs_do_diff(int argc, char **argv)
 	return (err != 0);
 }
 
+static int
+zfs_do_remap(int argc, char **argv)
+{
+	const char *fsname;
+	int err = 0;
+	if (argc != 2) {
+		(void) fprintf(stderr, gettext("wrong number of arguments\n"));
+		usage(B_FALSE);
+	}
+
+	fsname = argv[1];
+	err = zfs_remap_indirects(g_zfs, fsname);
+
+	return (err);
+}
+
 /*
  * zfs bookmark <fs@snap> <fs#bmark>
  *
diff --git a/cddl/contrib/opensolaris/cmd/zpool/zpool_main.c b/cddl/contrib/opensolaris/cmd/zpool/zpool_main.c
index b7b0825..66cc98b 100644
--- a/cddl/contrib/opensolaris/cmd/zpool/zpool_main.c
+++ b/cddl/contrib/opensolaris/cmd/zpool/zpool_main.c
@@ -21,7 +21,7 @@
 
 /*
  * Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2016 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2018 by Delphix. All rights reserved.
  * Copyright (c) 2012 by Frederik Wessels. All rights reserved.
  * Copyright (c) 2012 Martin Matuska <mm@FreeBSD.org>. All rights reserved.
  * Copyright (c) 2013 by Prasad Joshi (sTec). All rights reserved.
@@ -250,7 +250,7 @@ get_usage(zpool_help_t idx)
 		return (gettext("\treplace [-f] <pool> <device> "
 		    "[new-device]\n"));
 	case HELP_REMOVE:
-		return (gettext("\tremove <pool> <device> ...\n"));
+		return (gettext("\tremove [-nps] <pool> <device> ...\n"));
 	case HELP_REOPEN:
 		return (gettext("\treopen <pool>\n"));
 	case HELP_SCRUB:
@@ -599,8 +599,7 @@ zpool_do_add(int argc, char **argv)
 /*
  * zpool remove  <pool> <vdev> ...
  *
- * Removes the given vdev from the pool.  Currently, this supports removing
- * spares, cache, and log devices from the pool.
+ * Removes the given vdev from the pool.
  */
 int
 zpool_do_remove(int argc, char **argv)
@@ -608,28 +607,87 @@ zpool_do_remove(int argc, char **argv)
 	char *poolname;
 	int i, ret = 0;
 	zpool_handle_t *zhp;
+	boolean_t stop = B_FALSE;
+	boolean_t noop = B_FALSE;
+	boolean_t parsable = B_FALSE;
+	char c;
 
-	argc--;
-	argv++;
+	/* check options */
+	while ((c = getopt(argc, argv, "nps")) != -1) {
+		switch (c) {
+		case 'n':
+			noop = B_TRUE;
+			break;
+		case 'p':
+			parsable = B_TRUE;
+			break;
+		case 's':
+			stop = B_TRUE;
+			break;
+		case '?':
+			(void) fprintf(stderr, gettext("invalid option '%c'\n"),
+			    optopt);
+			usage(B_FALSE);
+		}
+	}
+
+	argc -= optind;
+	argv += optind;
 
 	/* get pool name and check number of arguments */
 	if (argc < 1) {
 		(void) fprintf(stderr, gettext("missing pool name argument\n"));
 		usage(B_FALSE);
 	}
-	if (argc < 2) {
-		(void) fprintf(stderr, gettext("missing device\n"));
-		usage(B_FALSE);
-	}
 
 	poolname = argv[0];
 
 	if ((zhp = zpool_open(g_zfs, poolname)) == NULL)
 		return (1);
 
-	for (i = 1; i < argc; i++) {
-		if (zpool_vdev_remove(zhp, argv[i]) != 0)
+	if (stop && noop) {
+		(void) fprintf(stderr, gettext("stop request ignored\n"));
+		return (0);
+	}
+
+	if (stop) {
+		if (argc > 1) {
+			(void) fprintf(stderr, gettext("too many arguments\n"));
+			usage(B_FALSE);
+		}
+		if (zpool_vdev_remove_cancel(zhp) != 0)
 			ret = 1;
+	} else {
+		if (argc < 2) {
+			(void) fprintf(stderr, gettext("missing device\n"));
+			usage(B_FALSE);
+		}
+
+		for (i = 1; i < argc; i++) {
+			if (noop) {
+				uint64_t size;
+
+				if (zpool_vdev_indirect_size(zhp, argv[i],
+				    &size) != 0) {
+					ret = 1;
+					break;
+				}
+				if (parsable) {
+					(void) printf("%s %llu\n",
+					    argv[i], size);
+				} else {
+					char valstr[32];
+					zfs_nicenum(size, valstr,
+					    sizeof (valstr));
+					(void) printf("Memory that will be "
+					    "used after removing %s: %s\n",
+					    argv[i], valstr);
+				}
+			} else {
+				if (zpool_vdev_remove(zhp, argv[i]) != 0)
+					ret = 1;
+			}
+		}
 	}
 
 	return (ret);
@@ -1416,6 +1474,7 @@ print_status_config(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
 	uint64_t ashift;
 	spare_cbdata_t cb;
 	const char *state;
+	char *type;
 
 	if (nvlist_lookup_nvlist_array(nv, ZPOOL_CONFIG_CHILDREN,
 	    &child, &children) != 0)
@@ -1424,6 +1483,11 @@ print_status_config(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
 	verify(nvlist_lookup_uint64_array(nv, ZPOOL_CONFIG_VDEV_STATS,
 	    (uint64_t **)&vs, &vsc) == 0);
 
+	verify(nvlist_lookup_string(nv, ZPOOL_CONFIG_TYPE, &type) == 0);
+
+	if (strcmp(type, VDEV_TYPE_INDIRECT) == 0)
+		return;
+
 	state = zpool_state_to_name(vs->vs_state, vs->vs_aux);
 	if (isspare) {
 		/*
@@ -2454,6 +2518,9 @@ print_vdev_stats(zpool_handle_t *zhp, const char *name, nvlist_t *oldnv,
 	double scale;
 	char *vname;
 
+	if (strcmp(name, VDEV_TYPE_INDIRECT) == 0)
+		return;
+
 	if (oldnv != NULL) {
 		verify(nvlist_lookup_uint64_array(oldnv,
 		    ZPOOL_CONFIG_VDEV_STATS, (uint64_t **)&oldvs, &c) == 0);
@@ -3060,6 +3127,9 @@ print_list_stats(zpool_handle_t *zhp, const char *name, nvlist_t *nv,
 		boolean_t toplevel = (vs->vs_space != 0);
 		uint64_t cap;
 
+		if (strcmp(name, VDEV_TYPE_INDIRECT) == 0)
+			return;
+
 		if (scripted)
 			(void) printf("\t%s", name);
 		else if (strlen(name) + depth > cb->cb_namewidth)
@@ -3998,7 +4068,7 @@ typedef struct status_cbdata {
 /*
  * Print out detailed scrub status.
  */
-void
+static void
 print_scan_status(pool_scan_stat_t *ps)
 {
 	time_t start, end, pause;
@@ -4124,6 +4194,111 @@ print_scan_status(pool_scan_stat_t *ps)
 	}
 }
 
+/*
+ * Print out detailed removal status.
+ */
+static void
+print_removal_status(zpool_handle_t *zhp, pool_removal_stat_t *prs)
+{
+	char copied_buf[7], examined_buf[7], total_buf[7], rate_buf[7];
+	time_t start, end;
+	nvlist_t *config, *nvroot;
+	nvlist_t **child;
+	uint_t children;
+	char *vdev_name;
+
+	if (prs == NULL || prs->prs_state == DSS_NONE)
+		return;
+
+	/*
+	 * Determine name of vdev.
+	 */
+	config = zpool_get_config(zhp, NULL);
+	nvroot = fnvlist_lookup_nvlist(config,
+	    ZPOOL_CONFIG_VDEV_TREE);
+	verify(nvlist_lookup_nvlist_array(nvroot, ZPOOL_CONFIG_CHILDREN,
+	    &child, &children) == 0);
+	assert(prs->prs_removing_vdev < children);
+	vdev_name = zpool_vdev_name(g_zfs, zhp,
+	    child[prs->prs_removing_vdev], B_TRUE);
+
+	(void) printf(gettext("remove: "));
+
+	start = prs->prs_start_time;
+	end = prs->prs_end_time;
+	zfs_nicenum(prs->prs_copied, copied_buf, sizeof (copied_buf));
+
+	/*
+	 * Removal is finished or canceled.
+	 */
+	if (prs->prs_state == DSS_FINISHED) {
+		uint64_t minutes_taken = (end - start) / 60;
+
+		(void) printf(gettext("Removal of vdev %llu copied %s "
+		    "in %lluh%um, completed on %s"),
+		    (longlong_t)prs->prs_removing_vdev,
+		    copied_buf,
+		    (u_longlong_t)(minutes_taken / 60),
+		    (uint_t)(minutes_taken % 60),
+		    ctime((time_t *)&end));
+	} else if (prs->prs_state == DSS_CANCELED) {
+		(void) printf(gettext("Removal of %s canceled on %s"),
+		    vdev_name, ctime(&end));
+	} else {
+		uint64_t copied, total, elapsed, mins_left, hours_left;
+		double fraction_done;
+		uint_t rate;
+
+		assert(prs->prs_state == DSS_SCANNING);
+
+		/*
+		 * Removal is in progress.
+		 */
+		(void) printf(gettext(
+		    "Evacuation of %s in progress since %s"),
+		    vdev_name, ctime(&start));
+
+		copied = prs->prs_copied > 0 ? prs->prs_copied : 1;
+		total = prs->prs_to_copy;
+		fraction_done = (double)copied / total;
+
+		/* elapsed time for this pass */
+		elapsed = time(NULL) - prs->prs_start_time;
+		elapsed = elapsed > 0 ? elapsed : 1;
+		rate = copied / elapsed;
+		rate = rate > 0 ? rate : 1;
+		mins_left = ((total - copied) / rate) / 60;
+		hours_left = mins_left / 60;
+
+		zfs_nicenum(copied, examined_buf, sizeof (examined_buf));
+		zfs_nicenum(total, total_buf, sizeof (total_buf));
+		zfs_nicenum(rate, rate_buf, sizeof (rate_buf));
+
+		/*
+		 * do not print estimated time if hours_left is more than
+		 * 30 days
+		 */
+		(void) printf(gettext("    %s copied out of %s at %s/s, "
+		    "%.2f%% done"),
+		    examined_buf, total_buf, rate_buf, 100 * fraction_done);
+		if (hours_left < (30 * 24)) {
+			(void) printf(gettext(", %lluh%um to go\n"),
+			    (u_longlong_t)hours_left, (uint_t)(mins_left % 60));
+		} else {
+			(void) printf(gettext(
+			    ", (copy is slow, no estimated time)\n"));
+		}
+	}
+
+	if (prs->prs_mapping_memory > 0) {
+		char mem_buf[7];
+		zfs_nicenum(prs->prs_mapping_memory, mem_buf, sizeof (mem_buf));
+		(void) printf(gettext("    %s memory used for "
+		    "removed device mappings\n"),
+		    mem_buf);
+	}
+}
+
 static void
 print_error_log(zpool_handle_t *zhp)
 {
@@ -4289,8 +4464,7 @@ status_callback(zpool_handle_t *zhp, void *data)
 	else
 		(void) printf("\n");
 
-	verify(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
-	    &nvroot) == 0);
+	nvroot = fnvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE);
 	verify(nvlist_lookup_uint64_array(nvroot, ZPOOL_CONFIG_VDEV_STATS,
 	    (uint64_t **)&vs, &c) == 0);
 	health = zpool_state_to_name(vs->vs_state, vs->vs_aux);
@@ -4507,11 +4681,16 @@ status_callback(zpool_handle_t *zhp, void *data)
 		nvlist_t **spares, **l2cache;
 		uint_t nspares, nl2cache;
 		pool_scan_stat_t *ps = NULL;
+		pool_removal_stat_t *prs = NULL;
 
 		(void) nvlist_lookup_uint64_array(nvroot,
 		    ZPOOL_CONFIG_SCAN_STATS, (uint64_t **)&ps, &c);
 		print_scan_status(ps);
 
+		(void) nvlist_lookup_uint64_array(nvroot,
+		    ZPOOL_CONFIG_REMOVAL_STATS, (uint64_t **)&prs, &c);
+		print_removal_status(zhp, prs);
+
 		namewidth = max_width(zhp, nvroot, 0, 0);
 		if (namewidth < 10)
 			namewidth = 10;
diff --git a/cddl/contrib/opensolaris/cmd/ztest/ztest.c b/cddl/contrib/opensolaris/cmd/ztest/ztest.c
index 79209f5..ecc3ce6 100644
--- a/cddl/contrib/opensolaris/cmd/ztest/ztest.c
+++ b/cddl/contrib/opensolaris/cmd/ztest/ztest.c
@@ -343,6 +343,8 @@ ztest_func_t ztest_vdev_aux_add_remove;
 ztest_func_t ztest_split_pool;
 ztest_func_t ztest_reguid;
 ztest_func_t ztest_spa_upgrade;
+ztest_func_t ztest_device_removal;
+ztest_func_t ztest_remap_blocks;
 
 uint64_t zopt_always = 0ULL * NANOSEC;		/* all the time */
 uint64_t zopt_incessant = 1ULL * NANOSEC / 10;	/* every 1/10 second */
@@ -384,6 +386,8 @@ ztest_info_t ztest_info[] = {
 	    &ztest_opts.zo_vdevtime				},
 	{ ztest_vdev_aux_add_remove,		1,
 	    &ztest_opts.zo_vdevtime				},
+	{ ztest_device_removal,			1,	&zopt_sometimes	},
+	{ ztest_remap_blocks,			1,	&zopt_sometimes }
 };
 
 #define	ZTEST_FUNCS	(sizeof (ztest_info) / sizeof (ztest_info_t))
@@ -786,10 +790,10 @@ ztest_kill(ztest_shared_t *zs)
 
 	/*
 	 * Before we kill off ztest, make sure that the config is updated.
-	 * See comment above spa_config_sync().
+	 * See comment above spa_write_cachefile().
 	 */
 	mutex_enter(&spa_namespace_lock);
-	spa_config_sync(ztest_spa, B_FALSE, B_FALSE);
+	spa_write_cachefile(ztest_spa, B_FALSE, B_FALSE);
 	mutex_exit(&spa_namespace_lock);
 
 	zfs_dbgmsg_print(FTAG);
@@ -1016,7 +1020,7 @@ ztest_random_vdev_top(spa_t *spa, boolean_t log_ok)
 	do {
 		top = ztest_random(rvd->vdev_children);
 		tvd = rvd->vdev_child[top];
-	} while (tvd->vdev_ishole || (tvd->vdev_islog && !log_ok) ||
+	} while (!vdev_is_concrete(tvd) || (tvd->vdev_islog && !log_ok) ||
 	    tvd->vdev_mg == NULL || tvd->vdev_mg->mg_class == NULL);
 
 	return (top);
@@ -2785,7 +2789,19 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
 	VERIFY(mutex_lock(&ztest_vdev_lock) == 0);
 	leaves = MAX(zs->zs_mirrors, 1) * ztest_opts.zo_raidz;
 
-	spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
+	spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
+
+	/*
+	 * If a vdev is in the process of being removed, its removal may
+	 * finish while we are in progress, leading to an unexpected error
+	 * value.  Don't bother trying to attach while we are in the middle
+	 * of removal.
+	 */
+	if (spa->spa_vdev_removal != NULL) {
+		spa_config_exit(spa, SCL_ALL, FTAG);
+		VERIFY(mutex_unlock(&ztest_vdev_lock) == 0);
+		return;
+	}
 
 	/*
 	 * Decide whether to do an attach or a replace.
@@ -2838,7 +2854,7 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
 	 * If oldvd has siblings, then half of the time, detach it.
 	 */
 	if (oldvd_has_siblings && ztest_random(2) == 0) {
-		spa_config_exit(spa, SCL_VDEV, FTAG);
+		spa_config_exit(spa, SCL_ALL, FTAG);
 		error = spa_vdev_detach(spa, oldguid, pguid, B_FALSE);
 		if (error != 0 && error != ENODEV && error != EBUSY &&
 		    error != ENOTSUP)
@@ -2865,6 +2881,10 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
 	}
 
 	if (newvd) {
+		/*
+		 * Reopen to ensure the vdev's asize field isn't stale.
+		 */
+		vdev_reopen(newvd);
 		newsize = vdev_get_min_asize(newvd);
 	} else {
 		/*
@@ -2902,7 +2922,7 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
 	else
 		expected_error = 0;
 
-	spa_config_exit(spa, SCL_VDEV, FTAG);
+	spa_config_exit(spa, SCL_ALL, FTAG);
 
 	/*
 	 * Build the nvlist describing newpath.
@@ -2940,6 +2960,26 @@ ztest_vdev_attach_detach(ztest_ds_t *zd, uint64_t id)
 	VERIFY(mutex_unlock(&ztest_vdev_lock) == 0);
 }
 
+/* ARGSUSED */
+void
+ztest_device_removal(ztest_ds_t *zd, uint64_t id)
+{
+	spa_t *spa = ztest_spa;
+	vdev_t *vd;
+	uint64_t guid;
+
+	VERIFY(mutex_lock(&ztest_vdev_lock) == 0);
+
+	spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
+	vd = vdev_lookup_top(spa, ztest_random_vdev_top(spa, B_FALSE));
+	guid = vd->vdev_guid;
+	spa_config_exit(spa, SCL_VDEV, FTAG);
+
+	(void) spa_vdev_remove(spa, guid, B_FALSE);
+
+	VERIFY(mutex_unlock(&ztest_vdev_lock) == 0);
+}
+
 /*
  * Callback function which expands the physical size of the vdev.
  */
@@ -3068,6 +3108,18 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
 	VERIFY(mutex_lock(&ztest_vdev_lock) == 0);
 	spa_config_enter(spa, SCL_STATE, spa, RW_READER);
 
+	/*
+	 * If there is a vdev removal in progress, it could complete while
+	 * we are running, in which case we would not be able to verify
+	 * that the metaslab_class space increased (because it decreases
+	 * when the device removal completes).
+	 */
+	if (spa->spa_vdev_removal != NULL) {
+		spa_config_exit(spa, SCL_STATE, FTAG);
+		VERIFY(mutex_unlock(&ztest_vdev_lock) == 0);
+		return;
+	}
+
 	top = ztest_random_vdev_top(spa, B_TRUE);
 
 	tvd = spa->spa_root_vdev->vdev_child[top];
@@ -3159,16 +3211,18 @@ ztest_vdev_LUN_growth(ztest_ds_t *zd, uint64_t id)
 	/*
 	 * Make sure we were able to grow the vdev.
 	 */
-	if (new_ms_count <= old_ms_count)
-		fatal(0, "LUN expansion failed: ms_count %llu <= %llu\n",
+	if (new_ms_count <= old_ms_count) {
+		fatal(0, "LUN expansion failed: ms_count %llu < %llu\n",
 		    old_ms_count, new_ms_count);
+	}
 
 	/*
 	 * Make sure we were able to grow the pool.
 	 */
-	if (new_class_space <= old_class_space)
-		fatal(0, "LUN expansion failed: class_space %llu <= %llu\n",
+	if (new_class_space <= old_class_space) {
+		fatal(0, "LUN expansion failed: class_space %llu < %llu\n",
 		    old_class_space, new_class_space);
+	}
 
 	if (ztest_opts.zo_verbose >= 5) {
 		char oldnumbuf[NN_NUMBUF_SZ], newnumbuf[NN_NUMBUF_SZ];
@@ -4637,6 +4691,20 @@ ztest_dsl_prop_get_set(ztest_ds_t *zd, uint64_t id)
 
 /* ARGSUSED */
 void
+ztest_remap_blocks(ztest_ds_t *zd, uint64_t id)
+{
+	(void) rw_rdlock(&ztest_name_lock);
+
+	int error = dmu_objset_remap_indirects(zd->zd_name);
+	if (error == ENOSPC)
+		error = 0;
+	ASSERT0(error);
+
+	(void) rw_unlock(&ztest_name_lock);
+}
+
+/* ARGSUSED */
+void
 ztest_spa_prop_get_set(ztest_ds_t *zd, uint64_t id)
 {
 	nvlist_t *props = NULL;
@@ -4886,6 +4954,9 @@ ztest_fault_inject(ztest_ds_t *zd, uint64_t id)
 			 */
 			vdev_file_t *vf = vd0->vdev_tsd;
 
+			zfs_dbgmsg("injecting fault to vdev %llu; maxfaults=%d",
+			    (long long)vd0->vdev_id, (int)maxfaults);
+
 			if (vf != NULL && ztest_random(3) == 0) {
 				(void) close(vf->vf_vnode->v_fd);
 				vf->vf_vnode->v_fd = -1;