Los vdevs

	uint64_t	vdev_state;	/* see VDEV_STATE_* #defines	*/
	uint64_t	vdev_prevstate;	/* used when reopening a vdev	*/
	vdev_ops_t	*vdev_ops;	/* vdev operations		*/
	spa_t		*vdev_spa;	/* spa for this vdev		*/
	void		*vdev_tsd;	/* type-specific data		*/
	vdev_t		*vdev_top;	/* top-level vdev		*/
	vdev_t		*vdev_parent;	/* parent vdev			*/
	vdev_t		**vdev_child;	/* array of children		*/
	uint64_t	vdev_children;	/* number of children		*/
	vdev_stat_t	vdev_stat;	/* virtual device statistics	*/
	vdev_stat_ex_t	vdev_stat_ex;	/* extended statistics		*/
	boolean_t	vdev_expanding;	/* expand the vdev?		*/
	boolean_t	vdev_reopening;	/* reopen in progress?		*/
	boolean_t	vdev_nonrot;	/* true if solid state		*/
	int		vdev_load_error; /* error on last load		*/
	int		vdev_open_error; /* error on last open		*/
	int		vdev_validate_error; /* error on last validate	*/
	kthread_t	*vdev_open_thread; /* thread opening children	*/
	kthread_t	*vdev_validate_thread; /* thread validating children */
	uint64_t	vdev_crtxg;	/* txg when top-level was added */
	uint64_t	vdev_root_zap;

	/*
	 * Top-level vdev state.
	 */
	uint64_t	vdev_ms_array;	/* metaslab array object	*/
	uint64_t	vdev_ms_shift;	/* metaslab size shift		*/
	uint64_t	vdev_ms_count;	/* number of metaslabs		*/
	metaslab_group_t *vdev_mg;	/* metaslab group		*/
	metaslab_group_t *vdev_log_mg;	/* embedded slog metaslab group	*/
	metaslab_t	**vdev_ms;	/* metaslab array		*/

typedef const struct vdev_ops {
	vdev_init_func_t		*vdev_op_init;
	vdev_fini_func_t		*vdev_op_fini;
	vdev_open_func_t		*vdev_op_open;
	vdev_close_func_t		*vdev_op_close;
	vdev_asize_func_t		*vdev_op_psize_to_asize;
	vdev_asize_func_t		*vdev_op_asize_to_psize;
	vdev_min_asize_func_t		*vdev_op_min_asize;
	vdev_min_alloc_func_t		*vdev_op_min_alloc;
	vdev_io_start_func_t		*vdev_op_io_start;
	vdev_io_done_func_t		*vdev_op_io_done;
	vdev_state_change_func_t	*vdev_op_state_change;
	vdev_need_resilver_func_t	*vdev_op_need_resilver;
	vdev_hold_func_t		*vdev_op_hold;
	vdev_rele_func_t		*vdev_op_rele;
	vdev_remap_func_t		*vdev_op_remap;
	vdev_xlation_func_t		*vdev_op_xlate;
	vdev_rebuild_asize_func_t	*vdev_op_rebuild_asize;
	vdev_metaslab_init_func_t	*vdev_op_metaslab_init;
	vdev_config_generate_func_t	*vdev_op_config_generate;
	vdev_nparity_func_t		*vdev_op_nparity;
	vdev_ndisks_func_t		*vdev_op_ndisks;
	vdev_kobj_post_evt_func_t	*vdev_op_kobj_evt_post;
	char				vdev_op_type[16];
	boolean_t			vdev_op_leaf;
} vdev_ops_t;

		/*
		 * For normal reads just pick one child.
		 */
		c = vdev_mirror_child_select(zio);
		children = (c >= 0);
	} else {
		ASSERT(zio->io_type == ZIO_TYPE_WRITE);

		/*
		 * Writes go to all children.
		 */
		c = 0;
		children = mm->mm_children;
	}

	while (children--) {
		mc = &mm->mm_child[c++];

		/*
		 * When sequentially resilvering and the integrity of the data
		 * is speculative (ZIO_FLAG_SPECULATIVE), issue write repair IOs
		 * only to the vdev which is being rebuilt. Existing data on
		 * other children must never be overwritten with unconfirmed
		 * data to avoid unrecoverable damage to the pool.
		 */
		if ((zio->io_priority == ZIO_PRIORITY_REBUILD) &&
		    (zio->io_flags & ZIO_FLAG_IO_REPAIR) &&
		    !(zio->io_flags & ZIO_FLAG_SCRUB) &&
		    (zio->io_flags & ZIO_FLAG_SPECULATIVE) &&
		    mm->mm_rebuilding && !mc->mc_rebuilding) {
			continue;
		}

		zio_nowait(zio_vdev_child_io(zio, zio->io_bp,
		    mc->mc_vd, mc->mc_offset, zio->io_abd, zio->io_size,
		    zio->io_type, zio->io_priority, 0,
		    vdev_mirror_child_done, mc));
	}

	if (vd->vdev_mg == NULL) {
		metaslab_class_t *mc;

		if (vd->vdev_islog && vd->vdev_alloc_bias == VDEV_BIAS_NONE)
			vd->vdev_alloc_bias = VDEV_BIAS_LOG;

		ASSERT3U(vd->vdev_islog, ==,
		    (vd->vdev_alloc_bias == VDEV_BIAS_LOG));

		switch (vd->vdev_alloc_bias) {
		case VDEV_BIAS_LOG:
			mc = spa_log_class(spa);
			break;
		case VDEV_BIAS_SPECIAL:
			mc = spa_special_class(spa);
			break;
		case VDEV_BIAS_DEDUP:
			mc = spa_dedup_class(spa);
			break;
		default:
			mc = spa_normal_class(spa);
		}

		vd->vdev_mg = metaslab_group_create(mc, vd);

		if (!vd->vdev_islog) {
			if (mc == spa_special_class(spa)) {
				vd->vdev_log_mg = metaslab_group_create(
				    spa_special_embedded_log_class(spa), vd);
			} else {
				vd->vdev_log_mg = metaslab_group_create(
				    spa_embedded_log_class(spa), vd);
			}
		}

spa_preferred_class(spa_t *spa, const zio_t *zio)
{
	metaslab_class_t *mc = zio->io_metaslab_class;
	boolean_t tried_dedup = (mc == spa_dedup_class(spa));
	boolean_t tried_special = (mc == spa_special_class(spa));
	const zio_prop_t *zp = &zio->io_prop;

	/* Gang children should always use the class of their parents. */
	if (zio->io_flags & ZIO_FLAG_GANG_CHILD) {
		ASSERT(mc != NULL);
		return (mc);
	}

	/*
	 * Override object type for the purposes of selecting a storage class.
	 * Primarily for DMU_OTN_ types where we can't explicitly control their
	 * storage class; instead, choose a static type most closely matches
	 * what we want.
	 */
	dmu_object_type_t objtype =
	    zp->zp_storage_type == DMU_OT_NONE ?
	    zp->zp_type : zp->zp_storage_type;

	/*
	 * ZIL allocations determine their class in zio_alloc_zil().
	 */
	ASSERT(objtype != DMU_OT_INTENT_LOG);

	if (DMU_OT_IS_DDT(objtype)) {
		if (spa_has_dedup(spa) && !tried_dedup && !tried_special)
			return (spa_dedup_class(spa));
		else if (spa_special_has_ddt(spa) && !tried_special)
			return (spa_special_class(spa));
		else
			return (spa_normal_class(spa));
	}

	if (!spa_has_special(spa) || tried_special)
		return (spa_normal_class(spa));

	if (DMU_OT_IS_METADATA(objtype) ||
	    (zfs_user_indirect_is_special && zp->zp_level > 0))
		return (spa_special_class(spa));

	/*
	 * Allow small blocks in special class.  However, leave a reserve of
	 * zfs_special_class_metadata_reserve_pct exclusively for metadata.
	 */
	if (zio->io_size <= zp->zp_zpl_smallblk) {
		metaslab_class_t *special = spa_special_class(spa);
		uint64_t limit = metaslab_class_get_space(special) *
		    (100 - zfs_special_class_metadata_reserve_pct) / 100;

		if (metaslab_class_get_alloc(special) < limit)
			return (special);
	}

	return (spa_normal_class(spa));
}

	/*
	 * Try allocating the block in the usual metaslab class.
	 * If that's full, allocate it in some other class(es).
	 * If that's full, allocate as a gang block,
	 * and if all are full, the allocation fails (which shouldn't happen).
	 *
	 * Note that we do not fall back on embedded slog (ZIL) space, to
	 * preserve unfragmented slog space, which is critical for decent
	 * sync write performance.  If a log allocation fails, we will fall
	 * back to spa_sync() which is abysmal for performance.
	 */
	ASSERT(ZIO_HAS_ALLOCATOR(zio));
	error = metaslab_alloc(spa, mc, zio->io_size, bp,
	    zio->io_prop.zp_copies, zio->io_txg, NULL, flags,
	    &zio->io_alloc_list, zio->io_allocator, zio);

	/*
	 * When the dedup or special class is spilling into the normal class,
	 * there can still be significant space available due to deferred
	 * frees that are in-flight.  We track the txg when this occurred and
	 * back off adding new DDT entries for a few txgs to allow the free
	 * blocks to be processed.
	 */
	if (error == ENOSPC && spa->spa_dedup_class_full_txg != zio->io_txg &&
	    (mc == spa_dedup_class(spa) || (mc == spa_special_class(spa) &&
	    !spa_has_dedup(spa) && spa_special_has_ddt(spa)))) {
		spa->spa_dedup_class_full_txg = zio->io_txg;
		zfs_dbgmsg("%s[%llu]: %s class spilling, req size %llu, "
		    "%llu allocated of %llu",
		    spa_name(spa), (u_longlong_t)zio->io_txg,
		    metaslab_class_get_name(mc),
		    (u_longlong_t)zio->io_size,
		    (u_longlong_t)metaslab_class_get_alloc(mc),
		    (u_longlong_t)metaslab_class_get_space(mc));
	}

	/*
	 * Fall back to some other class when this one is full.
	 */
	if (error == ENOSPC && (newmc = spa_preferred_class(spa, zio)) != mc) {

	 * If we are doing ditto or log blocks, try to spread them across
	 * consecutive vdevs.  If we're forced to reuse a vdev before we've
	 * allocated all of our ditto blocks, then try and spread them out on
	 * that vdev as much as possible.  If it turns out to not be possible,
	 * gradually lower our standards until anything becomes acceptable.
	 * Also, allocating on consecutive vdevs (as opposed to random vdevs)
	 * gives us hope of containing our fault domains to something we're
	 * able to reason about.  Otherwise, any two top-level vdev failures
	 * will guarantee the loss of data.  With consecutive allocation,
	 * only two adjacent top-level vdev failures will result in data loss.
	 *
	 * If we are doing gang blocks (hintdva is non-NULL), try to keep
	 * ourselves on the same vdev as our gang block header.  It makes our
	 * fault domains something tractable.
	 */
	if (hintdva && DVA_IS_VALID(&hintdva[d])) {
		vd = vdev_lookup_top(spa, DVA_GET_VDEV(&hintdva[d]));
		mg = vdev_get_mg(vd, mc);
	}
	if (mg == NULL && d != 0) {
		vd = vdev_lookup_top(spa, DVA_GET_VDEV(&dva[d - 1]));
		mg = vdev_get_mg(vd, mc)->mg_next;
	}
	if (mg == NULL || mg->mg_class != mc || mg->mg_activation_count <= 0) {
		ASSERT(mca->mca_rotor != NULL);
		mg = mca->mca_rotor;
	}

vdev_ops_t vdev_replacing_ops = {
	.vdev_op_init = NULL,
	.vdev_op_fini = NULL,
	.vdev_op_open = vdev_mirror_open,
	.vdev_op_close = vdev_mirror_close,
	.vdev_op_psize_to_asize = vdev_default_asize,
	.vdev_op_asize_to_psize = vdev_default_psize,
	.vdev_op_min_asize = vdev_default_min_asize,
	.vdev_op_min_alloc = NULL,
	.vdev_op_io_start = vdev_mirror_io_start,
	.vdev_op_io_done = vdev_mirror_io_done,
	.vdev_op_state_change = vdev_mirror_state_change,
	.vdev_op_need_resilver = vdev_default_need_resilver,
	.vdev_op_hold = NULL,
	.vdev_op_rele = NULL,
	.vdev_op_remap = NULL,
	.vdev_op_xlate = vdev_default_xlate,
	.vdev_op_rebuild_asize = vdev_mirror_rebuild_asize,
	.vdev_op_metaslab_init = NULL,
	.vdev_op_config_generate = NULL,
	.vdev_op_nparity = NULL,
	.vdev_op_ndisks = NULL,
	.vdev_op_type = VDEV_TYPE_REPLACING,	/* name of this vdev type */
	.vdev_op_leaf = B_FALSE			/* not a leaf vdev */
};

	} else {
		/*
		 * Active hot spares can only be replaced by inactive hot
		 * spares.
		 */
		if (pvd->vdev_ops == &vdev_spare_ops &&
		    oldvd->vdev_isspare &&
		    !spa_has_spare(spa, newvd->vdev_guid))
			return (spa_vdev_exit(spa, newrootvd, txg, ENOTSUP));

		/*
		 * If the source is a hot spare, and the parent isn't already a
		 * spare, then we want to create a new hot spare.  Otherwise, we
		 * want to create a replacing vdev.  The user is not allowed to
		 * attach to a spared vdev child unless the 'isspare' state is
		 * the same (spare replaces spare, non-spare replaces
		 * non-spare).
		 */
		if (pvd->vdev_ops == &vdev_replacing_ops &&
		    spa_version(spa) < SPA_VERSION_MULTI_REPLACE) {
			return (spa_vdev_exit(spa, newrootvd, txg, ENOTSUP));
		} else if (pvd->vdev_ops == &vdev_spare_ops &&
		    newvd->vdev_isspare != oldvd->vdev_isspare) {
			return (spa_vdev_exit(spa, newrootvd, txg, ENOTSUP));
		}

		if (spa_vdev_new_spare_would_cause_double_spares(newvd, pvd)) {
			vdev_dbgmsg(newvd,
			    "disk would create double spares, ignore.");
			return (spa_vdev_exit(spa, newrootvd, txg, EEXIST));
		}

		if (newvd->vdev_isspare)
			pvops = &vdev_spare_ops;
		else
			pvops = &vdev_replacing_ops;
	}

vdev_add_parent(vdev_t *cvd, vdev_ops_t *ops)
{
	spa_t *spa = cvd->vdev_spa;
	vdev_t *pvd = cvd->vdev_parent;
	vdev_t *mvd;

	ASSERT(spa_config_held(spa, SCL_ALL, RW_WRITER) == SCL_ALL);

	mvd = vdev_alloc_common(spa, cvd->vdev_id, 0, ops);

	mvd->vdev_asize = cvd->vdev_asize;
	mvd->vdev_min_asize = cvd->vdev_min_asize;
	mvd->vdev_max_asize = cvd->vdev_max_asize;
	mvd->vdev_psize = cvd->vdev_psize;
	mvd->vdev_ashift = cvd->vdev_ashift;
	mvd->vdev_logical_ashift = cvd->vdev_logical_ashift;
	mvd->vdev_physical_ashift = cvd->vdev_physical_ashift;
	mvd->vdev_state = cvd->vdev_state;
	mvd->vdev_crtxg = cvd->vdev_crtxg;
	mvd->vdev_nonrot = cvd->vdev_nonrot;

	vdev_remove_child(pvd, cvd);
	vdev_add_child(pvd, mvd);
	cvd->vdev_id = mvd->vdev_children;
	vdev_add_child(mvd, cvd);
	vdev_top_update(cvd->vdev_top, cvd->vdev_top);

	if (mvd == mvd->vdev_top)
		vdev_top_transfer(cvd, mvd);

	return (mvd);
}

	/*
	 * Check for a completed replacement.  We always consider the first
	 * vdev in the list to be the oldest vdev, and the last one to be
	 * the newest (see spa_vdev_attach() for how that works).  In
	 * the case where the newest vdev is faulted, we will not automatically
	 * remove it after a resilver completes.  This is OK as it will require
	 * user intervention to determine which disk the admin wishes to keep.
	 */
	if (vd->vdev_ops == &vdev_replacing_ops) {
		ASSERT(vd->vdev_children > 1);

		newvd = vd->vdev_child[vd->vdev_children - 1];
		oldvd = vd->vdev_child[0];

		if (vdev_dtl_empty(newvd, DTL_MISSING) &&
		    vdev_dtl_empty(newvd, DTL_OUTAGE) &&
		    !vdev_dtl_required(oldvd))
			return (oldvd);
	}

	uint64_t draid_seed[2] = { VDEV_DRAID_SEED, map->dm_seed };
	uint8_t *current_row, *previous_row = initial_row;

	/*
	 * Perform a Fisher-Yates shuffle of each row using the previous
	 * row as the starting point.  An initial_row with known pattern
	 * is used as the input for the first row.
	 */
	for (int i = 0; i < nperms; i++) {
		current_row = &perms[i * children];
		memcpy(current_row, previous_row, rowsz);

		for (int j = children - 1; j > 0; j--) {
			uint64_t k = vdev_draid_rand(draid_seed) % (j + 1);
			uint8_t val = current_row[j];
			current_row[j] = current_row[k];
			current_row[k] = val;
		}

		previous_row = current_row;
	}

	uint8_t *base;
	uint64_t iter, asize = 0;
	vdev_draid_get_perm(vdc, perm, &base, &iter);
	for (uint64_t i = 0; i < groupwidth; i++) {
		raidz_col_t *rc = &rr->rr_col[i];
		uint64_t c = (groupstart + i) % ndisks;

		/* increment the offset if we wrap to the next row */
		if (i == wrap)
			physical_offset += VDEV_DRAID_ROWHEIGHT;

		rc->rc_devidx = vdev_draid_permute_id(vdc, base, iter, c);
		rc->rc_offset = physical_offset;

		if (q == 0 && i >= bc)
			rc->rc_size = 0;
		else if (i < bc)
			rc->rc_size = (q + 1) << ashift;
		else
			rc->rc_size = q << ashift;

		asize += rc->rc_size;
	}