OpenZFS 6736 - ZFS per-vdev ZAPs

6736 ZFS per-vdev ZAPs
Reviewed by: Matthew Ahrens <[email protected]>
Reviewed by: John Kennedy <[email protected]>
Reviewed by: George Wilson <[email protected]>
Reviewed by: Don Brady <[email protected]>
Reviewed by: Dan McDonald <[email protected]>

References:
  https://www.illumos.org/issues/6736
  https://github.com/openzfs/openzfs/commit/215198a

Ported-by: Don Brady <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes #4515

1 files changed, 79 insertions, 0 deletions

diff --git a/module/zfs/vdev.c b/module/zfs/vdev.c
index cf0d9b7d0..7114c2efc 100644
--- a/module/zfs/vdev.c
+++ b/module/zfs/vdev.c
@@ -519,6 +519,10 @@ vdev_alloc(spa_t *spa, vdev_t **vdp, nvlist_t *nv, vdev_t *parent, uint_t id,
 		    &vd->vdev_asize);
 		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_REMOVING,
 		    &vd->vdev_removing);
+		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_VDEV_TOP_ZAP,
+		    &vd->vdev_top_zap);
+	} else {
+		ASSERT0(vd->vdev_top_zap);
 	}
 
 	if (parent && !parent->vdev_parent && alloctype != VDEV_ALLOC_ATTACH) {
@@ -530,9 +534,18 @@ vdev_alloc(spa_t *spa, vdev_t **vdp, nvlist_t *nv, vdev_t *parent, uint_t id,
 		    spa_log_class(spa) : spa_normal_class(spa), vd);
 	}
 
+	if (vd->vdev_ops->vdev_op_leaf &&
+	    (alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_SPLIT)) {
+		(void) nvlist_lookup_uint64(nv,
+		    ZPOOL_CONFIG_VDEV_LEAF_ZAP, &vd->vdev_leaf_zap);
+	} else {
+		ASSERT0(vd->vdev_leaf_zap);
+	}
+
 	/*
 	 * If we're a leaf vdev, try to load the DTL object and other state.
 	 */
+
 	if (vd->vdev_ops->vdev_op_leaf &&
 	    (alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_L2CACHE ||
 	    alloctype == VDEV_ALLOC_ROOTPOOL)) {
@@ -694,10 +707,12 @@ vdev_top_transfer(vdev_t *svd, vdev_t *tvd)
 	tvd->vdev_ms_array = svd->vdev_ms_array;
 	tvd->vdev_ms_shift = svd->vdev_ms_shift;
 	tvd->vdev_ms_count = svd->vdev_ms_count;
+	tvd->vdev_top_zap = svd->vdev_top_zap;
 
 	svd->vdev_ms_array = 0;
 	svd->vdev_ms_shift = 0;
 	svd->vdev_ms_count = 0;
+	svd->vdev_top_zap = 0;
 
 	if (tvd->vdev_mg)
 		ASSERT3P(tvd->vdev_mg, ==, svd->vdev_mg);
@@ -1977,6 +1992,51 @@ vdev_dtl_load(vdev_t *vd)
 }
 
 void
+vdev_destroy_unlink_zap(vdev_t *vd, uint64_t zapobj, dmu_tx_t *tx)
+{
+	spa_t *spa = vd->vdev_spa;
+
+	VERIFY0(zap_destroy(spa->spa_meta_objset, zapobj, tx));
+	VERIFY0(zap_remove_int(spa->spa_meta_objset, spa->spa_all_vdev_zaps,
+	    zapobj, tx));
+}
+
+uint64_t
+vdev_create_link_zap(vdev_t *vd, dmu_tx_t *tx)
+{
+	spa_t *spa = vd->vdev_spa;
+	uint64_t zap = zap_create(spa->spa_meta_objset, DMU_OTN_ZAP_METADATA,
+	    DMU_OT_NONE, 0, tx);
+
+	ASSERT(zap != 0);
+	VERIFY0(zap_add_int(spa->spa_meta_objset, spa->spa_all_vdev_zaps,
+	    zap, tx));
+
+	return (zap);
+}
+
+void
+vdev_construct_zaps(vdev_t *vd, dmu_tx_t *tx)
+{
+	uint64_t i;
+
+	if (vd->vdev_ops != &vdev_hole_ops &&
+	    vd->vdev_ops != &vdev_missing_ops &&
+	    vd->vdev_ops != &vdev_root_ops &&
+	    !vd->vdev_top->vdev_removing) {
+		if (vd->vdev_ops->vdev_op_leaf && vd->vdev_leaf_zap == 0) {
+			vd->vdev_leaf_zap = vdev_create_link_zap(vd, tx);
+		}
+		if (vd == vd->vdev_top && vd->vdev_top_zap == 0) {
+			vd->vdev_top_zap = vdev_create_link_zap(vd, tx);
+		}
+	}
+	for (i = 0; i < vd->vdev_children; i++) {
+		vdev_construct_zaps(vd->vdev_child[i], tx);
+	}
+}
+
+void
 vdev_dtl_sync(vdev_t *vd, uint64_t txg)
 {
 	spa_t *spa = vd->vdev_spa;
@@ -1998,6 +2058,18 @@ vdev_dtl_sync(vdev_t *vd, uint64_t txg)
 		space_map_close(vd->vdev_dtl_sm);
 		vd->vdev_dtl_sm = NULL;
 		mutex_exit(&vd->vdev_dtl_lock);
+
+		/*
+		 * We only destroy the leaf ZAP for detached leaves or for
+		 * removed log devices. Removed data devices handle leaf ZAP
+		 * cleanup later, once cancellation is no longer possible.
+		 */
+		if (vd->vdev_leaf_zap != 0 && (vd->vdev_detached ||
+		    vd->vdev_top->vdev_islog)) {
+			vdev_destroy_unlink_zap(vd, vd->vdev_leaf_zap, tx);
+			vd->vdev_leaf_zap = 0;
+		}
+
 		dmu_tx_commit(tx);
 		return;
 	}
@@ -2204,6 +2276,8 @@ vdev_remove(vdev_t *vd, uint64_t txg)
 	int m, i;
 
 	tx = dmu_tx_create_assigned(spa_get_dsl(spa), txg);
+	ASSERT(vd == vd->vdev_top);
+	ASSERT3U(txg, ==, spa_syncing_txg(spa));
 
 	if (vd->vdev_ms != NULL) {
 		metaslab_group_t *mg = vd->vdev_mg;
@@ -2245,6 +2319,11 @@ vdev_remove(vdev_t *vd, uint64_t txg)
 		(void) dmu_object_free(mos, vd->vdev_ms_array, tx);
 		vd->vdev_ms_array = 0;
 	}
+
+	if (vd->vdev_islog && vd->vdev_top_zap != 0) {
+		vdev_destroy_unlink_zap(vd, vd->vdev_top_zap, tx);
+		vd->vdev_top_zap = 0;
+	}
 	dmu_tx_commit(tx);
 }