Add fast path for zfs_ioc_space_snaps() handling of empty_bpobj

When there are many snapshots, calls to zfs_ioc_space_snaps() (e.g. from
`zfs destroy -nv pool/fs@snap1%snap10000`) can be very slow, resulting
in poor performance because we are holding the dp_config_rwlock the
entire time, blocking spa_sync() from continuing.  With around ten
thousand snapshots, we've seen up to 500 seconds in this ioctl,
iterating over up to 50,000,000 bpobjs, ~99% of which are the empty
bpobj.

By creating a fast path for zfs_ioc_space_snaps() handling of the
empty_bpobj, we can achieve a ~5x performance improvement of this ioctl
(when there are many snapshots, and the deadlist is mostly
empty_bpobj's).

Reviewed-by: Pavel Zakharov <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Reviewed-by: Paul Dagnelie <[email protected]>
Signed-off-by: Matthew Ahrens <[email protected]>
External-issue: DLPX-58348
Closes #8744 

1 files changed, 7 insertions, 0 deletions

diff --git a/module/zfs/dsl_destroy.c b/module/zfs/dsl_destroy.c
index 5c483c5dd..788753bdc 100644
--- a/module/zfs/dsl_destroy.c
+++ b/module/zfs/dsl_destroy.c
@@ -413,6 +413,13 @@ dsl_destroy_snapshot_sync_impl(dsl_dataset_t *ds, boolean_t defer, dmu_tx_t *tx)
 		/* Merge our deadlist into next's and free it. */
 		dsl_deadlist_merge(&ds_next->ds_deadlist,
 		    dsl_dataset_phys(ds)->ds_deadlist_obj, tx);
+
+		/*
+		 * We are done with the deadlist tree (generated/used
+		 * by dsl_deadlist_move_bpobj() and dsl_deadlist_merge()).
+		 * Discard it to save memory.
+		 */
+		dsl_deadlist_discard_tree(&ds_next->ds_deadlist);
 	}
 
 	dsl_deadlist_close(&ds->ds_deadlist);