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, 13 insertions, 1 deletions

diff --git a/include/sys/dsl_deadlist.h b/include/sys/dsl_deadlist.h
index bb8248a66..64358bb5f 100644
--- a/include/sys/dsl_deadlist.h
+++ b/include/sys/dsl_deadlist.h
@@ -48,8 +48,10 @@ typedef struct dsl_deadlist_phys {
 typedef struct dsl_deadlist {
 	objset_t *dl_os;
 	uint64_t dl_object;
-	avl_tree_t dl_tree;
+	avl_tree_t dl_tree; /* contains dsl_deadlist_entry_t */
+	avl_tree_t dl_cache; /* contains dsl_deadlist_cache_entry_t */
 	boolean_t dl_havetree;
+	boolean_t dl_havecache;
 	struct dmu_buf *dl_dbuf;
 	dsl_deadlist_phys_t *dl_phys;
 	kmutex_t dl_lock;
@@ -59,6 +61,15 @@ typedef struct dsl_deadlist {
 	boolean_t dl_oldfmt;
 } dsl_deadlist_t;
 
+typedef struct dsl_deadlist_cache_entry {
+	avl_node_t dlce_node;
+	uint64_t dlce_mintxg;
+	uint64_t dlce_bpobj;
+	uint64_t dlce_bytes;
+	uint64_t dlce_comp;
+	uint64_t dlce_uncomp;
+} dsl_deadlist_cache_entry_t;
+
 typedef struct dsl_deadlist_entry {
 	avl_node_t dle_node;
 	uint64_t dle_mintxg;
@@ -108,6 +119,7 @@ int dsl_process_sub_livelist(bpobj_t *bpobj, struct bplist *to_free,
     zthr_t *t, uint64_t *size);
 void dsl_deadlist_clear_entry(dsl_deadlist_entry_t *dle, dsl_deadlist_t *dl,
     dmu_tx_t *tx);
+void dsl_deadlist_discard_tree(dsl_deadlist_t *dl);
 
 #ifdef	__cplusplus
 }