Sequential scrub and resilvers

Currently, scrubs and resilvers can take an extremely
long time to complete. This is largely due to the fact
that zfs scans process pools in logical order, as
determined by each block's bookmark. This makes sense
from a simplicity perspective, but blocks in zfs are
often scattered randomly across disks, particularly
due to zfs's copy-on-write mechanisms.

This patch improves performance by splitting scrubs
and resilvers into a metadata scanning phase and an IO
issuing phase. The metadata scan reads through the
structure of the pool and gathers an in-memory queue
of I/Os, sorted by size and offset on disk. The issuing
phase will then issue the scrub I/Os as sequentially as
possible, greatly improving performance.

This patch also updates and cleans up some of the scan
code which has not been updated in several years.

Reviewed-by: Brian Behlendorf <[email protected]>
Authored-by: Saso Kiselkov <[email protected]>
Authored-by: Alek Pinchuk <[email protected]>
Authored-by: Tom Caputi <[email protected]>
Signed-off-by: Tom Caputi <[email protected]>
Closes #3625 
Closes #6256 

1 files changed, 8 insertions, 2 deletions

diff --git a/module/zfs/spa_misc.c b/module/zfs/spa_misc.c
index 9a3290e95..116b0ebd9 100644
--- a/module/zfs/spa_misc.c
+++ b/module/zfs/spa_misc.c
@@ -1892,6 +1892,7 @@ spa_init(int mode)
 	zpool_feature_init();
 	spa_config_load();
 	l2arc_start();
+	scan_init();
 	qat_init();
 }
 
@@ -1915,6 +1916,7 @@ spa_fini(void)
 	unique_fini();
 	refcount_fini();
 	fm_fini();
+	scan_fini();
 	qat_fini();
 
 	avl_destroy(&spa_namespace_avl);
@@ -2016,6 +2018,7 @@ spa_scan_stat_init(spa_t *spa)
 		spa->spa_scan_pass_scrub_pause = 0;
 	spa->spa_scan_pass_scrub_spent_paused = 0;
 	spa->spa_scan_pass_exam = 0;
+	spa->spa_scan_pass_issued = 0;
 	vdev_scan_stat_init(spa->spa_root_vdev);
 }
 
@@ -2033,18 +2036,21 @@ spa_scan_get_stats(spa_t *spa, pool_scan_stat_t *ps)
 
 	/* data stored on disk */
 	ps->pss_func = scn->scn_phys.scn_func;
+	ps->pss_state = scn->scn_phys.scn_state;
 	ps->pss_start_time = scn->scn_phys.scn_start_time;
 	ps->pss_end_time = scn->scn_phys.scn_end_time;
 	ps->pss_to_examine = scn->scn_phys.scn_to_examine;
-	ps->pss_examined = scn->scn_phys.scn_examined;
 	ps->pss_to_process = scn->scn_phys.scn_to_process;
 	ps->pss_processed = scn->scn_phys.scn_processed;
 	ps->pss_errors = scn->scn_phys.scn_errors;
-	ps->pss_state = scn->scn_phys.scn_state;
+	ps->pss_examined = scn->scn_phys.scn_examined;
+	ps->pss_issued =
+	    scn->scn_issued_before_pass + spa->spa_scan_pass_issued;
 
 	/* data not stored on disk */
 	ps->pss_pass_start = spa->spa_scan_pass_start;
 	ps->pss_pass_exam = spa->spa_scan_pass_exam;
+	ps->pss_pass_issued = spa->spa_scan_pass_issued;
 	ps->pss_pass_scrub_pause = spa->spa_scan_pass_scrub_pause;
 	ps->pss_pass_scrub_spent_paused = spa->spa_scan_pass_scrub_spent_paused;