Fix ztest deadman panic with indirect vdev damage

This patch fixes an issue where ztest's deadman thread would
trigger a panic because reconstructing artifically damaged
blocks would take too long to reconstruct. This patch simply
limits how often ztest inflicts split-block damage and how
many segments it can damage when it does.

Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed-by: Matthew Ahrens <mahrens@delphix.com>
Signed-off-by: Tom Caputi <tcaputi@datto.com>
Closes #8010

2 files changed, 9 insertions, 4 deletions

diff --git a/cmd/ztest/ztest.c b/cmd/ztest/ztest.c
index 44d4e97403f4..983bc0dfe036 100644
--- a/cmd/ztest/ztest.c
+++ b/cmd/ztest/ztest.c
@@ -7383,8 +7383,13 @@ main(int argc, char **argv)
 	 * Verify that even extensively damaged split blocks with many
 	 * segments can be reconstructed in a reasonable amount of time
 	 * when reconstruction is known to be possible.
+	 *
+	 * Note: the lower this value is, the more damage we inflict, and
+	 * the more time ztest spends in recovering that damage. We chose
+	 * to induce damage 1/100th of the time so recovery is tested but
+	 * not so frequently that ztest doesn't get to test other code paths.
 	 */
-	zfs_reconstruct_indirect_damage_fraction = 4;
+	zfs_reconstruct_indirect_damage_fraction = 100;
 
 	action.sa_handler = sig_handler;
 	sigemptyset(&action.sa_mask);
diff --git a/module/zfs/vdev_indirect.c b/module/zfs/vdev_indirect.c
index 097be6f0e312..7863fe9d0f35 100644
--- a/module/zfs/vdev_indirect.c
+++ b/module/zfs/vdev_indirect.c
@@ -1614,7 +1614,7 @@ vdev_indirect_splits_damage(indirect_vsd_t *iv, zio_t *zio)
 	 * result in two or less unique copies per indirect_child_t.
 	 * Both may need to be checked in order to reconstruct the block.
 	 * Set iv->iv_attempts_max such that all unique combinations will
-	 * enumerated, but limit the damage to at most 16 indirect splits.
+	 * enumerated, but limit the damage to at most 12 indirect splits.
 	 */
 	iv->iv_attempts_max = 1;
 
@@ -1632,7 +1632,7 @@ vdev_indirect_splits_damage(indirect_vsd_t *iv, zio_t *zio)
 		}
 
 		iv->iv_attempts_max *= 2;
-		if (iv->iv_attempts_max > (1ULL << 16)) {
+		if (iv->iv_attempts_max >= (1ULL << 12)) {
 			iv->iv_attempts_max = UINT64_MAX;
 			break;
 		}
@@ -1718,7 +1718,7 @@ vdev_indirect_reconstruct_io_done(zio_t *zio)
 	/*
 	 * If nonzero, every 1/x blocks will be damaged, in order to validate
 	 * reconstruction when there are split segments with damaged copies.
-	 * Known_good will TRUE when reconstruction is known to be possible.
+	 * Known_good will be TRUE when reconstruction is known to be possible.
 	 */
 	if (zfs_reconstruct_indirect_damage_fraction != 0 &&
 	    spa_get_random(zfs_reconstruct_indirect_damage_fraction) == 0)