Illumos 4958 zdb trips assert on pools with ashift >= 0xe

4958 zdb trips assert on pools with ashift >= 0xe
Reviewed by: Matthew Ahrens <[email protected]>
Reviewed by: Max Grossman <[email protected]>
Reviewed by: George Wilson <[email protected]>
Reviewed by: Christopher Siden <[email protected]>
Approved by: Garrett D'Amore <[email protected]>

References:
  https://www.illumos.org/issues/4958
  https://github.com/illumos/illumos-gate/commit/2a104a5

Porting notes:

Keep the ZIO_FLAG_FASTWRITE define.  This is for a feature present
in Linux but not yet in *BSD.

Ported by: Turbo Fredriksson <[email protected]>
Signed-off-by: Brian Behlendorf <[email protected]>
Closes #2697

1 files changed, 37 insertions, 6 deletions

diff --git a/cmd/ztest/ztest.c b/cmd/ztest/ztest.c
index 203da4032..0967717fb 100644
--- a/cmd/ztest/ztest.c
+++ b/cmd/ztest/ztest.c
@@ -859,7 +859,7 @@ static uint64_t
 ztest_get_ashift(void)
 {
 	if (ztest_opts.zo_ashift == 0)
-		return (SPA_MINBLOCKSHIFT + ztest_random(3));
+		return (SPA_MINBLOCKSHIFT + ztest_random(5));
 	return (ztest_opts.zo_ashift);
 }
 
@@ -1021,11 +1021,28 @@ ztest_random_spa_version(uint64_t initial_version)
 	return (version);
 }
 
+/*
+ * Find the largest ashift used
+ */
+static uint64_t
+ztest_spa_get_ashift() {
+	uint64_t i;
+	uint64_t ashift = SPA_MINBLOCKSHIFT;
+	vdev_t *rvd = ztest_spa->spa_root_vdev;
+
+	for (i = 0; i < rvd->vdev_children; i++) {
+		ashift = MAX(ashift, rvd->vdev_child[i]->vdev_ashift);
+	}
+	return (ashift);
+}
+
 static int
 ztest_random_blocksize(void)
 {
-	return (1 << (SPA_MINBLOCKSHIFT +
-	    ztest_random(SPA_MAXBLOCKSHIFT - SPA_MINBLOCKSHIFT + 1)));
+	// Choose a block size >= the ashift.
+	uint64_t block_shift =
+	    ztest_random(SPA_MAXBLOCKSHIFT - ztest_spa_get_ashift() + 1);
+	return (1 << (SPA_MINBLOCKSHIFT + block_shift));
 }
 
 static int
@@ -5964,16 +5981,30 @@ ztest_freeze(void)
 	spa_freeze(spa);
 
 	/*
+	 * Because it is hard to predict how much space a write will actually
+	 * require beforehand, we leave ourselves some fudge space to write over
+	 * capacity.
+	 */
+	uint64_t capacity = metaslab_class_get_space(spa_normal_class(spa)) / 2;
+
+	/*
 	 * Run tests that generate log records but don't alter the pool config
 	 * or depend on DSL sync tasks (snapshots, objset create/destroy, etc).
 	 * We do a txg_wait_synced() after each iteration to force the txg
 	 * to increase well beyond the last synced value in the uberblock.
 	 * The ZIL should be OK with that.
+	 *
+	 * Run a random number of times less than zo_maxloops and ensure we do
+	 * not run out of space on the pool.
 	 */
 	while (ztest_random(10) != 0 &&
-	    numloops++ < ztest_opts.zo_maxloops) {
-		ztest_dmu_write_parallel(zd, 0);
-		ztest_dmu_object_alloc_free(zd, 0);
+	    numloops++ < ztest_opts.zo_maxloops &&
+	    metaslab_class_get_alloc(spa_normal_class(spa)) < capacity) {
+		ztest_od_t od;
+		ztest_od_init(&od, 0, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0);
+		VERIFY0(ztest_object_init(zd, &od, sizeof (od), B_FALSE));
+		ztest_io(zd, od.od_object,
+		    ztest_random(ZTEST_RANGE_LOCKS) << SPA_MAXBLOCKSHIFT);
 		txg_wait_synced(spa_get_dsl(spa), 0);
 	}