Fix commit callbacks

The upstream commit cb code had a few bugs:

1) The arguments of the list_move_tail() call in txg_dispatch_callbacks()
were reversed by mistake. This caused the commit callbacks to not be
called at all.

2) ztest had a bug in ztest_dmu_commit_callbacks() where "error" was not
initialized correctly. This seems to have caused the test to always take
the simulated error code path, which made ztest unable to detect whether
commit cbs were being called for transactions that successfuly complete.

3) ztest had another bug in ztest_dmu_commit_callbacks() where the commit
cb threshold was not being compared correctly.

4) The commit cb taskq was using 'max_ncpus * 2' as the maxalloc argument
of taskq_create(), which could have caused unnecessary delays in the txg
sync thread.

Signed-off-by: Brian Behlendorf <[email protected]>

1 files changed, 32 insertions, 15 deletions

diff --git a/cmd/ztest/ztest.c b/cmd/ztest/ztest.c
index ad7373558..b5cee5b3b 100644
--- a/cmd/ztest/ztest.c
+++ b/cmd/ztest/ztest.c
@@ -341,6 +341,22 @@ static boolean_t ztest_exiting;
 
 /* Global commit callback list */
 static ztest_cb_list_t zcl;
+/* Commit cb delay */
+static uint64_t zc_min_txg_delay = UINT64_MAX;
+static int zc_cb_counter = 0;
+
+/*
+ * Minimum number of commit callbacks that need to be registered for us to check
+ * whether the minimum txg delay is acceptable.
+ */
+#define	ZTEST_COMMIT_CB_MIN_REG	100
+
+/*
+ * If a number of txgs equal to this threshold have been created after a commit
+ * callback has been registered but not called, then we assume there is an
+ * implementation bug.
+ */
+#define	ZTEST_COMMIT_CB_THRESH	(TXG_CONCURRENT_STATES + 1000)
 
 extern uint64_t metaslab_gang_bang;
 extern uint64_t metaslab_df_alloc_threshold;
@@ -4092,18 +4108,20 @@ ztest_commit_callback(void *arg, int error)
 		return;
 	}
 
-	/* Was this callback added to the global callback list? */
-	if (!data->zcd_added)
-		goto out;
-
+	ASSERT(data->zcd_added);
 	ASSERT3U(data->zcd_txg, !=, 0);
 
-	/* Remove our callback from the list */
 	(void) mutex_lock(&zcl.zcl_callbacks_lock);
+
+	/* See if this cb was called more quickly */
+	if ((synced_txg - data->zcd_txg) < zc_min_txg_delay)
+		zc_min_txg_delay = synced_txg - data->zcd_txg;
+
+	/* Remove our callback from the list */
 	list_remove(&zcl.zcl_callbacks, data);
+
 	(void) mutex_unlock(&zcl.zcl_callbacks_lock);
 
-out:
 	umem_free(data, sizeof (ztest_cb_data_t));
 }
 
@@ -4122,13 +4140,6 @@ ztest_create_cb_data(objset_t *os, uint64_t txg)
 }
 
 /*
- * If a number of txgs equal to this threshold have been created after a commit
- * callback has been registered but not called, then we assume there is an
- * implementation bug.
- */
-#define	ZTEST_COMMIT_CALLBACK_THRESH	(TXG_CONCURRENT_STATES + 2)
-
-/*
  * Commit callback test.
  */
 void
@@ -4139,7 +4150,7 @@ ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id)
 	dmu_tx_t *tx;
 	ztest_cb_data_t *cb_data[3], *tmp_cb;
 	uint64_t old_txg, txg;
-	int i, error;
+	int i, error = 0;
 
 	ztest_od_init(&od[0], id, FTAG, 0, DMU_OT_UINT64_OTHER, 0, 0);
 
@@ -4219,7 +4230,7 @@ ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id)
 	 */
 	tmp_cb = list_head(&zcl.zcl_callbacks);
 	if (tmp_cb != NULL &&
-	    tmp_cb->zcd_txg > txg - ZTEST_COMMIT_CALLBACK_THRESH) {
+	    tmp_cb->zcd_txg + ZTEST_COMMIT_CB_THRESH < txg) {
 		fatal(0, "Commit callback threshold exceeded, oldest txg: %"
 		    PRIu64 ", open txg: %" PRIu64 "\n", tmp_cb->zcd_txg, txg);
 	}
@@ -4250,6 +4261,8 @@ ztest_dmu_commit_callbacks(ztest_ds_t *zd, uint64_t id)
 		tmp_cb = cb_data[i];
 	}
 
+	zc_cb_counter += 3;
+
 	(void) mutex_unlock(&zcl.zcl_callbacks_lock);
 
 	dmu_tx_commit(tx);
@@ -5256,6 +5269,10 @@ ztest_run(ztest_shared_t *zs)
 	for (uint64_t object = 1; object < 50; object++)
 		dmu_prefetch(spa->spa_meta_objset, object, 0, 1ULL << 20);
 
+	/* Verify that at least one commit cb was called in a timely fashion */
+	if (zc_cb_counter >= ZTEST_COMMIT_CB_MIN_REG)
+		VERIFY3U(zc_min_txg_delay, ==, 0);
+
 	spa_close(spa, FTAG);
 
 	/*