Fix flaky replication tests (#13518)

tezc · web-flow · commit ac03e3721dd3 · 2024-09-08T12:54:01.000+03:00
#13495 introduced a change to reply -LOADING while flushing existing db on a replica. Some of our tests are sensitive to this change and do no expect -LOADING reply. Fixing a couple of tests that fail time to time.
diff --git a/tests/cluster/tests/14-consistency-check.tcl b/tests/cluster/tests/14-consistency-check.tcl
@@ -32,6 +32,13 @@ proc get_one_of_my_replica {id} {
     }
     set replica_port [lindex [lindex [lindex [R $id role] 2] 0] 1]
     set replica_id_num [get_instance_id_by_port redis $replica_port]
+
+    # To avoid -LOADING reply, wait until replica syncs with master.
+    wait_for_condition 1000 50 {
+        [RI $replica_id_num master_link_status] eq {up}
+    } else {
+        fail "Replica did not sync in time."
+    }
     return $replica_id_num
 }
 
@@ -105,8 +112,15 @@ proc test_slave_load_expired_keys {aof} {
         # start the replica again (loading an RDB or AOF file)
         restart_instance redis $replica_id
 
+        # Replica may start a full sync after restart, trying in a loop to avoid
+        # -LOADING reply in that case.
+        wait_for_condition 1000 50 {
+            [catch {set replica_dbsize_3 [R $replica_id dbsize]} e] == 0
+        } else {
+            fail "Replica is not up."
+        }
+
         # make sure the keys are still there
-        set replica_dbsize_3 [R $replica_id dbsize]
         assert {$replica_dbsize_3 > $replica_dbsize_0}
         
         # restore settings
diff --git a/tests/unit/scripting.tcl b/tests/unit/scripting.tcl
@@ -2069,6 +2069,14 @@ start_server {tags {"scripting"}} {
             } 1 x
 
             r replicaof [srv -1 host] [srv -1 port]
+
+            # To avoid -LOADING reply, wait until replica syncs with master.
+            wait_for_condition 50 100 {
+                [s master_link_status] eq {up}
+            } else {
+                fail "Replica did not sync in time."
+            }
+
             assert_error {EXECABORT Transaction discarded because of: READONLY *} {$rr exec}
             assert_error {READONLY You can't write against a read only replica. script: *} {$rr2 exec}
             $rr close
