Delay to discard cached master when full synchronization (#9398)

* Delay to discard cache master when full synchronization
* Don't disconnect with replicas before loading transferred RDB when full sync

Previously, once replica need to start full synchronization with master,
it will discard cached master whatever full synchronization is failed or
not. 
Now we discard cached master only when transferring RDB is finished
and start to change data space, this make replica could start partial
resynchronization with another new master if new master is failed
during full synchronization.

1 files changed, 68 insertions, 0 deletions

diff --git a/tests/integration/replication.tcl b/tests/integration/replication.tcl
index c0f0240ff..ceb587ff6 100644
--- a/tests/integration/replication.tcl
+++ b/tests/integration/replication.tcl
@@ -926,3 +926,71 @@ test {Kill rdb child process if its dumping RDB is not useful} {
         }
     }
 } {} {external:skip}
+
+start_server {tags {"repl external:skip"}} {
+    set master1_host [srv 0 host]
+    set master1_port [srv 0 port]
+    r set a b
+
+    start_server {} {
+        set master2 [srv 0 client]
+        set master2_host [srv 0 host]
+        set master2_port [srv 0 port]
+        # Take 10s for dumping RDB
+        $master2 debug populate 10 master2 10
+        $master2 config set rdb-key-save-delay 1000000
+
+        start_server {} {
+            set sub_replica [srv 0 client]
+
+            start_server {} {
+                # Full sync with master1
+                r slaveof $master1_host $master1_port
+                wait_for_sync r
+                assert_equal "b" [r get a]
+
+                # Let sub replicas sync with me
+                $sub_replica slaveof [srv 0 host] [srv 0 port]
+                wait_for_sync $sub_replica
+                assert_equal "b" [$sub_replica get a]
+
+                # Full sync with master2, and then kill master2 before finishing dumping RDB
+                r slaveof $master2_host $master2_port
+                wait_for_condition 50 100 {
+                    ([s -2 rdb_bgsave_in_progress] == 1) &&
+                    ([string match "*wait_bgsave*" [s -2 slave0]])
+                } else {
+                    fail "full sync didn't start"
+                }
+                catch {$master2 shutdown nosave}
+
+                test {Don't disconnect with replicas before loading transferred RDB when full sync} {
+                    assert ![log_file_matches [srv -1 stdout] "*Connection with master lost*"]
+                    # The replication id is not changed in entire replication chain
+                    assert_equal [s master_replid] [s -3 master_replid]
+                    assert_equal [s master_replid] [s -1 master_replid]
+                }
+
+                test {Discard cache master before loading transferred RDB when full sync} {
+                    set full_sync [s -3 sync_full]
+                    set partial_sync [s -3 sync_partial_ok]
+                    # Partial sync with master1
+                    r slaveof $master1_host $master1_port
+                    wait_for_sync r
+                    # master1 accepts partial sync instead of full sync
+                    assert_equal $full_sync [s -3 sync_full]
+                    assert_equal [expr $partial_sync+1] [s -3 sync_partial_ok]
+
+                    # Since master only partially sync replica, and repl id is not changed,
+                    # the replica doesn't disconnect with its sub-replicas
+                    assert_equal [s master_replid] [s -3 master_replid]
+                    assert_equal [s master_replid] [s -1 master_replid]
+                    assert ![log_file_matches [srv -1 stdout] "*Connection with master lost*"]
+                    # Sub replica just has one full sync, no partial resync.
+                    assert_equal 1 [s sync_full]
+                    assert_equal 0 [s sync_partial_ok]
+                }
+            }
+        }
+    }
+}