From b0dd7b324505ebb3b6fac3f3067eba948cf0b09d Mon Sep 17 00:00:00 2001
From: "zhaozhao.zz" <zhaozhao.zz@alibaba-inc.com>
Date: Sat, 6 May 2023 11:53:28 +0800
Subject: Free backlog only if rsi is invalid when master reboot (#12088)

When master reboot from RDB, if rsi in RDB is valid we should not free replication backlog, even if master_repl_offset or repl-offset is 0.

Since if master doesn't send any data to replicas master_repl_offset is 0, it's a valid number.

A clear example:

1. start a master and apply some write commands, the master's master_repl_offset is 0 since it has no replicas.
2. stop write commands on master, and start another instance and replicaof the master, trigger an FULLRESYNC
3. the master's master_repl_offset is still 0 (set a large number for repl-ping-replica-period), do BGSAVE and restart the master
4. master load master_repl_offset from RDB's rsi and it's still 0, and we should make sure replica can partially resync with master.
---
 src/server.c                                |  4 ++-
 tests/integration/psync2-master-restart.tcl | 41 ++++++++++++++++++++++++++---
 2 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/src/server.c b/src/server.c
index 381edabc6..b6ed1d9c5 100644
--- a/src/server.c
+++ b/src/server.c
@@ -6700,6 +6700,7 @@ void loadDataFromDisk(void) {
             serverLog(LL_NOTICE, "DB loaded from append only file: %.3f seconds", (float)(ustime()-start)/1000000);
     } else {
         rdbSaveInfo rsi = RDB_SAVE_INFO_INIT;
+        int rsi_is_valid = 0;
         errno = 0; /* Prevent a stale value from affecting error checking */
         int rdb_flags = RDBFLAGS_NONE;
         if (iAmMaster()) {
@@ -6721,6 +6722,7 @@ void loadDataFromDisk(void) {
                  * information in function rdbPopulateSaveInfo. */
                 rsi.repl_stream_db != -1)
             {
+                rsi_is_valid = 1;
                 if (!iAmMaster()) {
                     memcpy(server.replid,rsi.repl_id,sizeof(server.replid));
                     server.master_repl_offset = rsi.repl_offset;
@@ -6754,7 +6756,7 @@ void loadDataFromDisk(void) {
          * if RDB doesn't have replication info or there is no rdb, it is not
          * possible to support partial resynchronization, to avoid extra memory
          * of replication backlog, we drop it. */
-        if (server.master_repl_offset == 0 && server.repl_backlog)
+        if (!rsi_is_valid && server.repl_backlog)
             freeReplicationBacklog();
     }
 }
diff --git a/tests/integration/psync2-master-restart.tcl b/tests/integration/psync2-master-restart.tcl
index e925aaab8..a9e21d12d 100644
--- a/tests/integration/psync2-master-restart.tcl
+++ b/tests/integration/psync2-master-restart.tcl
@@ -21,6 +21,10 @@ start_server {} {
     $replica config set repl-timeout 3600
     $sub_replica config set repl-timeout 3600
 
+    # Avoid PINGs
+    $master config set repl-ping-replica-period 3600
+    $master config rewrite
+
     # Build replication chain
     $replica replicaof $master_host $master_port
     $sub_replica replicaof $replica_host $replica_port
@@ -32,14 +36,43 @@ start_server {} {
         fail "Replication not started."
     }
 
-    # Avoid PINGs
-    $master config set repl-ping-replica-period 3600
-    $master config rewrite
+    test "PSYNC2: Partial resync after Master restart using RDB aux fields when offset is 0" {
+        assert {[status $master master_repl_offset] == 0}
+
+        set replid [status $master master_replid]
+        $replica config resetstat
+
+        catch {
+            restart_server 0 true false true now
+            set master [srv 0 client]
+        }
+        wait_for_condition 50 1000 {
+            [status $replica master_link_status] eq {up} &&
+            [status $sub_replica master_link_status] eq {up}
+        } else {
+            fail "Replicas didn't sync after master restart"
+        }
+
+        # Make sure master restore replication info correctly
+        assert {[status $master master_replid] != $replid}
+        assert {[status $master master_repl_offset] == 0}
+        assert {[status $master master_replid2] eq $replid}
+        assert {[status $master second_repl_offset] == 1}
+
+        # Make sure master set replication backlog correctly
+        assert {[status $master repl_backlog_active] == 1}
+        assert {[status $master repl_backlog_first_byte_offset] == 1}
+        assert {[status $master repl_backlog_histlen] == 0}
+
+        # Partial resync after Master restart
+        assert {[status $master sync_partial_ok] == 1}
+        assert {[status $replica sync_partial_ok] == 1}
+    }
 
     # Generate some data
     createComplexDataset $master 1000
 
-    test "PSYNC2: Partial resync after Master restart using RDB aux fields" {
+    test "PSYNC2: Partial resync after Master restart using RDB aux fields with data" {
         wait_for_condition 500 100 {
             [status $master master_repl_offset] == [status $replica master_repl_offset] &&
             [status $master master_repl_offset] == [status $sub_replica master_repl_offset]
-- 
cgit v1.2.1