From f4a6721dfd4d8e8a2aa7ce86304d0182070d8a64 Mon Sep 17 00:00:00 2001
From: "debing.sun" <debing.sun@redis.com>
Date: Fri, 2 Aug 2024 07:22:13 +0800
Subject: [PATCH] Fix CLUSTER SHARDS command returns empty array (#13422)

Close https://github.com/redis/redis/issues/13414

When the cluster's master node fails and is switched to another node,
the first node in the shard node list (the old master) is no longer
valid.
Add a new method clusterGetMasterFromShard() to obtain the current
master.
---
 src/cluster.c                             | 23 +++++++++++++++++++----
 tests/cluster/tests/28-cluster-shards.tcl |  4 ++++
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/src/cluster.c b/src/cluster.c
index 661b4e184..9aa5d9549 100644
--- a/src/cluster.c
+++ b/src/cluster.c
@@ -1722,6 +1722,22 @@ void clusterRemoveNodeFromShard(clusterNode *node) {
     sdsfree(s);
 }
 
+static clusterNode *clusterGetMasterFromShard(list *nodes) {
+    clusterNode *n = NULL;
+    listIter li;
+    listNode *ln;
+    listRewind(nodes,&li);
+    while ((ln = listNext(&li)) != NULL) {
+        clusterNode *node = listNodeValue(ln);
+        if (!nodeFailed(node)) {
+            n = node;
+            break;
+        }
+    }
+    if (!n) return NULL;
+    return clusterNodeGetMaster(n);
+}
+
 /* -----------------------------------------------------------------------------
  * CLUSTER config epoch handling
  * -------------------------------------------------------------------------- */
@@ -5727,14 +5743,13 @@ void addNodeDetailsToShardReply(client *c, clusterNode *node) {
 /* Add the shard reply of a single shard based off the given primary node. */
 void addShardReplyForClusterShards(client *c, list *nodes) {
     serverAssert(listLength(nodes) > 0);
-    clusterNode *n = listNodeValue(listFirst(nodes));
+
     addReplyMapLen(c, 2);
     addReplyBulkCString(c, "slots");
 
     /* Use slot_info_pairs from the primary only */
-    n = clusterNodeGetMaster(n);
-
-    if (n->slot_info_pairs != NULL) {
+    clusterNode *n = clusterGetMasterFromShard(nodes);
+    if (n && n->slot_info_pairs != NULL) {
         serverAssert((n->slot_info_pairs_count % 2) == 0);
         addReplyArrayLen(c, n->slot_info_pairs_count);
         for (int i = 0; i < n->slot_info_pairs_count; i++)
diff --git a/tests/cluster/tests/28-cluster-shards.tcl b/tests/cluster/tests/28-cluster-shards.tcl
index f24b91729..cbdae001f 100644
--- a/tests/cluster/tests/28-cluster-shards.tcl
+++ b/tests/cluster/tests/28-cluster-shards.tcl
@@ -124,6 +124,10 @@ test "Verify health as fail for killed node" {
     }
 }
 
+test "Verify that other nodes can correctly output the new master's slots" {
+    assert_not_equal {} [dict get [get_node_info_from_shard [R 4 CLUSTER MYID] 8 "shard"] slots]
+}
+
 set primary_id 4
 set replica_id 0