Add shard id field to CLUSTER SHARDS response (valkey-io#2568)

This change exposes an existing, persistent (in nodes.conf) unique shard
identifier for each shard in the cluster as part of the `CLUSTER SHARDS` command
response.

```
1) 1) "slots"
   2) 1) (integer) 0
      2) (integer) 999
      3) (integer) 2001
      4) (integer) 3999
      5) (integer) 4501
      6) (integer) 5460
   3) "nodes"
   4) 1)  1) "id"
          2) "6e76043bed00e716e85035107866ea16e9a5f700"
          3) "port"
          4) (integer) 6385
          5) "ip"
          6) "127.0.0.1"
          7) "endpoint"
          8) "127.0.0.1"
          9) "role"
         10) "replica"
         11) "replication-offset"
         12) (integer) 8092
         13) "health"
         14) "online"
      2)  1) "id"
          2) "b2f8c841707b2246ec2a641c37f16e88fe0bb700"
          3) "port"
          4) (integer) 6380
          5) "ip"
          6) "127.0.0.1"
          7) "endpoint"
          8) "127.0.0.1"
          9) "role"
         10) "master"
         11) "replication-offset"
         12) (integer) 8092
         13) "health"
         14) "online"
   5) "id"
   6) "3f2a7bb7bbd5fc2a331fe9bf95f5e02bcca02430"
```

---------

Signed-off-by: Satheesha Chattenahalli Hanume Gowda <satheesha@apple.com>
Co-authored-by: Satheesha Chattenahalli Hanume Gowda <satheesha@apple.com>

Author: satheeshaGowda

src/cluster_legacy.c

@@ -6909,9 +6909,11 @@ void addNodeDetailsToShardReply(client *c, clusterNode *node) {
     setDeferredMapLen(c, node_replylen, reply_count);
 }
 
-/* Add to the output buffer of the given client, an array of slot (start, end)
- * pair owned by the shard, also the primary and set of replica(s) along with
- * information about each node. */
+/* Add to the output buffer of the given client,
+ * an array of slot (start, end) pair owned by the shard,
+ * an array of the primary and set of replica(s) along with information about each node,
+ * and shard id.
+ */
 void clusterCommandShards(client *c) {
     addReplyArrayLen(c, dictSize(server.cluster->shards));
     /* This call will add slot_info_pairs to all nodes */
@@ -6920,7 +6922,7 @@ void clusterCommandShards(client *c) {
     for (dictEntry *de = dictNext(di); de != NULL; de = dictNext(di)) {
         list *nodes = dictGetVal(de);
         serverAssert(listLength(nodes) > 0);
-        addReplyMapLen(c, 2);
+        addReplyMapLen(c, 3);
         addReplyBulkCString(c, "slots");
 
         /* Find a node which has the slot information served by this shard. */
@@ -6953,6 +6955,8 @@ void clusterCommandShards(client *c) {
             addNodeDetailsToShardReply(c, n);
             clusterFreeNodesSlotsInfo(n);
         }
+        addReplyBulkCString(c, "id");
+        addReplyBulkCBuffer(c, dictGetKey(de), CLUSTER_NAMELEN);
     }
     dictReleaseIterator(di);
 }

src/commands.def

@@ -1006,7 +1006,9 @@ struct COMMAND_ARG CLUSTER_SETSLOT_Args[] = {
 
 #ifndef SKIP_CMD_HISTORY_TABLE
 /* CLUSTER SHARDS history */
-#define CLUSTER_SHARDS_History NULL
+commandHistory CLUSTER_SHARDS_History[] = {
+{"9.0.0","Added shard id field to CLUSTER SHARDS response"},
+};
 #endif
 
 #ifndef SKIP_CMD_TIPS_TABLE
@@ -1165,7 +1167,7 @@ struct COMMAND_STRUCT CLUSTER_Subcommands[] = {
 {MAKE_CMD("saveconfig","Forces a node to save the cluster configuration to disk.","O(1)","3.0.0",CMD_DOC_NONE,NULL,NULL,"cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SAVECONFIG_History,0,CLUSTER_SAVECONFIG_Tips,0,clusterCommand,2,CMD_NO_ASYNC_LOADING|CMD_ADMIN|CMD_STALE,0,CLUSTER_SAVECONFIG_Keyspecs,0,NULL,0)},
 {MAKE_CMD("set-config-epoch","Sets the configuration epoch for a new node.","O(1)","3.0.0",CMD_DOC_NONE,NULL,NULL,"cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SET_CONFIG_EPOCH_History,0,CLUSTER_SET_CONFIG_EPOCH_Tips,0,clusterCommand,3,CMD_NO_ASYNC_LOADING|CMD_ADMIN|CMD_STALE,0,CLUSTER_SET_CONFIG_EPOCH_Keyspecs,0,NULL,1),.args=CLUSTER_SET_CONFIG_EPOCH_Args},
 {MAKE_CMD("setslot","Binds a hash slot to a node.","O(1)","3.0.0",CMD_DOC_NONE,NULL,NULL,"cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SETSLOT_History,1,CLUSTER_SETSLOT_Tips,0,clusterCommand,-4,CMD_NO_ASYNC_LOADING|CMD_ADMIN|CMD_STALE|CMD_MAY_REPLICATE,0,CLUSTER_SETSLOT_Keyspecs,0,NULL,3),.args=CLUSTER_SETSLOT_Args},
-{MAKE_CMD("shards","Returns the mapping of cluster slots to shards.","O(N) where N is the total number of cluster nodes","7.0.0",CMD_DOC_NONE,NULL,NULL,"cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SHARDS_History,0,CLUSTER_SHARDS_Tips,1,clusterCommand,2,CMD_LOADING|CMD_STALE,0,CLUSTER_SHARDS_Keyspecs,0,NULL,0)},
+{MAKE_CMD("shards","Returns the mapping of cluster slots to shards.","O(N) where N is the total number of cluster nodes","7.0.0",CMD_DOC_NONE,NULL,NULL,"cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SHARDS_History,1,CLUSTER_SHARDS_Tips,1,clusterCommand,2,CMD_LOADING|CMD_STALE,0,CLUSTER_SHARDS_Keyspecs,0,NULL,0)},
 {MAKE_CMD("slaves","Lists the replica nodes of a primary node.","O(N) where N is the number of replicas.","3.0.0",CMD_DOC_DEPRECATED,"`CLUSTER REPLICAS`","5.0.0","cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SLAVES_History,0,CLUSTER_SLAVES_Tips,1,clusterCommand,3,CMD_ADMIN|CMD_STALE,0,CLUSTER_SLAVES_Keyspecs,0,NULL,1),.args=CLUSTER_SLAVES_Args},
 {MAKE_CMD("slot-stats","Return an array of slot usage statistics for slots assigned to the current node.","O(N) where N is the total number of slots based on arguments. O(N*log(N)) with ORDERBY subcommand.","8.0.0",CMD_DOC_NONE,NULL,NULL,"cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SLOT_STATS_History,0,CLUSTER_SLOT_STATS_Tips,2,clusterSlotStatsCommand,-4,CMD_STALE|CMD_LOADING,0,CLUSTER_SLOT_STATS_Keyspecs,0,NULL,1),.args=CLUSTER_SLOT_STATS_Args},
 {MAKE_CMD("slots","Returns the mapping of cluster slots to nodes.","O(N) where N is the total number of Cluster nodes","3.0.0",CMD_DOC_NONE,NULL,NULL,"cluster",COMMAND_GROUP_CLUSTER,CLUSTER_SLOTS_History,2,CLUSTER_SLOTS_Tips,1,clusterCommand,2,CMD_LOADING|CMD_STALE,0,CLUSTER_SLOTS_Keyspecs,0,NULL,0)},

src/commands/cluster-shards.json

@@ -7,6 +7,12 @@
         "arity": 2,
         "container": "CLUSTER",
         "function": "clusterCommand",
+        "history": [
+            [
+                "9.0.0",
+                "Added shard id field to CLUSTER SHARDS response"
+            ]
+        ],
         "command_flags": [
             "LOADING",
             "STALE"
@@ -81,6 +87,10 @@
                                 }
                             }
                         }
+                    },
+                    "id": {
+                        "description": "A unique shard identifier.",
+                        "type": "string"
                     }
                 }
             }

tests/cluster/tests/28-cluster-shards.tcl

@@ -285,3 +285,28 @@ test "CLUSTER MYSHARDID reports same shard id after cluster restart" {
         assert_equal [dict get $node_ids $i] [R $i cluster myshardid]
     }
 }
+
+test "CLUSTER SHARDS id response validation" {
+    # For each node in the cluster
+    for {set i 0} {$i < $::cluster_master_nodes + $::cluster_replica_nodes} {incr i} {
+        # Get the CLUSTER SHARDS output from this node
+        set shards [R $i CLUSTER SHARDS]
+        set seen_shard_ids {}
+
+        # For each shard in the output
+        foreach shard $shards {
+            set shard_dict [dict create {*}$shard]
+
+            # 1. Verify 'id' key exists
+            assert {[dict exists $shard_dict id]}
+            set shard_id [dict get $shard_dict id]
+
+            # 2. Verify shard_id is a 40-char string
+            assert {[string length $shard_id] == 40}
+
+            # 3. Verify that for a given node's output, all shard IDs are unique
+            assert {[dict exists $seen_shard_ids $shard_id] == 0}
+            dict set seen_shard_ids $shard_id 1
+        }
+    }
+}