From ee1d27ee06685d70367577954527cea8a5dae07b Mon Sep 17 00:00:00 2001
From: Peng Junzhi <201250214@smail.nju.edu.cn>
Date: Sat, 18 Apr 2026 00:35:19 +0800
Subject: [PATCH] Fix region migration retries and peer recreation

---
 .../procedure/env/RegionMaintainHandler.java     | 16 +++++++++++-----
 .../apache/iotdb/consensus/iot/IoTConsensus.java |  9 ++++++++-
 2 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/iotdb-core/confignode/src/main/java/org/apache/iotdb/confignode/procedure/env/RegionMaintainHandler.java b/iotdb-core/confignode/src/main/java/org/apache/iotdb/confignode/procedure/env/RegionMaintainHandler.java
index 5043becc1fad5..34d4802c1c4f4 100644
--- a/iotdb-core/confignode/src/main/java/org/apache/iotdb/confignode/procedure/env/RegionMaintainHandler.java
+++ b/iotdb-core/confignode/src/main/java/org/apache/iotdb/confignode/procedure/env/RegionMaintainHandler.java
@@ -96,6 +96,7 @@
 public class RegionMaintainHandler {
 
   private static final Logger LOGGER = LoggerFactory.getLogger(RegionMaintainHandler.class);
+  private static final int DELETE_OLD_REGION_PEER_RPC_RETRY_NUM = 3;
 
   private static final ConfigNodeConfig CONF = ConfigNodeDescriptor.getInstance().getConf();
 
@@ -175,7 +176,10 @@ public TSStatus createNewRegionPeer(TConsensusGroupId regionId, TDataNodeLocatio
             || IOT_CONSENSUS_V2.equals(CONF.getDataRegionConsensusProtocolClass()))) {
       // parameter of createPeer for MultiLeader should be all peers
       currentPeerNodes = new ArrayList<>(regionReplicaNodes);
-      currentPeerNodes.add(destDataNode);
+      if (currentPeerNodes.stream()
+          .noneMatch(node -> node.getDataNodeId() == destDataNode.getDataNodeId())) {
+        currentPeerNodes.add(destDataNode);
+      }
     } else {
       // parameter of createPeer for Ratis can be empty
       currentPeerNodes = Collections.emptyList();
@@ -299,15 +303,17 @@ public TSStatus submitDeleteOldRegionPeerTask(
     TMaintainPeerReq maintainPeerReq =
         new TMaintainPeerReq(regionId, originalDataNode, procedureId);
 
-    // Always use full retries regardless of node status, because after a cluster crash the
-    // target DataNode may be Unknown but still in the process of restarting.
+    // RemoveRegionPeerProcedure already retries DELETE_OLD_REGION_PEER at the procedure level.
+    // Keep each RPC attempt bounded so a permanently down original DataNode does not block the
+    // procedure for minutes, while still tolerating a briefly restarting node after cluster crash.
     status =
         (TSStatus)
             SyncDataNodeClientPool.getInstance()
-                .sendSyncRequestToDataNodeWithRetry(
+                .sendSyncRequestToDataNodeWithGivenRetry(
                     originalDataNode.getInternalEndPoint(),
                     maintainPeerReq,
-                    CnToDnSyncRequestType.DELETE_OLD_REGION_PEER);
+                    CnToDnSyncRequestType.DELETE_OLD_REGION_PEER,
+                    DELETE_OLD_REGION_PEER_RPC_RETRY_NUM);
     LOGGER.info(
         "{}, Send action deleteOldRegionPeer finished, regionId: {}, dataNodeId: {}",
         REGION_MIGRATE_PROCESS,
diff --git a/iotdb-core/consensus/src/main/java/org/apache/iotdb/consensus/iot/IoTConsensus.java b/iotdb-core/consensus/src/main/java/org/apache/iotdb/consensus/iot/IoTConsensus.java
index 959191ca2d6d3..5e59c1a727368 100644
--- a/iotdb-core/consensus/src/main/java/org/apache/iotdb/consensus/iot/IoTConsensus.java
+++ b/iotdb-core/consensus/src/main/java/org/apache/iotdb/consensus/iot/IoTConsensus.java
@@ -273,10 +273,17 @@ public void createLocalPeer(ConsensusGroupId groupId, List<Peer> peers)
 
                   String path = buildPeerDir(storageDir, groupId);
                   File file = new File(path);
-                  if (!file.mkdirs()) {
+                  if (!file.exists() && !file.mkdirs()) {
                     logger.warn("Unable to create consensus dir for group {} at {}", groupId, path);
                     return null;
                   }
+                  if (!file.isDirectory()) {
+                    logger.warn(
+                        "Consensus dir path for group {} exists but is not a directory: {}",
+                        groupId,
+                        path);
+                    return null;
+                  }
 
                   IoTConsensusServerImpl impl =
                       new IoTConsensusServerImpl(