(iotdb) branch dev/1.3 updated: [To dev/1.3] Optimized the error log & enable retry for exceptions caused by concurrent removal of regions (#15076) #15078

[tanxinyu]

This is an automated email from the ASF dual-hosted git repository.

tanxinyu pushed a commit to branch dev/1.3
in repository https://gitbox.apache.org/repos/asf/iotdb.git


The following commit(s) were added to refs/heads/dev/1.3 by this push:
     new d60844b5aa3   [To dev/1.3] Optimized the error log & enable retry for 
exceptions caused by concurrent removal of regions (#15076) #15078
d60844b5aa3 is described below

commit d60844b5aa32c850245e41f6c9391ba44ec179bf
Author: Caideyipi <87789683+caidey...@users.noreply.github.com>
AuthorDate: Thu Mar 13 19:56:00 2025 +0800

      [To dev/1.3] Optimized the error log & enable retry for exceptions caused 
by concurrent removal of regions (#15076) #15078
---
 .../execution/executor/RegionWriteExecutor.java        | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git 
a/iotdb-core/datanode/src/main/java/org/apache/iotdb/db/queryengine/execution/executor/RegionWriteExecutor.java
 
b/iotdb-core/datanode/src/main/java/org/apache/iotdb/db/queryengine/execution/executor/RegionWriteExecutor.java
index 46b56804b36..1f11c86ad99 100644
--- 
a/iotdb-core/datanode/src/main/java/org/apache/iotdb/db/queryengine/execution/executor/RegionWriteExecutor.java
+++ 
b/iotdb-core/datanode/src/main/java/org/apache/iotdb/db/queryengine/execution/executor/RegionWriteExecutor.java
@@ -83,6 +83,7 @@ import java.util.Collections;
 import java.util.Iterator;
 import java.util.List;
 import java.util.Map;
+import java.util.Objects;
 import java.util.concurrent.locks.ReentrantReadWriteLock;
 
 public class RegionWriteExecutor {
@@ -142,9 +143,9 @@ public class RegionWriteExecutor {
   }
 
   @SuppressWarnings("squid:S1181")
-  public RegionExecutionResult execute(ConsensusGroupId groupId, PlanNode 
planNode) {
+  public RegionExecutionResult execute(final ConsensusGroupId groupId, final 
PlanNode planNode) {
     try {
-      ReentrantReadWriteLock lock = regionManager.getRegionLock(groupId);
+      final ReentrantReadWriteLock lock = regionManager.getRegionLock(groupId);
       if (lock == null) {
         return RegionExecutionResult.create(
             false,
@@ -152,7 +153,18 @@ public class RegionWriteExecutor {
             RpcUtils.getStatus(TSStatusCode.NO_AVAILABLE_REGION_GROUP));
       }
       return planNode.accept(executionVisitor, new 
WritePlanNodeExecutionContext(groupId, lock));
-    } catch (Throwable e) {
+    } catch (final Throwable e) {
+      // Detect problems caused by removed region
+      if (Objects.isNull(regionManager.getRegionLock(groupId))) {
+        final String errorMsg =
+            "Exception "
+                + e.getClass().getSimpleName()
+                + " encountered during region removal, will retry. Message: "
+                + e.getMessage();
+        LOGGER.info(errorMsg);
+        return RegionExecutionResult.create(
+            false, errorMsg, 
RpcUtils.getStatus(TSStatusCode.NO_AVAILABLE_REGION_GROUP));
+      }
       LOGGER.warn(e.getMessage(), e);
       return RegionExecutionResult.create(
           false,