[dolphinscheduler] branch 2.0.8-prepare updated: [Fix-13409] [Worker] concurrent task response occasional cause status error (#13433)

[zhongjiajie]

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

zhongjiajie pushed a commit to branch 2.0.8-prepare
in repository https://gitbox.apache.org/repos/asf/dolphinscheduler.git


The following commit(s) were added to refs/heads/2.0.8-prepare by this push:
     new 02a53f59ab [Fix-13409] [Worker] concurrent task response occasional 
cause status error (#13433)
02a53f59ab is described below

commit 02a53f59ab63f1daa2394b01608598179fac8ef7
Author: JinYong Li <42576980+jinyleech...@users.noreply.github.com>
AuthorDate: Thu Jan 19 16:20:51 2023 +0800

    [Fix-13409] [Worker] concurrent task response occasional cause status error 
(#13433)
---
 .../server/master/runner/WorkflowExecuteThread.java               | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git 
a/dolphinscheduler-server/src/main/java/org/apache/dolphinscheduler/server/master/runner/WorkflowExecuteThread.java
 
b/dolphinscheduler-server/src/main/java/org/apache/dolphinscheduler/server/master/runner/WorkflowExecuteThread.java
index 9dfac7bffc..2dba7b2a18 100644
--- 
a/dolphinscheduler-server/src/main/java/org/apache/dolphinscheduler/server/master/runner/WorkflowExecuteThread.java
+++ 
b/dolphinscheduler-server/src/main/java/org/apache/dolphinscheduler/server/master/runner/WorkflowExecuteThread.java
@@ -46,6 +46,7 @@ import org.apache.dolphinscheduler.common.model.TaskNode;
 import org.apache.dolphinscheduler.common.model.TaskNodeRelation;
 import org.apache.dolphinscheduler.common.process.ProcessDag;
 import org.apache.dolphinscheduler.common.process.Property;
+import org.apache.dolphinscheduler.common.thread.ThreadUtils;
 import org.apache.dolphinscheduler.common.utils.DateUtils;
 import org.apache.dolphinscheduler.common.utils.JSONUtils;
 import org.apache.dolphinscheduler.common.utils.NetUtils;
@@ -404,9 +405,14 @@ public class WorkflowExecuteThread implements Runnable {
             return true;
         }
         if (task.getState().typeIsFinished()) {
-            if 
(completeTaskList.containsKey(Long.toString(task.getTaskCode())) && 
completeTaskList.get(Long.toString(task.getTaskCode())).getId() == 
task.getId()) {
+            if 
(completeTaskList.containsKey(Long.toString(task.getTaskCode())) && 
completeTaskList.get(Long.toString(task.getTaskCode())).getId() == task.getId()
+                && task.getState() != ExecutionStatus.NEED_FAULT_TOLERANCE) {
                 return true;
             }
+            if (task.getStartTime() == null) {
+                logger.info("Maybe TASK_EXECUTE_ACK has not been received when 
the task finish, will wait for one second");
+                ThreadUtils.sleep(Constants.SLEEP_TIME_MILLIS);
+            }
             taskFinished(task);
             return true;
         }