Browse Source

[Bug-11101] fix task failover NPE (#11168)

(cherry picked from commit 6c7e00c4aa)
3.0.0/version-upgrade
caishunfeng 2 years ago committed by Jiajie Zhong
parent
commit
034475bfbe
  1. 22
      dolphinscheduler-master/src/main/java/org/apache/dolphinscheduler/server/master/service/MasterFailoverService.java

22
dolphinscheduler-master/src/main/java/org/apache/dolphinscheduler/server/master/service/MasterFailoverService.java

@ -40,6 +40,7 @@ import org.apache.dolphinscheduler.server.master.runner.task.TaskProcessorFactor
import org.apache.dolphinscheduler.server.utils.ProcessUtils;
import org.apache.dolphinscheduler.service.process.ProcessService;
import org.apache.dolphinscheduler.service.registry.RegistryClient;
import org.apache.dolphinscheduler.spi.utils.StringUtils;
import org.apache.commons.collections4.CollectionUtils;
import org.apache.commons.lang3.time.StopWatch;
@ -232,6 +233,20 @@ public class MasterFailoverService {
// kill worker task, When the master failover and worker failover happened in the same time,
// the task may not be failover if we don't set NEED_FAULT_TOLERANCE.
// This can be improved if we can load all task when cache a workflowInstance in memory
sendKillCommandToWorker(taskInstance);
} else {
LOGGER.info("The failover taskInstance is a master task");
}
taskInstance.setState(ExecutionStatus.NEED_FAULT_TOLERANCE);
taskInstance.setFlag(Flag.NO);
processService.saveTaskInstance(taskInstance);
}
private void sendKillCommandToWorker(@NonNull TaskInstance taskInstance) {
if (StringUtils.isEmpty(taskInstance.getHost())) {
return;
}
try {
TaskKillRequestCommand killCommand = new TaskKillRequestCommand(taskInstance.getId());
Host workerHost = Host.of(taskInstance.getHost());
@ -240,13 +255,6 @@ public class MasterFailoverService {
} catch (ExecuteException e) {
LOGGER.error("Kill task failed", e);
}
} else {
LOGGER.info("The failover taskInstance is a master task");
}
taskInstance.setState(ExecutionStatus.NEED_FAULT_TOLERANCE);
taskInstance.setFlag(Flag.NO);
processService.saveTaskInstance(taskInstance);
}
private boolean checkTaskInstanceNeedFailover(@NonNull TaskInstance taskInstance) {

Loading…
Cancel
Save