Merge "Fix iDRAC import configuration missing task handling"

ironic/drivers/modules/drac/management.py

@@ -535,7 +535,29 @@ class DracRedfishManagement(redfish_management.RedfishManagement):
         """Checks progress of running import configuration task"""
 
         node = task.node
-        task_monitor = redfish_utils.get_task_monitor(node, task_monitor_url)
+        try:
+            task_monitor = redfish_utils.get_task_monitor(
+                node, task_monitor_url)
+        except exception.RedfishError as e:
+            error_msg = (_("Failed import configuration task: "
+                           "%(task_monitor_url)s. Message: '%(message)s'. "
+                           "Most likely this happened because could not find "
+                           "the task anymore as it got deleted by iDRAC. "
+                           "If not already, upgrade iDRAC firmware to "
+                           "5.00.00.00 or later that preserves tasks for "
+                           "longer or decrease "
+                           "[drac]query_import_config_job_status_interval")
+                         % {'task_monitor_url': task_monitor_url,
+                            'message': e})
+            log_msg = ("Import configuration task failed for node "
+                       "%(node)s. %(error)s" % {'node': task.node.uuid,
+                                                'error': error_msg})
+            info = node.driver_internal_info
+            info.pop('import_task_monitor_url', None)
+            node.driver_internal_info = info
+            node.save()
+            self._set_failed(task, log_msg, error_msg)
+            return
 
         if not task_monitor.is_processing:
             import_task = task_monitor.get_task()

ironic/tests/unit/drivers/modules/drac/test_management.py

@@ -1088,6 +1088,25 @@ class DracRedfishManagementTestCase(test_utils.BaseDracTest):
             ._check_import_configuration_task
             .assert_called_once_with(task, '/TaskService/123'))
 
+    @mock.patch.object(redfish_utils, 'get_task_monitor', autospec=True)
+    def test__check_import_configuration_task_missing(
+            self, mock_get_task_monitor):
+        mock_get_task_monitor.side_effect = exception.RedfishError(
+            error='Task not found')
+        self.management._set_success = mock.Mock()
+        self.management._set_failed = mock.Mock()
+
+        with task_manager.acquire(self.context, self.node.uuid,
+                                  shared=False) as task:
+            self.management._check_import_configuration_task(
+                task, '/TaskService/123')
+
+            self.management._set_failed.assert_called_once_with(
+                task, mock.ANY, mock.ANY)
+            self.management._set_success.assert_not_called()
+            self.assertIsNone(
+                task.node.driver_internal_info.get('import_task_monitor_url'))
+
     @mock.patch.object(drac_mgmt.LOG, 'debug', autospec=True)
     @mock.patch.object(redfish_utils, 'get_task_monitor', autospec=True)
     def test__check_import_configuration_task_still_processing(

releasenotes/notes/idrac-import-configuration-task-deleted-2a0e6a96509394b6.yaml

@@ -0,0 +1,12 @@
+---
+fixes:
+  - |
+    Fix ``idrac-redfish`` clean/deploy step ``import_configuration`` to handle
+    completed import configuration tasks that are deleted by iDRAC before
+    Ironic has checked task's status.
+    Prior iDRAC firmware version 5.00.00.00 completed tasks are deleted after
+    1 minute in iDRAC Redfish. That is not always sufficient to check for
+    their status in periodic check that runs every minute by default. Before
+    this fix node got stuck in wait mode forever. This is fixed by failing the
+    step with error informing to decrease periodic check interval or upgrade
+    iDRAC firmware if not done already.