Avoid to set nodes into DOWN if no nodes are passed as input

Avoid to set nodes into DOWN, hence avoid calling Slurm scontrol update, if node list is empty Avoided log line is ``` 2023-09-19 10:56:39,439 - [slurm_plugin.resume:_handle_failed_nodes] - INFO - Setting following failed nodes into DOWN state (x0) [] with reason: (Code:LimitedInstanceCapacity)Failure when resuming nodes ``` Signed-off-by: Luca Carrogu <[email protected]>
aws · Sep 19, 2023 · 125c7c0 · 125c7c0
1 parent 0d033ef
commit 125c7c0
Showing 1 changed file with 13 additions and 12 deletions.
diff --git a/src/slurm_plugin/resume.py b/src/slurm_plugin/resume.py
@@ -157,18 +157,19 @@ def _handle_failed_nodes(node_list, reason="Failure when resuming nodes"):
     To save time, should explicitly set nodes to DOWN in ResumeProgram so clustermgtd can maintain failed nodes.
     Clustermgtd will be responsible for running full DOWN -> POWER_DOWN process.
     """
-    try:
-        log.info(
-            "Setting following failed nodes into DOWN state %s with reason: %s", print_with_count(node_list), reason
-        )
-        set_nodes_down(node_list, reason=reason)
-    except Exception as e:
-        log.error(
-            "Failed to place nodes %s into DOWN for reason %s with exception: %s",
-            print_with_count(node_list),
-            reason,
-            e,
-        )
+    if node_list:
+        try:
+            log.info(
+                "Setting following failed nodes into DOWN state %s with reason: %s", print_with_count(node_list), reason
+            )
+            set_nodes_down(node_list, reason=reason)
+        except Exception as e:
+            log.error(
+                "Failed to place nodes %s into DOWN for reason %s with exception: %s",
+                print_with_count(node_list),
+                reason,
+                e,
+            )
 
 
 def _resume(arg_nodes, resume_config, slurm_resume):