From 6af8aa571d237bb6a7236ffa8abe8667a2185c37 Mon Sep 17 00:00:00 2001
From: Thomas Kluyver <thomas@kluyver.me.uk>
Date: Mon, 5 Jun 2023 09:22:39 +0100
Subject: [PATCH] NODE_FAIL is not a finished state; jobs will be requeued

---
 webservice/job_monitor.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/webservice/job_monitor.py b/webservice/job_monitor.py
index 207e4442d..f7d841321 100644
--- a/webservice/job_monitor.py
+++ b/webservice/job_monitor.py
@@ -25,7 +25,7 @@ log = logging.getLogger(__name__)
 
 STATES_FINISHED = {  # https://slurm.schedmd.com/squeue.html#lbAG
     'BOOT_FAIL',  'CANCELLED', 'COMPLETED',  'DEADLINE', 'FAILED',
-    'NODE_FAIL', 'OUT_OF_MEMORY', 'PREEMPTED', 'SPECIAL_EXIT', 'TIMEOUT',
+    'OUT_OF_MEMORY', 'PREEMPTED', 'SPECIAL_EXIT', 'TIMEOUT',
 }
 
 
-- 
GitLab