<!DOCTYPE html>
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Dear Slurm User list,</p>
<p>using <a class="moz-txt-link-freetext" href="https://slurm.schedmd.com/power_save.html">https://slurm.schedmd.com/power_save.html</a> we had one case
out of many (>242) node starts that resulted in</p>
<pre class="notranslate"><code class="notranslate">slurm_update error: Invalid node state specified</code></pre>
<p></p>
<p>when we called:</p>
<p><code class="notranslate">scontrol update NodeName="$1"
state=RESUME reason=FailedStartup</code></p>
<p>in the Fail script. We run this to make 100% sure that the
instances - that are created on demand - are again `~idle` after
being removed by the fail program. They are set to RESUME before
the actual instance gets destroyed. I remember that I had this
case manually before, but I don't remember when it occurs.</p>
<p>Maybe someone has a great idea how to tackle this problem.</p>
<p>Best regards<br>
Xaver Stiensmeier<br>
</p>
</body>
</html>