<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="overflow-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;">
Hi,
<div><br>
</div>
<div>As explained in the Lustre Operations Manual in this section:</div>
<div><a href="https://doc.lustre.org/lustre_manual.xhtml#idm139831573757696">https://doc.lustre.org/lustre_manual.xhtml#idm139831573757696</a></div>
<div>it is required to define a nodemap that matches all server nodes, with admin and trusted to 1.</div>
<div>Have you?</div>
<div><br>
</div>
<div>Cheers,</div>
<div>Sebastien.<br id="lineBreakAtBeginningOfMessage">
<div><br>
<blockquote type="cite">
<div>Le 9 janv. 2025 à 13:03, Thomas Roth <dibbegucker@googlemail.com> a écrit :</div>
<br class="Apple-interchange-newline">
<div>
<div>[Vous ne recevez pas souvent de courriers de dibbegucker@googlemail.com. D?couvrez pourquoi ceci est important ? https://aka.ms/LearnAboutSenderIdentification ]<br>
<br>
Hi all,<br>
<br>
we have just switched on nodemap on our 2.12 cluster, with all batch clients being trusted=1 but admin=0, so bascially root-squashing.<br>
<br>
The batch system is done by Slurm.<br>
<br>
Now all jobs are failing, when the user's directory on Lustre is not world-readable ("permission denied").<br>
<br>
RW - Access in the shell is not a problem.<br>
<br>
<br>
<br>
Any site running Slurm and having encountered a similar issue?<br>
<br>
<br>
Regards,<br>
Thomas<br>
<br>
<br>
Perhaps I should add that I have used the default nodemap for this, to avoid having to specify many hundreds of non-contiguous batch node IP ranges.<br>
_______________________________________________<br>
lustre-discuss mailing list<br>
lustre-discuss@lists.lustre.org<br>
http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org<br>
</div>
</div>
</blockquote>
</div>
<br>
</div>
</body>
</html>