<div dir="ltr"><br><div class="gmail_extra"><br><div class="gmail_quote">On 26 January 2017 at 13:50, Kent Engström <span dir="ltr"><<a href="mailto:kent@nsc.liu.se" target="_blank">kent@nsc.liu.se</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">Peter Bortas <<a href="mailto:zino@nsc.liu.se">zino@nsc.liu.se</a>> writes:<br>
> Dear Bi users,<br>
><br>
> Thursday next week (26 Jan) Bi will be down for maintenance 12:30-13:30 CET.<br>
<br>
</span>We have run into some problems while doing this maintenance. Bi is down<br>
for some more time while we investigate this.<br></blockquote><div><br></div><div>Bi is now up and running jobs.<br></div><div> <span class=""></span><br><span class=""></span></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">
> After the stop the filesystems fouo6, rossby20 and smhid13 will remain<br>
> unavailable until 21:00 to fix the issues I informed about before<br>
> Christmas.<br>
><br>
> Any jobs that start between 13:30 and 21:00 that require those<br>
> filesystems will fail. Unfortunately the system does not know what<br>
> filesystems a job will use during a run, so the only way to avoid that<br>
> would be to make the cluster unavailable until all filesystems are<br>
> back.</span></blockquote><div><br></div><div>fouo6, rossby20 and smhid13 might not be back before 21:00 due to the delays caused by Bi' restart problems. I will send a new update when they are back.<br><br></div><div>Regards,<br>-- <br></div><div>Peter Bortas, NSC<br></div><div><br><br></div></div></div></div>