<div dir="ltr"><div class="gmail_default" style="font-size:small">FYI. Please mark this maintenance on your calendars and plan accordingly.</div><div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div style="margin:0px;padding:0px;border:0px;font-stretch:inherit;font-size:12pt;line-height:inherit;font-family:Calibri,Arial,Helvetica,sans-serif;vertical-align:baseline;color:black"><br></div></div></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">---------- Forwarded message ---------<br>From: <span dir="auto"><<a href="mailto:no-reply@hpcc.ucr.edu">no-reply@hpcc.ucr.edu</a>></span><br>Date: Tue, Jul 18, 2023 at 9:04 PM<br>Subject: [HPCC] Maintenance Shutdown Confirmation<br>To: <<a href="mailto:no-reply@hpcc.ucr.edu">no-reply@hpcc.ucr.edu</a>><br></div><br><br><p>Hello HPCC users,</p>
<p>HPCC staff will be performing a maintenance shutdown on <strong>Friday, August 4, 2023</strong>
at <strong>noon</strong>, and will last into <strong>Saturday afternoon</strong>. This shutdown will focus on
finalizing electrical work that began during the May shutdown, which is
necessary for supporting the incoming NSF-funded nodes, as well as activating
all available bigdata storage space. In addition, routine updates to system
software will be performed.</p>
<p>During the shutdown, all of our online services hosted from the Genomics Building
will be unavailable. This includes, but is not limited to: SSH, Slurm, Rstudio Server,
JupyterHub, web file access, and email support. Our primary method of communication
during the shutdown will be our Slack channel:</p>
<p><a href="https://ucr-hpcc.slack.com/" target="_blank">https://ucr-hpcc.slack.com/</a></p>
<p>If your compute job duration extends into the maintenance window, you will receive
a "ReqNodeNotAvail" error, and your job will not start. It is recommended to reduce
the duration of your job such that it will finish before the aformentioned time.
<strong>Unlike the previous shutdown, we are expecting to start from a fresh Slurm
installation. What this means is that pending jobs will not automatically start
after the shutdown; you must manually resubmit your pending jobs.</strong></p>
<p>We understand that interruptions like this are disruptive to your research
and teaching, and for that we apologize. However, these maintenance shutdowns
are necessary for the reliability and performance of our cluster services.
Thank you for your understanding.</p>
<p>Sincerely,</p>
<p>Austin Leong<br>
UCR High Performance Computing Center</p></div></div>