<html><head><meta http-equiv="content-type" content="text/html; charset=utf-8"></head><body dir="auto"><div>Greetings G12,</div><div id="AppleMailSignature"><br></div><div id="AppleMailSignature">I am not sure how many received this email from Harut, so please read below.</div><div id="AppleMailSignature">I think we, g12, can help out drastically on this because we all know the amount of active analyses in g12 should not be on the order of 8.1 TB of data.</div><div id="AppleMailSignature"><br></div><div id="AppleMailSignature">I have previewed some directories from g12 members long departed.</div><div id="AppleMailSignature"><br></div><div id="AppleMailSignature">Please review your workspace for ONLY g12 stuff. CLAS12 data/analyses belong on the CLAS12 directory, same for GLUEX.</div><div id="AppleMailSignature"><br></div><div id="AppleMailSignature">Let's discuss this topic at our Tuesday meeting. I rather not be the experiment that had a hand in having the disk availability cut for halb.<br><br><div style="direction: inherit;"><span style="background-color: rgba(255, 255, 255, 0);">BR<br>MK <br>----------------------------------------<br>Michael C. Kunkel, USMC, PhD<br>Forschungszentrum Jülich<br>Nuclear Physics Institute and Juelich Center for Hadron Physics<br>Experimental Hadron Structure (IKP-1)</span></div><div style="direction: inherit;"><a href="http://www.fz-juelich.de/ikp">www.fz-juelich.de/ikp</a> </div></div><div><br>Begin forwarded message:<br><br></div><blockquote type="cite"><div><b>From:</b> Harut Avakian <<a href="mailto:avakian@jlab.org">avakian@jlab.org</a>><br><b>Date:</b> June 1, 2017 at 17:01:24 GMT+2<br><b>To:</b> "<a href="mailto:clas_offline@jlab.org">clas_offline@jlab.org</a>" <<a href="mailto:clas_offline@jlab.org">clas_offline@jlab.org</a>><br><b>Subject:</b> <b>[Clas_offline] Fwd: ENP consumption of disk space under /work</b><br><br></div></blockquote><blockquote type="cite"><div>
<meta http-equiv="content-type" content="text/html; charset=utf-8">
<p><br>
</p>
<div class="moz-forward-container"><br>
<br>
<p>Dear All,</p>
<p>As you can see from the e-mail below, keeping all our work
disk space requires some additional funding.<br>
</p>
<p>Option 3 will inevitably impact on farm operations, removing of
~20% space from Lustre. </p>
<p>We can also choose something between options 1) and 3).<br>
</p>
<p>Please revise the content and move at least 75% of what is in
/work/clas to either /cache or /volatile? <br>
</p>
<p>The current Hall-B usage includes:<br>
</p>
<p>550G hallb/bonus<br>
1.5T hallb/clase1<br>
3.6T hallb/clase1-6<br>
3.3T hallb/clase1dvcs<br>
2.8T hallb/clase1dvcs2<br>
987G hallb/clase1f<br>
1.8T hallb/clase2<br>
1.6G hallb/clase5<br>
413G hallb/clase6<br>
2.2T hallb/claseg1<br>
3.9T hallb/claseg1dvcs<br>
1.2T hallb/claseg3<br>
4.1T hallb/claseg4<br>
2.7T hallb/claseg5<br>
1.7T hallb/claseg6<br>
367G hallb/clas-farm-output<br>
734G hallb/clasg10<br>
601G hallb/clasg11<br>
8.1T hallb/clasg12<br>
2.4T hallb/clasg13<br>
2.4T hallb/clasg14<br>
28G hallb/clasg3<br>
5.8G hallb/clasg7<br>
269G hallb/clasg8<br>
1.2T hallb/clasg9<br>
1.3T hallb/clashps<br>
1.8T hallb/clas-production<br>
5.6T hallb/clas-production2<br>
1.4T hallb/clas-production3<br>
12T hallb/hps<br>
13T hallb/prad<br>
</p>
<p><br>
</p>
<p>Regards,</p>
Harut<br>
<div class="moz-forward-container"><br>
P.S. Few times we had crashes and they may also happen in
future, so keeping important files in /work is not recommended.<br>
You can see the list of lost files in
/site/scicomp/lostfiles.txt and
/site/scicomp/lostfiles-jan-2017.txt<br>
<br>
<br>
<br>
-------- Forwarded Message --------
<table class="moz-email-headers-table" border="0" cellpadding="0" cellspacing="0">
<tbody>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">Subject:
</th>
<td>ENP consumption of disk space under /work</td>
</tr>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">Date:
</th>
<td>Wed, 31 May 2017 10:35:51 -0400</td>
</tr>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">From:
</th>
<td>Chip Watson <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:watson@jlab.org"><watson@jlab.org></a></td>
</tr>
<tr>
<th align="RIGHT" nowrap="nowrap" valign="BASELINE">To: </th>
<td>Sandy Philpott <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:philpott@jlab.org"><philpott@jlab.org></a>,
Graham Heyes <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:heyes@jlab.org"><heyes@jlab.org></a>,
Ole Hansen <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:ole@jlab.org"><ole@jlab.org></a>,
Harut Avakian <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:avakian@jlab.org"><avakian@jlab.org></a>,
Brad Sawatzky <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:brads@jlab.org"><brads@jlab.org></a>,
Mark M. Ito <a moz-do-not-send="true" class="moz-txt-link-rfc2396E" href="mailto:marki@jlab.org"><marki@jlab.org></a></td>
</tr>
</tbody>
</table>
<br>
<br>
<pre>All,
As I have started on the procurement of the new /work file server, I
have discovered that Physics' use of /work has grown unrestrained over
the last year or two.
"Unrestrained" because there is no way under Lustre to restrain it
except via a very unfriendly Lustre quota system. As we leave some
quota headroom to accommodate large swings in usage for each hall for
cache and volatile, then /work continues to grow.
Total /work has now reached 260 TB, several times larger than I was
anticipating. This constitutes more than 25% of Physics' share of
Lustre, compared to LQCD which uses less than 5% of its disk space on
the un-managed /work.
It would cost Physics an extra $25K (total $35K - $40K) to treat the 260
TB as a requirement.
There are 3 paths forward:
(1) Physics cuts its use of /work by a factor of 4-5.
(2) Physics increases funding to $40K
(3) We pull a server out of Lustre, decreasing Physics' share of the
system, and use that as half of the new active-active pair, beefing it
up with SSDs and perhaps additional memory; this would actually shrink
Physics near term costs, but puts higher pressure on the file system for
the farm
The decision is clearly Physics', but I do need a VERY FAST response to
this question, as I need to move quickly now for LQCD's needs.
Hall D + GlueX, 96 TB
CLAS + CLAS12, 98 TB
Hall C, 35 TB
Hall A <unknown, still scanning>
Email, call (x7101), or drop by today 1:30-3:00 p.m. for discussion.
thanks,
Chip
</pre>
</div>
</div>
</div></blockquote><blockquote type="cite"><div><span>_______________________________________________</span><br><span>Clas_offline mailing list</span><br><span><a href="mailto:Clas_offline@jlab.org">Clas_offline@jlab.org</a></span><br><span><a href="https://mailman.jlab.org/mailman/listinfo/clas_offline">https://mailman.jlab.org/mailman/listinfo/clas_offline</a></span></div></blockquote></body></html>