<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Dear Colleagues,</p>
<p>There is a motion in other halls to move processes for monitoring
and controls from dedicated hardware to centrally administered
virtual machines (see below). Please let me know in case you see
any use-cases in Hall D.</p>
<p>Best regards,</p>
<p>Alex<br>
</p>
<div class="moz-forward-container"><br>
<br>
-------- Forwarded Message --------
<table class="moz-email-headers-table" cellspacing="0"
cellpadding="0" border="0">
<tbody>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">Subject:
</th>
<td>[EXTERNAL] Interest in a dedicated ENP/Hall VM cluster?</td>
</tr>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">Date: </th>
<td>Tue, 24 May 2022 12:19:10 -0400</td>
</tr>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">From: </th>
<td>Brad Sawatzky <a class="moz-txt-link-rfc2396E" href="mailto:brads@jlab.org"><brads@jlab.org></a></td>
</tr>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">To: </th>
<td>Ole Hansen <a class="moz-txt-link-rfc2396E" href="mailto:ole@jlab.org"><ole@jlab.org></a>, Nathan Baltzell
<a class="moz-txt-link-rfc2396E" href="mailto:baltzell@jlab.org"><baltzell@jlab.org></a>, David Lawrence
<a class="moz-txt-link-rfc2396E" href="mailto:davidl@jlab.org"><davidl@jlab.org></a>, Thomas Britton
<a class="moz-txt-link-rfc2396E" href="mailto:tbritton@jlab.org"><tbritton@jlab.org></a>, Alexander Austregesilo
<a class="moz-txt-link-rfc2396E" href="mailto:aaustreg@jlab.org"><aaustreg@jlab.org></a></td>
</tr>
<tr>
<th valign="BASELINE" nowrap="nowrap" align="RIGHT">CC: </th>
<td>Bryan Hess <a class="moz-txt-link-rfc2396E" href="mailto:bhess@jlab.org"><bhess@jlab.org></a>, Graham Heyes
<a class="moz-txt-link-rfc2396E" href="mailto:heyes@jlab.org"><heyes@jlab.org></a></td>
</tr>
</tbody>
</table>
<br>
<br>
Hi all,<br>
<br>
I touched on this at the last SciComp meeting and am working out<br>
the (initial) scope for a dedicated 'Hall' VM cluster.<br>
<br>
It would help if each Compute Coordinator could respond with a<br>
rough list of hosts/use-cases that might be better served by being<br>
on a VM rather than dedicated hardware.<br>
<br>
As an example, here is what I would like Hall C migrate to VMs.<br>
The '*'s indicate my initial priorities. The [] lines are
estimates of<br>
VM resource allocations that will help spec the needed VM cluster
HW.<br>
(Note that none of these are intended to be "high performance"
systems,<br>
but they are all to some degree critical path for Hall
operations.)<br>
<br>
-- Hall C --<br>
*'skylla10': Win10 based system running Hall C HMI/PLC
spectrometer<br>
controls (main backend server).<br>
[16GB RAM, CPUS:2, 1TB disk; user interactive]<br>
*'cmagnets': Win10 system providing Shift Worker 'User'
spectrometer<br>
controls.<br>
[8GB RAM, CPUS:2, 500TB disk; user interactive]<br>
<br>
*EPICS SoftIOCs : JLab/RHEL system providing monitoring, alarms,
data<br>
logging, etc for many Hall C systems (cryo, magnets, target,<br>
high-voltage, etc)<br>
[2GB RAM, CPUS:2, 500TB disk]<br>
<br>
CryoTarget User Controls : Linux host providing user controls<br>
to Target Operators. Non-standard linux install, presently<br>
on dedicated hardware. A VM that can be brought up on<br>
standard Hall Cluster hosts would have advantages.<br>
[8GB RAM, CPUS:2, 500TB disk; user interactive]<br>
<br>
etc...<br>
<br>
<br>
Just to remind people, the primary function of this cluster would
be to<br>
move systems providing slow-controls, monitoring, softIOC support,
etc<br>
off dedicated hardware to VMs. That would allow us to take
advantage of<br>
VM features like snapshotting, improved/simplified fail-over, etc.<br>
<br>
Roughly speaking this VM cluster would need to follow these
guidelines:<br>
- Physically located inside the accelerator fence<br>
- existing compute racks on 2nd floor CH?<br>
- generator and battery backed power<br>
- It would follow the "Experimental Hall Computing" directive and
be<br>
as independent of the central resources as possible.<br>
- For example, the VM cluster hosts should stay up and remain<br>
functional if a network link to the main campus goes down.<br>
- It will be maintained independently of the central systems<br>
and existing ESX cluster.<br>
- Updates/changes would need to be scheduled with direct input
from<br>
the Hall Compute Coordinators.<br>
- etc..<br>
- VMs would be mapped directly the relevant Hall VLANs/subnets<br>
<br>
<br>
-- Brad<br>
<br>
<pre class="moz-signature">--
Brad Sawatzky (he/him), PhD <a class="moz-txt-link-rfc2396E" href="mailto:brads@jlab.org"><brads@jlab.org></a> -<>- Jefferson Lab/ Hall C/C111
Ph: 757-269-5947 -<>- Fax: 757-269-5235 -<>- Pager: <a class="moz-txt-link-abbreviated" href="mailto:brads-page@jlab.org">brads-page@jlab.org</a>
The most exciting phrase to hear in science, the one that heralds new
discoveries, is not "Eureka!" but "That's funny..." -- Isaac Asimov
</pre>
</div>
</body>
</html>