<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body text="#000000" bgcolor="#FFFFFF">
<p>Thank you all for your answers, I will research some more along
these lines!</p>
<p>Any other opinion is welcome<br>
</p>
<p>Regards,</p>
<p>Antonio<br>
</p>
<br>
<div class="moz-cite-prefix">El 11/05/18 a las 16:05, Vicker, Darby
(JSC-EG311) escribió:<br>
</div>
<blockquote type="cite"
cite="mid:41690EE7-7679-4A01-8F1E-D637D45CCED3@nasa.gov">
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<meta name="Generator" content="Microsoft Word 15 (filtered
medium)">
<style><!--
/* Font Definitions */
@font-face
{font-family:Courier;
panose-1:2 0 5 0 0 0 0 0 0 0;}
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Calibri;
panose-1:2 15 5 2 2 2 4 3 2 4;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
margin-bottom:.0001pt;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
a:link, span.MsoHyperlink
{mso-style-priority:99;
color:blue;
text-decoration:underline;}
a:visited, span.MsoHyperlinkFollowed
{mso-style-priority:99;
color:purple;
text-decoration:underline;}
p.msonormal0, li.msonormal0, div.msonormal0
{mso-style-name:msonormal;
mso-margin-top-alt:auto;
margin-right:0in;
mso-margin-bottom-alt:auto;
margin-left:0in;
font-size:11.0pt;
font-family:"Calibri",sans-serif;}
span.EmailStyle18
{mso-style-type:personal-reply;
font-family:"Calibri",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:10.0pt;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style>
<div class="WordSection1">
<p class="MsoNormal">I’ll second that – we have a cluster with 4
generations of nodes. We assign a processor type feature to
each node and require the users to ask for at least one of
those features in their jobs via job_submit.lua – see the code
below. For a job that can run on any processor type, you can
use this:<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">#SBATCH --constraint=[wes|san|has|bro]<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">See the constraint section of “man sbatch”
for more details but this will constrain the job to any
processor type but all nodes of one type. It really works
great from a utilization standpoint – jobs will run on the
first processor type that is free. <o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><span style="font-family:Courier"> local
feature_count = 0<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> if
job_desc ~= nil and job_desc.features ~= nil then<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> if
string.match(job_desc.features, "wes") then
feature_count=feature_count+1 end<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> if
string.match(job_desc.features, "san") then
feature_count=feature_count+1 end<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> if
string.match(job_desc.features, "has") then
feature_count=feature_count+1 end<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> if
string.match(job_desc.features, "bro") then
feature_count=feature_count+1 end<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> end<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"><o:p> </o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> if
feature_count > 0 then<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier">
slurm.log_info("Found %s valid cpu features",feature_count)<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> else<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier">
slurm.log_user("Invalid features - aerolab policy requires
specifying one or more of wes,san,has,bro.")<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier">
slurm.log_error("Found %s cpu features from
%s",feature_count,submit_uid)<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> --
See slurm/slurm_errno.h and src/common/slurm_errno.c<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> --
for the list of error codes and messages.<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier">
return 2002<o:p></o:p></span></p>
<p class="MsoNormal"><span style="font-family:Courier"> end<o:p></o:p></span></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Of course, the user can leave off the
square brackets and get any mix of processor types. We have
some codes that run fine across different processor types so
we allow this. Our group is small enough that we can easily
educate and police the users to do the right thing. But you
could add more logic to job_submit.lua to require the brackets
if you wanted to.
<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal">Darby<o:p></o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<p class="MsoNormal"><o:p> </o:p></p>
<div style="border:none;border-top:solid #B5C4DF
1.0pt;padding:3.0pt 0in 0in 0in">
<p class="MsoNormal"><b><span
style="font-size:12.0pt;color:black">From: </span></b><span
style="font-size:12.0pt;color:black">slurm-users
<a class="moz-txt-link-rfc2396E" href="mailto:slurm-users-bounces@lists.schedmd.com"><slurm-users-bounces@lists.schedmd.com></a> on behalf of
Hadrian Djohari <a class="moz-txt-link-rfc2396E" href="mailto:hxd58@case.edu"><hxd58@case.edu></a><br>
<b>Reply-To: </b>Slurm User Community List
<a class="moz-txt-link-rfc2396E" href="mailto:slurm-users@lists.schedmd.com"><slurm-users@lists.schedmd.com></a><br>
<b>Date: </b>Friday, May 11, 2018 at 5:22 AM<br>
<b>To: </b>Slurm User Community List
<a class="moz-txt-link-rfc2396E" href="mailto:slurm-users@lists.schedmd.com"><slurm-users@lists.schedmd.com></a><br>
<b>Cc: </b><a class="moz-txt-link-rfc2396E" href="mailto:slurm-users@schedmd.com">"slurm-users@schedmd.com"</a>
<a class="moz-txt-link-rfc2396E" href="mailto:slurm-users@schedmd.com"><slurm-users@schedmd.com></a><br>
<b>Subject: </b>Re: [slurm-users] Distribute jobs in
similar nodes in the same partition<o:p></o:p></span></p>
</div>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">You can use node feature in defining the
node types in slurm.conf.
<o:p></o:p></p>
<div>
<p class="MsoNormal"><o:p> </o:p></p>
</div>
<div>
<p class="MsoNormal">Then when requesting for the job, use
-C <feature name> toy just use those node type.<o:p></o:p></p>
</div>
</div>
<p class="MsoNormal"><o:p> </o:p></p>
<div>
<div>
<p class="MsoNormal">On Fri, May 11, 2018, 5:38 AM Antonio
Lara <<a href="mailto:antonio.lara@uam.es"
moz-do-not-send="true">antonio.lara@uam.es</a>>
wrote:<o:p></o:p></p>
</div>
<blockquote style="border:none;border-left:solid #CCCCCC
1.0pt;padding:0in 0in 0in
6.0pt;margin-left:4.8pt;margin-right:0in">
<p class="MsoNormal" style="margin-bottom:12.0pt">Hello
everyone,<br>
<br>
Hopefully someone can help me with this, I cannot find in
the manual if <br>
this is even possible:<br>
<br>
I'm a system administrator, and the following question is
from the <br>
administrator point of view, not the user's point of view:<br>
<br>
I work with a cluster which has a partition containing
many nodes. These <br>
nodes belong to "different categories". This is, we bought
at once <br>
several machines that are of the same type, and we did
this several <br>
times. So, for example, we have 10 machines of type A, 20
machines of <br>
type B and 15 machines of type C. Machines of type A are
more powerful <br>
than machines of type B, which are more powerful than
machines of type C.<br>
<br>
What I am trying to achieve is that Slurm "forces"
parallelized jobs to <br>
be allocated in machines of the same type, if possible.
That is, that <br>
there is some type of priority which tries to allocate
only machines of <br>
type A, or only machines of type B, or only of type C, and
only <br>
distribute jobs among machines of different types when
there are not <br>
enough nodes of the same type available.<br>
<br>
Does anyone know if this is possible? The idea behind this
is that <br>
slower machines are not delaying the calculations in
faster machines <br>
when a job is distributed among them, and all machines
work more or less <br>
at the same pace.<br>
<br>
I've been told that It is NOT an option to create
different partitions, <br>
each containing only one type of machine.<br>
<br>
Please, note that I'm not looking for a way to choose as a
user which <br>
nodes to use for a job, what I need is that slurm does
that, and decides <br>
what nodes to use, using similar nodes if available.<br>
<br>
The closest that I could find in the manual was using
consumable <br>
resources, but I think this is not what I need, there are
several <br>
examples, but they don't seem to fit with this.<br>
<br>
Thank you for your help!<br>
<br>
<o:p></o:p></p>
</blockquote>
</div>
</div>
</blockquote>
<br>
</body>
</html>