<div dir="ltr">Hi fellows,<div><br></div><div>I´ve talked to Jeff Barr and he told me that EC2 group said to him:</div><div>"<span lang="EN-US" style="font-family:Wingdings">Ø<span style="font-size:7pt;font-family:'Times New Roman'"> </span></span><span lang="EN-US" style="font-size:11pt;font-family:Calibri,sans-serif;color:rgb(31,73,125)">C3.8xl instance is indeed on 10GB
network like CC2. We don’t have it correctly described on our website and
console."</span></div><div><span lang="EN-US" style="font-size:11pt;font-family:Calibri,sans-serif;color:rgb(31,73,125)"><br></span></div><div style="text-indent:0px"><span lang="EN-US" style>So someone has to change the code to put c3.8xlarge in the placement group.</span></div>
<div style="text-indent:0px"><span lang="EN-US" style><br></span></div><div style="text-indent:0px"><span lang="EN-US" style>All best,</span></div><div style="text-indent:0px"><span lang="EN-US" style><br>Sergio Mafra</span></div>
<div style="text-indent:0px"><span lang="EN-US" style><br></span></div><p class="" style><span lang="EN-US"></span></p>
</div><div class="gmail_extra"><br><br><div class="gmail_quote">On Wed, Nov 27, 2013 at 4:47 PM, Sergio Mafra <span dir="ltr"><<a href="mailto:sergiohmafra@gmail.com" target="_blank">sergiohmafra@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">I´m a little confused about the c3.8xlarge instance.<div>Despite all documentation that tell us that this runs on a 1 Gb network, AWS told me today that it really runs on a 10 Gb network...</div>
<div>Does anybody has more info on that?</div>
<div><br></div></div><div class="HOEnZb"><div class="h5"><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Nov 25, 2013 at 3:42 PM, Rayson Ho <span dir="ltr"><<a href="mailto:raysonlogin@gmail.com" target="_blank">raysonlogin@gmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Thanks Sergio, I check the docs the day when c3 was announced, there's<br>
no mention of placement group support for c3. I think I was reading<br>
the older version of the doc.<br>
<br>
Yuichi, we can't take advantage of SR-IOV (yet) as we don't run in a VPC.<br>
<div><br>
Rayson<br>
<br>
==================================================<br>
Open Grid Scheduler - The Official Open Source Grid Engine<br>
<a href="http://gridscheduler.sourceforge.net/" target="_blank">http://gridscheduler.sourceforge.net/</a><br>
<a href="http://gridscheduler.sourceforge.net/GridEngine/GridEngineCloud.html" target="_blank">http://gridscheduler.sourceforge.net/GridEngine/GridEngineCloud.html</a><br>
<br>
<br>
</div><div><div>On Mon, Nov 25, 2013 at 9:39 AM, Yoshiara, Yuichi <<a href="mailto:yoshiara@amazon.co.jp" target="_blank">yoshiara@amazon.co.jp</a>> wrote:<br>
><br>
> Hi Sergio,<br>
><br>
><br>
><br>
> There is a new feature called Enhanced Networking which is available in C3 instances.<br>
><br>
> Please read through the link below and see if it helps you.<br>
><br>
><br>
><br>
> <a href="http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/enhanced-networking.html" target="_blank">http://docs.aws.amazon.com/AWSEC2/latest/UserGuide/enhanced-networking.html</a><br>
><br>
><br>
><br>
> <a href="http://aws.amazon.com/ec2/faqs/#What_networking_capabilities_are_included_in_this_feature" target="_blank">http://aws.amazon.com/ec2/faqs/#What_networking_capabilities_are_included_in_this_feature</a><br>
><br>
><br>
><br>
> Yuichi Yoshiara<br>
><br>
><br>
><br>
><br>
><br>
> From: <a href="mailto:starcluster-bounces@mit.edu" target="_blank">starcluster-bounces@mit.edu</a> [mailto:<a href="mailto:starcluster-bounces@mit.edu" target="_blank">starcluster-bounces@mit.edu</a>] On Behalf Of Sergio Mafra<br>
> Sent: Monday, November 25, 2013 8:16 PM<br>
> To: Rayson Ho; <a href="mailto:starcluster@mit.edu" target="_blank">starcluster@mit.edu</a><br>
> Subject: Re: [StarCluster] MIT StarCluster and the new C3 instances<br>
><br>
><br>
><br>
> Hi Rayson,<br>
><br>
><br>
><br>
> I noticed that StarCluster didn´t allocate a placement group for C3 instances and did it by myself in the code.<br>
><br>
> But this was not helpfull since C3 instances uses high throughput insted of the 10 giga network.<br>
><br>
> In my tests, using C3 or CC2 in a cluster config where MPI is required will be equal to same processing time.<br>
><br>
> Hope that AWS put them on 10 Giga net in the near future.<br>
><br>
><br>
><br>
><br>
><br>
> Compute optimized<br>
><br>
> c3.8xlarge<br>
><br>
> 64-bit<br>
><br>
> Intel Xeon E5-2680<br>
><br>
> 32<br>
><br>
> 108<br>
><br>
> 60.00<br>
><br>
> 640 GB (2 x 320 SSD)<br>
><br>
> -<br>
><br>
> 240<br>
><br>
> High<br>
><br>
> Compute optimized<br>
><br>
> cc2.8xlarge<br>
><br>
> 64-bit<br>
><br>
> Intel Xeon E5-2670<br>
><br>
> 32<br>
><br>
> 88<br>
><br>
> 60.50<br>
><br>
> 3370 GB (4 x 840)<br>
><br>
> -<br>
><br>
> 240<br>
><br>
> 10 Gigabit<br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
><br>
> On Mon, Nov 18, 2013 at 7:13 PM, Sergio Mafra <<a href="mailto:sergiohmafra@gmail.com" target="_blank">sergiohmafra@gmail.com</a>> wrote:<br>
><br>
> Hi Rayson,<br>
><br>
><br>
><br>
> I´ll try to do that.<br>
><br>
><br>
><br>
> All best,<br>
><br>
><br>
><br>
> Sergio<br>
><br>
><br>
><br>
> On Mon, Nov 18, 2013 at 1:27 PM, Rayson Ho <<a href="mailto:raysonlogin@gmail.com" target="_blank">raysonlogin@gmail.com</a>> wrote:<br>
><br>
> It's in the development branch:<br>
><br>
> <a href="https://github.com/jtriley/StarCluster/pull/325" target="_blank">https://github.com/jtriley/StarCluster/pull/325</a><br>
><br>
> It's a few lines of code, and you can merge the changes into your<br>
> local version very easily.<br>
><br>
> Rayson<br>
><br>
> ==================================================<br>
> Open Grid Scheduler - The Official Open Source Grid Engine<br>
> <a href="http://gridscheduler.sourceforge.net/" target="_blank">http://gridscheduler.sourceforge.net/</a><br>
> <a href="http://gridscheduler.sourceforge.net/GridEngine/GridEngineCloud.html" target="_blank">http://gridscheduler.sourceforge.net/GridEngine/GridEngineCloud.html</a><br>
><br>
><br>
><br>
> On Mon, Nov 18, 2013 at 8:29 AM, Sergio Mafra <<a href="mailto:sergiohmafra@gmail.com" target="_blank">sergiohmafra@gmail.com</a>> wrote:<br>
> > Hi everyone,<br>
> ><br>
> > I attended AWS Re:Invent this year and liked a lot. Right place to go.<br>
> > AWS announced there the new C3 family of HPC instances.<br>
> > I´m anxious to test them in my models but I understand that StarCluster must<br>
> > take aware of them in the code.<br>
> > So when will be the C3s available?<br>
> ><br>
> > All the best,<br>
> ><br>
> > Sergio Mafra<br>
> ><br>
><br>
> > _______________________________________________<br>
> > StarCluster mailing list<br>
> > <a href="mailto:StarCluster@mit.edu" target="_blank">StarCluster@mit.edu</a><br>
> > <a href="http://mailman.mit.edu/mailman/listinfo/starcluster" target="_blank">http://mailman.mit.edu/mailman/listinfo/starcluster</a><br>
> ><br>
><br>
><br>
><br>
><br>
</div></div></blockquote></div><br></div>
</div></div></blockquote></div><br></div>