Unsolved

This post is more than 5 years old

112 Posts

869

June 2nd, 2008 13:00

Virtualization and HPCC

I agree with you that there is not alot of overlap where Server Virtualization and HPCC are part of the same solution.

I just have one tweak to your first scenario where they might - just might - be able to coexist. If you had a scenario where you had completely different software requirements to run two different HPCC applications - but only one cluster. You could have a VM on each phyiscal server that was dedicated to one of the HPCC applicaitons. To then switch between the two, it would only be necessary to suspend one VM and restore the other VM on all of the physical servers. This would enable very easy sharing of a single cluster.

I think is just an extension of what you had already stated, but I just wanted to throw it in for discussion.

Todd

8 Posts

August 7th, 2008 14:00

That's a very interesting idea. It's kind of a variation on the idea of creating the VM and loading the requested OS when a job runs. I'm not sure which one is faster (always a question that people will ask)?

This shows my limited experience with virtualization, but when you suspend a VM, you would dump it to disk - correct? Then to restart the VM, you just restart it from the disk image? Not a bad idea. One sort-of drawback is that you need a disk in each node :) I'm a fan of diskless nodes since it increases uptime (you would be surprised what impact hard drive failures have on the uptime of systems - I wrote an article about his using data from CMU - it's amazing and it's totally indpendend of the disk type), saves money, saves power (a little). So it would be difficult to save the image to disk unless it's a centralized storage point.

Thanks for the idea! It's very intriguing!

Jeff

2 Intern

 • 

162 Posts

July 10th, 2022 21:00

In computing, virtualization or virtualisation is the act of creating a virtual (rather than actual) version of something at the same abstraction level, including virtual computer hardware platforms, storage devices, and computer network resources.

Virtualize high performance computing (HPC) workloads, adding flexibility, operational efficiency, agility, and security to enable faster time to insights and discovery. High Performance Computing (HPC) workloads are forecasted to be one of the fastest-growing workload types through 2020.

 

This may help you,

Rachel Gomez

0 events found

No Events found!

Top