Extra memory on EC2 [closed]

Question

So, i'm looking at amazons high-cpu on demand instances, they have an 8 virtual core extra large high-cpu instance, but it only has 8GB of RAM.

http://aws.amazon.com/ec2/instance-types/

I'm trying to offload a load of circuit simulations that I've written, however they're all only single threaded, so I can run 8 different simulations at once, on 8 cores, but they each consume 2GB of ram each for the duration.

So is there anyway to purchase more memory for that instance? or would it be better to use the 'Cluster Compute Quadruple Extra Large Instance', which although expensive already has the necessary amount of ram.

Thanks

Answer 1

Do you know that each process uses 2gb of dedicated memory? I'd imagine that a lot of memory can be shared between these processes, since they're likely using the same shared libraries, etc.

If you have control over the application, and can refactor it slightly to fork 8 instances, rather than starting 8 instances individually, you can probably share even more memory, since Linux will only duplicate dirty pages in a forked child, meaning that even more memory can be shared in many cases.

Although maybe you've already considered all of this, and know that you truly need 2gb of dedicated memory per process.

Answer 2

I've looked for ways to expand memory capacity on EC2 and have yet to see a means of doing it, other than changing instance types. So, I think your only option without getting some custom help from AWS, is to use the next instance type up the list.

Alternatively, you may want to look at other VPS services. Linode, for example will let you purchase extra specific resources a la carte. Though you should talk to them first to see what their limits are, as your needs sound fairly industrial strength.