Many organisations waste huge sums of money by selecting a cloud storage solution that does not match their requirements. In response, Ellexus has published a new whitepaper that examines how to select the right storage solutions.
See below for an excerpt and download the full whitepaper here.
Planning cloud storage for HPC and high throughput applications
When adopting flexible compute, half the challenge is in selecting a storage solution that suits the application. Whether you are tuning for performance, throughput or cost, or a combination of all three, it’s important to balance the compute nodes with the right access to data so that you are not paying for underutilised resources. Whether you get the storage architecture right or wrong can make or break the success of the cloud deployment; over provisioning can escalate costs far beyond the expense of an in-house solution, but with reasonable planning there are big cost savings to be found.
Replicating in-house infrastructure can get you started, but it shouldn’t be a long-term plan, as high-performance shared file systems are a very expensive way to use cloud storage. Sizing cloud storage is not just about knowing how much you need, but also about bandwidth, latency, peak performance and fault tolerance. Putting all this together means designing a storage solution that suits the application and the key starting point lies in understanding the storage requirements.
This whitepaper will present tried and tested means to help you take advantage of the elastic compute offered by the cloud. Establishing good in-house working practices from the beginning will help you to get much more from your in-house infrastructure and make it easier to move workflows to the cloud.