Issue link: https://read.uberflip.com/i/1187300
Amazon Web Services – HPC Lens AWS Well-Architected Framework Page 28 Design Principles In the cloud, a number of principles can help you increase reliability. In particular, the following are emphasized for HPC workloads. See also the design principles in the AWS Well-Architected Framework whitepaper. • Scale horizontally to increase aggregate system availability: It is important to consider horizontal scaling options that might reduce the impact of a single failure on the overall system. For example, rather than having one large, shared HPC cluster running multiple jobs from multiple cases, consider creating multiple clusters across the Amazon infrastructure to further isolate your risk of potential failures. Since infrastructure can be treated as code, not only can you horizontally scale resources inside a single cluster, but you can also horizontally scale the number of clusters running individual cases. • Stop guessing capacity: A set of HPC clusters can be provisioned to meet current needs and scaled either manually or automatically to meet increases or decreases in demand. Compute nodes need not be idle when not in use and computations need not have long wait times because of limited resources. • Manage change in automation: Changes to your infrastructure should be done using automation. This allows you to place a cluster infrastructure under version control and make exact duplicates of a previously created cluster. The changes that need to be managed are changes to the automation. Definition There are three best practice areas for reliability in the cloud: • Foundations • Change management • Failure management The change management category will not be described in this paper as the best practices in the AWS Well-Architected Framework whitepaper do not require modification for HPC workloads. Please refer to the AWS Well- Architected Framework paper for an understanding of best practices.