Issue link: https://read.uberflip.com/i/1187300
Amazon Web Services – HPC Lens AWS Well-Architected Framework Page 23 downtime, and they should not require manual execution. A wide range of logs and metrics that are based on key operational indicators for a workload should be collected and reviewed to ensure continuous operations. When choosing AWS, you have the opportunity to use additional tools for handling HPC operations. These tools can vary from monitoring assistance to automating deployments. For example, you can have Auto Scaling restart failed instances, use CloudWatch to monitor your cluster's load metrics, configure notifications for when jobs finish, or use a managed service, such as AWS Batch, to implement retry rules for failed jobs. Cloud-native tools can greatly improve your application deployment and change management. Release management processes, whether manual or automated, should be based on small incremental changes and tracked versions. You should be able to revert releases that introduce operational issues without causing operational impact. Tracked changes can vary from version control of source code, such as AWS CodeCommit, or infrastructure configuration, such as AWS CloudFormation templates. HPCOPS 1: How are you evolving your workload while minimizing the impact of change? HPCOPS 2: How do monitor your workload to ensure it's operating as expected? Using the cloud for HPC introduces new operational considerations. While on- premises clusters are fixed in size, cloud clusters can scale to meet demands. At the same time, cloud-native architectures for HPC operate differently, for example, using different mechanisms for job submission and provisioning resources on-demand as jobs arrive. Consider adopting operational procedures that benefit from and accommodate the elasticity of the cloud and the dynamic nature of cloud-native architectures. Evolve There are no operational practices unique to HPC for the evolve practice area, so review the corresponding section in the AWS Well-Architected Framework whitepaper.