Issue link: https://read.uberflip.com/i/1187300
Amazon Web Services – HPC Lens AWS Well-Architected Framework Page 36 You can gain further performance enhancements by selecting an Amazon EBS- optimized instance. An EBS-optimized instance uses an optimized configuration stack and provides additional, dedicated capacity for Amazon EBS I/O. This optimization provides the best performance for your EBS volumes by minimizing contention between Amazon EBS I/O and other network traffic to and from your instance. Choosing an EBS-optimized instance provides more consistent performance and is recommended for HPC applications that rely on a low-latency network or have intensive I/O data needs to EBS volumes. To launch an EBS-optimized instance, you should choose an instance type that enables EBS optimization by default or choose an instance type that allows enabling EBS optimization at launch. Please refer to the instance type matrix for EBS optimization support. 10 Lastly, instance-store volumes, including non-volatile memory express (NVMe) SSD volumes (only available on certain instance families), can be used for temporary block-level storage. Shared network storage using instance-store volumes typically implement clustered file systems (e.g., Lustre) across instances to allow for underlying hardware failures and instance lifecycle events (e.g., stop, terminate). The following example question focuses on storage considerations for performance efficiency: HPCPERF 4: How do you select your storage solution? When you select a storage solution, ensure that it aligns with your access patterns to achieve the desired performance. It is easy to experiment with different storage types and configurations. With HPC workloads, the most expensive option is not always the best performing solution. Networking The optimal network solution for an HPC workload will vary based on latency, bandwidth, and throughput requirements. Tightly coupled HPC applications often require the lowest latency possible for network connections between compute nodes. For moderately sized, tightly coupled workloads, it is often possible to select a large instance type with a large number of cores such that the application fits entirely within the instance without crossing the network at