Which combination of solutions will meet these requirements?
(Choose two.)
Create an accelerator in AWS Global Accelerator. Configure custom routing for the accelerator.
Create an Amazon FSx for Lustre file system. Configure the file system with scratch storage.
Create an Amazon CloudFront distribution. Configure the viewer protocol policy to be HTTP and HTTPS.
Launch Amazon EC2 instances. Attach an Elastic Fabric Adapter (EFA) to the instances.
Create an AWS Elastic Beanstalk deployment to manage the environment.
Explanations:
AWS Global Accelerator is designed to improve the availability and performance of applications by directing traffic to optimal endpoints, but it does not specifically optimize HPC environments for high-performance networking and storage requirements.
Amazon FSx for Lustre is a high-performance file system that can be used for workloads such as HPC. Configuring it with scratch storage is ideal for transient data storage during HPC jobs, which optimizes performance.
Amazon CloudFront is a content delivery network (CDN) primarily used for distributing static and dynamic web content globally. It does not optimize networking or storage specifically for HPC applications.
Elastic Fabric Adapter (EFA) is a network interface that allows Amazon EC2 instances to use the underlying network fabric for high-performance inter-instance communication. It is specifically designed for HPC workloads and enhances networking capabilities significantly.
AWS Elastic Beanstalk is a platform-as-a-service (PaaS) that simplifies application deployment but is not tailored for high-performance computing or optimizing networking and storage for HPC environments.
In my experience, the answer is:
Create an Amazon FSx for Lustre file system. Configure the file system with scratch storage.