AWS Certified Solutions Architect – ProfessionalDesign for New SolutionsHard

A research institution is building a new data platform to ingest genomic sequencing data, which consists of extremely large files (terabytes per file) and requires high-throughput, low-latency access for parallel processing by high-performance computing (HPC) clusters. The data will be accessed by hundreds of compute nodes concurrently. The solution must provide POSIX-compliant file system access. Which AWS storage solution is most suitable for this use case?

  1. AAmazon FSx for Lustre.
  2. BAmazon S3 Standard.
  3. CAmazon EFS Standard.
  4. DAmazon EBS Provisioned IOPS SSD (io2 Block Express).
Show answer & explanation

Correct answer: A. Amazon FSx for Lustre.

Amazon FSx for Lustre is a high-performance file system designed specifically for HPC workloads, machine learning, and media processing. It provides high-throughput, low-latency, and parallel access to data, supporting POSIX compliance, making it ideal for large genomic datasets and concurrent access from HPC clusters.

Why the other options are wrong

  • B. Amazon S3 is object storage, not a POSIX-compliant file system, and its access patterns are not optimized for the extremely high-throughput, low-latency, parallel access required by HPC.
  • C. Amazon EFS is a shared file system but generally offers lower throughput and higher latency than FSx for Lustre, making it less suitable for the extreme demands of genomic HPC workloads.
  • D. EBS io2 Block Express provides high performance for single EC2 instances but is not a shared, distributed, POSIX-compliant file system designed for hundreds of concurrent HPC nodes.

Amazon FSx for Lustre

Amazon FSx for Lustre is a fully managed file system that is optimized for compute-intensive workloads, such as high-performance computing (HPC), machine learning, and media processing.

  • Provides high-throughput and low-latency access to data.
  • Supports POSIX-compliant file system access.
  • Integrates with Amazon S3 for data lifecycle management and cost-effective storage.

Memory trick: Lustre's HPC Speed Powers Genomic Research.

More Design for New Solutions questions