AWS SA Pro question is incorrectly flagged as right option

[hunny]

For this Specific question :
A company is running a financial modeling application on the AWS cloud. The application tier runs on an Auto Scaling group of Amazon EC2 instances. A separate EC2 cluster with a fixed number of instances is hosting the 200 TB of financial data in a shared file system. The application reads and processes the data on the shared filesystem to generate an overall financial report, which takes about 72 hours to complete. This whole process only needs to run at the end of each month, but the storage tier instances are running continuously to retain all the data in the shared file system.

As the storage tier takes up a large percentage of operational costs, the management wants to reduce the cost of the storage tier while maintaining the high-performance access needed by the application during its 72-hour run.

Which of the following options should the solutions architect implement that will have the largest overall cost reduction?

Option A: For the data tier, create an Amazon S3 bucket and move the objects of the existing shared file system to it. Use S3 Glacier Instant Retrieval Storage class to save costs. Use lazy-loading on an Amazon FSx for Lustre filesystem to import the contents of the S3 bucket. Use this filesystem as shared storage for the application tier EC2 instances for the duration of the job and delete it once the job is completed.

Option B: For the data tier, use Mountpoint for Amazon S3 to access the financial data directly from an S3 bucket. This will eliminate the need for a shared file system and reduce costs. Mount the S3 bucket on the application tier EC2 instances and run the job directly from it.

Option C: For the data tier, create an Amazon EFS filesystem and move the objects of the existing shared file system to it. Since the data will only be used once a month, use EFS Standard–Infrequent Access (IA) class to save costs. Mount this filesystem as shared storage for the application tier EC2 instance for the duration of the job.

Option D : For the data tier, create an Amazon S3 bucket and move the objects of the existing shared file system to it. Use S3 Intelligent-Tiering Storage class to save costs. Use lazy-loading on an Amazon FSx for Lustre filesystem to import the contents of the S3 bucket. Use this filesystem as shared storage for the application tier EC2 instances for the duration of the job and delete it once the job is completed.

I Selected Option A which is S3 Glacier Instant Retrieval Storage class however the correct response that I see is Option D but I don’t agree, The explanation says “S3 Glacier is typically recommended for long-lived archive data accessed once a quarter. Also, S3 Glacier has additional charges for retrieving data from cold storage.” however this is not Glacier , it’s GIR which is different. Also Intelligent tiering would not be a cost effective method as it comes with Monitoring cost which will add additional cost. So if a data is accessed once every month, i.e 3 times a quarter, Glacier instant retrieval would be a better choice, why would I choose intelligent tiering when it has extra cost and access patterns are already known?

[JR-TutorialsDojo]

Hello hunny,

Thank you for sharing your thoughts on this item.

The key issue in this scenario is the retrieval cost model. Since the workload scans through 200 TB every month, S3 Glacier Instant Retrieval’s per‑GB retrieval charges would add up significantly. Intelligent‑Tiering avoids those retrieval costs and integrates seamlessly with FSx for Lustre, which is designed for high‑performance workloads like financial modeling.

That’s why the exam answer favors Intelligent‑Tiering + FSx for Lustre. It balances cost savings with HPC‑level performance, whereas GIR is better suited for archival data that is accessed occasionally, not for full dataset scans.

I hope this helps! Let me know if you need further assistance.

Best regards,
JR @ Tutorials Dojo