Exam AWS Certified Machine Learning - Specialty topic 1 question 323 discussion

Exam question from Amazon's AWS Certified Machine Learning - Specialty

Question #: 323
Topic #: 1

[All AWS Certified Machine Learning - Specialty Questions]

A growing company has a business-critical key performance indicator (KPI) for the uptime of a machine learning (ML) recommendation system. The company is using Amazon SageMaker hosting services to develop a recommendation model in a single Availability Zone within an AWS Region.

A machine learning (ML) specialist must develop a solution to achieve high availability. The solution must have a recovery time objective (RTO) of 5 minutes.

Which solution will meet these requirements with the LEAST effort?

A. Deploy multiple instances for each endpoint in a VPC that spans at least two Regions.
B. Use the SageMaker auto scaling feature for the hosted recommendation models.
C. Deploy multiple instances for each production endpoint in a VPC that spans least two subnets that are in a second Availability Zone.
D. Frequently generate backups of the production recommendation model. Deploy the backups in a second Region.

Show Suggested Answer

Suggested Answer: C 🗳️

by AIWave at March 14, 2024, 6:39 p.m.

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
- Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Submit Cancel

MultiCloudIronMan

8 months, 1 week ago

Selected Answer: C

Options A and D involve more complex configurations and higher operational overhead. Option B, while useful for scaling, does not directly address the need for high availability across multiple Availability Zones

upvoted 1 times

...

vkbajoria

1 year, 3 months ago

Selected Answer: C

two different AZ will provide highly available deployment

upvoted 2 times

...

butaman

1 year, 3 months ago

Selected Answer: C

This solution meets the requirements because it provides high availability by deploying multiple instances across different subnets in a second Availability Zone. This approach ensures that if one Availability Zone goes down, the other can continue to serve requests, achieving the desired recovery time objective (RTO) of 5 minutes. This solution requires the least effort compared to the others because it doesn’t involve managing resources across multiple regions or frequent backups, and it’s more directly targeted at high availability compared to auto-scaling. Please note that while auto-scaling (option B) can help handle increased load, it doesn’t directly address high availability in terms of uptime or recovery time objectives. Options A and D involve multiple regions, which can add complexity and may not be necessary for achieving the desired high availability and RTO.

upvoted 3 times

...

AIWave

1 year, 3 months ago

Selected Answer: C

A: No - Multi region setup unnecessary B: No - Auto scaling is for capacity not for failovers C: Yes - Multiple instances running in separate subnets in two different AZ's provide quick failover D: No - Backups are for DR, not production failover

upvoted 1 times

...