MLA-C01 · Question #220
An airline company uses an ML model to adjust ticket prices based on demand. The model runs on Amazon SageMaker real-time endpoints. During previous deployments, the model failed to scale quickly enou
The correct answer is D. Configure auto scaling based on the SageMaker InvocationsPerInstance metric. Configure high-. Using the SageMaker InvocationsPerInstance metric with high-resolution 10-second intervals allows auto scaling to detect traffic spikes quickly. Keeping the default 300-second scale-in cooldown avoids overly aggressive scale-in while still allowing fast scale-out, making this con
Question
An airline company uses an ML model to adjust ticket prices based on demand. The model runs on Amazon SageMaker real-time endpoints. During previous deployments, the model failed to scale quickly enough when website traffic increased, which caused delays in price adjustments. An ML engineer needs to configure auto scaling for the SageMaker endpoints to respond rapidly to traffic changes. The solution must use target tracking scaling policies. Which configuration will be MOST responsive to sudden changes in traffic?
Options
- AConfigure auto scaling based on the SageMaker AI InvocationsPerInstance standard metric.
- BConfigure auto scaling based on the SageMaker AI InvocationsPerInstance metric. Configure
- CConfigure auto scaling based on the SageMaker InvocationsPerInstance standard metric.
- DConfigure auto scaling based on the SageMaker InvocationsPerInstance metric. Configure high-
How the community answered
(34 responses)- A9% (3)
- B15% (5)
- C6% (2)
- D71% (24)
Explanation
Using the SageMaker InvocationsPerInstance metric with high-resolution 10-second intervals allows auto scaling to detect traffic spikes quickly. Keeping the default 300-second scale-in cooldown avoids overly aggressive scale-in while still allowing fast scale-out, making this configuration the most responsive to sudden traffic changes under a target tracking policy.
Topics
Community Discussion
No community discussion yet for this question.