Topic 1 Question 138
A company has set up and deployed its machine learning (ML) model into production with an endpoint using Amazon SageMaker hosting services. The ML team has configured automatic scaling for its SageMaker instances to support workload changes. During testing, the team notices that additional instances are being launched before the new instances are ready. This behavior needs to change as soon as possible. How can the ML team solve this issue?
Decrease the cooldown period for the scale-in activity. Increase the configured maximum capacity of instances.
Replace the current endpoint with a multi-model endpoint using SageMaker.
Set up Amazon API Gateway and AWS Lambda to trigger the SageMaker inference endpoint.
Increase the cooldown period for the scale-out activity.
解説
ユーザの投票
コメント(5)
- 正解だと思う選択肢: D
I believe this is a problem to do with scaling out (increasing the number of instances), cooldown period should be increased.
https://docs.aws.amazon.com/autoscaling/ec2/userguide/Cooldown.html
👍 11cron00012022/04/23 - 正解だと思う選択肢: D
Definitely D.
👍 2SDikeman622022/05/11 - 正解だと思う選択肢: D
The issue is related to scaling out, specifically the fact that new instances are being launched before the existing ones are ready.
To address this issue, the ML team could consider increasing the minimum number of instances, reducing the target value for CPU utilization, or increasing the warm-up time for the instances. These actions can help to ensure that new instances are not launched until the existing ones have reached a stable state, which can prevent performance issues and ensure the reliability of the service.
👍 2AjoseO2023/02/15
シャッフルモード