You recently deployed a model to a Vertex AI endpoint and set up online serving in Vertex AI Feature Store. You have configured a daily batch ingestion job to update your featurestore. During the batch ingestion jobs, you discover that CPU utilization is high in your featurestore’s online serving nodes and that feature retrieval latency is high. You need to improve online serving performance during the daily batch ingestion. What should you do?
To address the high CPU utilization and high feature retrieval latency during batch ingestion jobs, the best solution is to schedule an increase in the number of online serving nodes in your featurestore before the batch ingestion jobs. This approach ensures that the necessary resources are available to handle the increased load, thus improving online serving performance. Enabling autoscaling might not react quickly enough to sudden spikes in traffic during batch ingestion, and increasing the worker_count in the batch ingestion job could further strain the online serving nodes.
Vertex AI Feature Store provides two options for online serving: Bigtable and optimized online serving. Both options support autoscaling, which means that the number of online serving nodes can automatically adjust to the traffic demand. By enabling autoscaling, you can improve the online serving performance and reduce the feature retrieval latency during the daily batch ingestion. Autoscaling also helps you optimize the cost and resource utilization of your featurestore.
https://cloud.google.com/vertex-ai/docs/featurestore/managing-featurestores?&_gl=1*sswg5e*_ga*NDE2OTc3OTAzLjE3MDU4OTQ5OTE.*_ga_WH2QY8WWF5*MTcwNTkzNDM0NS40LjAuMTcwNTkzNDM0NS4wLjAuMA..&_ga=2.242492743.-416977903.1705894991#online_serving_nodes
Option A: Manually scheduling node increases requires prior knowledge of batch ingestion times and might not be as responsive to unexpected workload spikes. Option C: Autoscaling prediction nodes in the Vertex AI endpoint might help with model prediction latency but doesn't directly address feature retrieval latency from the featurestore. Option D: Increasing worker_count in the batch ingestion job could speed up ingestion but might further strain online serving nodes, potentially worsening latency.
Hey Pikachu, did you pass the exam or are you preparing? I am as well preparing and I have noticed that in many question you chose the same answer I would chose, but which is not the indicated answer of my Udemy Course Exam Preparation. Thanks and Best
Yes passed
Hi @pikachu007 May I ask when did you pass the exam? was it after they updated the new questions? I need to take the exam ASAP, just want to make sure the new questions are valid?
This question is valid for the Legacy feature store. https://cloud.google.com/vertex-ai/docs/featurestore/ingesting-batch#import_job_performance
"CPU utilization is high in your featurestore’s online serving nodes"
Gemini + Perplexity ai + ChatGPT votes A Because : B. Enable Autoscaling: While autoscaling can be useful, it might not react quickly enough to sudden spikes in traffic during batch ingestion. Scheduling the increase ensures that the resources are available when needed.
https://cloud.google.com/vertex-ai/docs/featurestore/managing-featurestores Specifically mentioned here that --> If CPU utilization is consistently high, consider increasing the number of online serving nodes for your featurestore.