Suppose you have produced a simple prediction model that has been containerised and deployed on infrastructure like
Fantastic news! We've Found the answer you've been seeking!
Question:
Suppose you have produced a simple prediction model that has been containerised and deployed on infrastructure like Kubernetes (K8S), configured to autoscale your service. As part of your model lifecycle, you wish to capture all predictions made when users interact with the service. You are currently storing these data to a sharded NoSQL technology (say MongoDB for the sake of this question), and are using range partitioning on the timestamp to distribute your data.
1. What problems/issues is sharding solving?
2. What happens if your service gains in popularity? Is this shading solution still viable?
Related Book For
Management Accounting Information for Decision-Making and Strategy Execution
ISBN: 978-0137024971
6th Edition
Authors: Anthony A. Atkinson, Robert S. Kaplan, Ella Mae Matsumura, S. Mark Young
Posted Date: