Smart Workload: Automated Routing, Scaling of K8s and Serverless Functions
summary
Built a testbed that runs the same function on Knative edge vs AWS Lambda, uses Kong for static mapping and Istio virtual service label routing, and plugs Turbonomic as a decision engine that watches Kubernetes node VM congestion. When the edge cluster shows high host memory and slower responses, the engine flips labels so Istio/Kong route traffic to Lambda; the demo shifts traffic instantly and shows noticeably lower response times after the reroute, proving automated placement/routing works end to end.
AI-written summary · about
chapters (18)
- 0:00Introduction
- 0:47About Turbonomic
- 2:32Agenda
- 3:29Challenges
- 5:03Service Use Cases
- 5:23Service Application
- 6:09Data Operations
- 7:57Smart Workloads
- 9:55Demo
- 13:49Service Platform
- 14:42Service Match
- 15:51Decision Making
- 16:20How Turbonomic works
- 18:05Economic Theory
- 21:53Cognitive Layer
- 22:55API Gateway Layer
- 26:24Turbonomic Overview
- 31:41Summary
related talks
39mDelivering Serverless Experience on Kubernetes: Beyond Web Applications
31mBeyond Traditional DevOps: Dive into Serverless with K8s
34mModern Serverless Workloads with KNative and Kubernetes
21mServerless computing using Knative Open Source
30mUnleashing the Power of Serverless on K8s with Knative, Crossplane, Dapr, KEDA
57mServerless with Knative
20mKnative: A Kubernetes Framework to manage Serverless Workloads
29mAccelerate AppDev with KIK (Kubernetes-Istio-Knative)