Spring Apps at Scale from 0 to 5B to 100B+ Requests
summary
A Spring Boot catalog service scales from a single instance to 1.38M requests/sec (≈113B/day) by using Azure Spring Apps, Azure Load Testing, Postgres scaled to 64 cores with 5,000 connections, HikariCP pool tuning, 495 app instances, and a local Caffeine cache to cut DB hits; autoscaling and request-sampling for logs/traces prevent observability overload. Load tests initially break the test harness so multiple engines run in parallel; the setup succeeds without rewriting the app using reactive frameworks.
AI-written summary · about
chapters (12)
- 0:00Introductions
- 1:28Architecture overview
- 2:51Application demonstration
- 8:14Codebase exploration
- 10:35Scaling benchmarks
- 12:54Initial load testing
- 20:10Optimizing for scale
- 27:33Advanced performance tuning
- 33:04Achieving massive scale
- 37:28Contextualizing performance
- 41:04Managed services solution
- 43:57Support and conclusion
related talks
56mAccelerate Spring Apps to Cloud at Scale—Discussion with Azure Spring Cloud Customers
36mDrive Higher Utilization of Apps in Azure Spring Cloud with Autoscale
41mSupercharge Your Spring Boot Apps!
01h 05mRapidly Develop, Deploy and Scale Java Cloud Apps Using Spring Boot - Asir Selvasingh
55mThe Easy Way to Run and Scale Spring Apps on Cloud
27mAccelerate Spring Apps to Cloud at Scale—Discussion with Azure Spring Cloud Customers
51mSupercharge your Spring Boot Apps: The Path to Production
51mSpring on Azure