Why and How to Choose Arm64 for your Cloud Applications
summary
Arm64 instances (Ampere) claim 20–30% lower core-hour cost and reports show 30–47% better performance‑per‑price for real workloads; case studies include object caches and Postgres saving ~30% and build/test pipelines dropping from 5–6 hours to under 30 minutes when run natively on Arm64, and one lab booting thousands of VMs on a 192‑core server. Practical how‑tos cover Podman multi-arch build and manifest handling, Kubernetes placement with node affinity and taints/tolerations, and incremental migration using ArgoCD Rollouts.
AI-written summary · about
chapters (17)
- 0:00ARM64 for cloud apps
- 1:05Why ARM64 in cloud
- 2:31ARM64 benefits for providers
- 4:00ARM64 cost savings examples
- 7:50ARM64-friendly workloads
- 9:40Latency-sensitive apps on ARM64
- 12:12Building/testing ARM64 software
- 15:45ARM64 for microservices/databases
- 17:54AI inference on ARM64
- 20:46Multi-arch containers
- 22:52Multi-arch manifests explained
- 24:39Container build best practices
- 26:47Kubernetes + ARM64 workloads
- 29:15ARM64 node selectors vs affinities
- 31:45Migrating to ARM64
- 33:51Canary deployments with Argo Rollouts
- 35:15ARM64 adoption resources
related talks
06mChange Your Architecture and Save the World
44mWhat to know before adopting Arm: Lessons learned at Datadog
15mMake a Once-in-a-Generation Leap – Migrate to Azure Ampere-based VMs
27mWhat's Going ARM: Adopting ARM64 At Airbnb
01h 14mModernizing and Optimizing Applications for the Cloud
35mThe Future of Green Cloud: Serverless WebAssembly on Arm64 Architecture
16mChange Your Chip Architecture and Save the World
41mRunning Java on ARM - is it worth it?