Moving a Large Workload from a Public Cloud to an OpenStack Private Cloud...
summary
Company migrates high-volume, low-latency bidding and caching workloads off public cloud into OpenStack on Ubuntu, automates bare-metal provisioning and cloud build, and runs load balancers and core data on bare metal + HAProxy after virtualized instances hit packet-per-second limits and unexplained network drops. Migration spans ~3 years, touches a 2,500-server estate and ~5 PB/month traffic with near‑trillion ad auctions, yields about 30% cost savings in one region and ~40% server footprint reduction, and includes engineering OPEX in the TCO.
AI-written summary · about
chapters (10)
- 0:00Intro
- 2:26Digital Branding
- 4:27Operational Engineering
- 6:06Building Layer
- 7:27Challenges with Public Cloud
- 9:37Strategy
- 13:24Three Simple Rules
- 14:48Eucalyptus
- 15:17Mistakes
- 18:25Lessons Learned
related talks
29mOpenStack public clouds: 7 reasons to become a local cloud service provider
33mEscaping the Vendor Trap: A Journey for Migrating Legacy Infrastructure To Op...
23mOpen Matters: HP & OpenStack
30mOpenStack Works, so now what?
13mOpenStack in 0 to 45 seconds - Engineering at the speed of light
23mTransitioning from VMware to Apache CloudStack: A Path to Profitability and Competitiveness
27mLessons Learned from a Large Scale OpenStack Deployment with Tripleo
18mChallenges of scaling a upstream Openstack Cloud