Downtime is not an option
summary
Claims that DC/OS runs containers and Big Data together on Apache Mesos and actually does it at scale with customers like Twitter on 27k-node clusters. Shows Marathon and the Universe for one‑click Cassandra and Prometheus installs, demos a Rails app deployed via Marathon REST API, and explains local persistent volumes for stateful services plus rolling upgrades that replace agents without stopping containers. Provides CLI debug tools, schedulers per workload, and verified failover behavior.
AI-written summary · about
chapters (12)
- 0:00Downtime-free systems intro
- 1:04Local dev to containerized prod
- 3:13Twitter’s spreadsheet scheduling
- 7:30Data center challenges today
- 9:42Apache Mesos resource sharing
- 15:23Data handling in containers
- 17:55DC/OS unified platform
- 19:20Monitoring DC/OS clusters
- 21:08Deploy Twitter clone on DC/OS
- 24:03Post-deployment ops and monitoring
- 25:47Debugging distributed systems
- 26:51Conclusion and Q&A
related talks
01h 05mMy Application is Ready for Production... Now What?
31mDeep dive into one of the application of DC/OS : Velocity.
39mHow we learned to love the Data Center Operating System
50mAdvanced Deployment Strategies and Workflows for Containerized Apps on DC/OS
34mContinuous Deployment at Enterprise Scale
31mDoing “DropBox” the Cloud Native Way
40mTo Build My Own Cloud with Blackjack…
49mDoing Real DevOps with DC/OS