A Distributed and Fault-Tolerant Application with Apache Mesos & Apache Aurora

on YouTube ↗57m

" summary

Describes using Apache Mesos together with Apache Aurora (not Marathon/Kronos) plus Zookeeper, HDFS and cgroups to consolidate datacenter resources so developers deploy directly into the cluster. Explains architecture with multiple Mesos masters and a Zookeeper quorum for fault tolerance, demonstrates automatic rolling/canary deployments that keep production reachable (deploys ~10 minutes in a small ~10‑slave setup) and reports reduced VM overhead and large-scale Mesos use (Twitter cited at ~40,000 nodes).

AI-written summary · about

" chapters (12)

1. 0:00Mesos & Aurora intro
2. 5:03Monolith to distributed
3. 7:09Mesos architecture
4. 11:30Aurora for services
5. 19:41Team benefits
6. 25:11Continuous deployment
7. 31:16Implementation
8. 36:40Aurora vs Marathon
9. 41:47Zookeeper config & failures
10. 47:37Monitoring clusters
11. 51:50Cluster sizing
12. 56:13Q&A

" related talks

• 59mBuilding Distributed Systems with Apache MesosBen Hindman · Philly ETE 2015
• 42mA Year with Apache AuroraRick Mangi · MesosCon Europe 2017
• 01h 00mDeveloping Distributed Systems with Apache MesosYaniv Rodenski · NDC Sydney 2016
• 45mMesos, Then and NowBen Hindman, Ian Downes · Scale By the Bay 2017
• 42mMesos: The Operating System for your ClusterDavid Greenberg · Strange Loop 2014
• 29mGetting Started with Apache MesosRoger Ignazio · MesosCon Asia 2016
• 53mDocker as the Building Block for Datacenter-Scale ApplicationsBen Hindman · GOTO Amsterdam 2015
• 33mAn Introduction to the Mesos Framework ZooBenjamin Bannier · MesosCon Asia 2016