Monitoring OVH 300k Servers, 27 DCs: A Metrics Platform
summary
How to monitor the entire infrastructure of OVH (27 data centers, 300k+ physical servers) by building OVH Metrics: a metrics/time-series platform that replaces fragmented legacy tools. Describes using and scaling open-source components (time-series systems, HBase clusters pushed to capacity) plus custom code to operate monitoring at cloud-provider scale and support hundreds of products and 1.3M customers.
AI-written summary · about
chapters (6)
- 0:00Introduction
- 10:00Scalability challenges at OVH
- 20:00Metrics platform architecture
- 30:00Machine learning and data analysis
- 40:00Lessons learned and best practices
- 48:00Q&A
related talks
22mImproving the efficiency of more than 800 databases with o11y
27mFast DIY O11y with OpenSrc Analytics & Visualization
46mBig databases, many servers, data center or cloud - it's all here!
20mLessons Learned from Operating ETCD
24mDevOps. Monitoring Databases. On-Premise and Cloud environments
49mThinking in time series, the new solution to your pro...
40mScale Your Monitoring Solution With the VictoriaMetrics Ecosystem
35mBuilding a Real Time Metrics Database