Measuring Distributed Databases Across the Globe
Distributed systems are an important part of what makes the OpenX digital advertising and monetization platforms run. In addition to data storage and computation on our large Hadoop clusters, Riak supports several different use cases across hundreds of nodes: local key/value reporting utilities, world-wide distribution of configurations, regional datastores used for delivery, and multi-datacenter cloud-storage.
This talk will present some of the problems the OpenX team has faced operating such large and diverse clusters, and how we approached solving them using configuration management, monitoring and statistics toolsets, and close collaboration with development teams.
Topics covered will include the ways we gather and present data about our clusters, how the front-end applications interact with them, and the lessons we've learned from the issues we've faced.