The article Instrumentation and Observability describes the critical role that instrumentation plays in the DevOps process, "To progress, one must ask questions. These questions must be answered." The article goes on to state, "To observe a situation without changing it is the ultimate achievement." Finally, the case is made for pervasively embedding instrumentation within the production environment, "applications should expose this information as a consequence of normal behavior."
The sFlow standard embeds lightweight instrumentation within switches, servers and applications throughout the data center. sFlow is highly scalable, combining an efficient "push" mechanism with statistical sampling in order to provide continuous, real-time, data center wide visibility.
The article, Host-based sFlow: the drop-in, cloud-friendly monitoring standard, describes some of the operational benefits of sFlow. The granular visibility into scale-out web applications provided by sFlow facilitates DevOps by allowing software developers to see how services perform at scale and identify bottlenecks that can be eliminated through continuous refinement of application logic. At the same time, visibility into application transactions, response times and throughput allows operations teams to flexibly allocate network and server resources as demand changes, controlling costs and ensuring optimal performance.