April 03, 2013 - by rachelbalik
In today’s video, Bryan Cantrill and Brendan Gregg discuss the challenges of applications that exhibit data-intensive real-time semantics -- aka DIRTy apps. These apps present a unique new challenge: the explosiveness of demand of the social web with the constraints of a real-time system— all via brittle, failure-prone mobile networks. Deploying asynchronous, event-oriented systems like Node.js can pose further challenges.
As the server-side infrastructure provider for one such “DIRTy” app, Joyent has experienced this problem first hand. In this talk at Surge 2012, Bryan and Brendan describe how they debugged latency-inducing issues at all layers of the stack: from the bowels of the operating system (I/O, networking, CPU scheduling) through platform (node.js, Erlang/Riak) and into the application. The talk also details some of the Joyent’s debugging and visualization technology that helped the team to understand and diagnose these systems.