Wednesday, February 4, 2015

Real-time distributed tracing for website performance and efficiency optimizations

With LinkedIn’s service-oriented architecture, a single page view request can fan out calls to downstream services spanning multiple backend tiers, many levels deep. Though applications depend on downstream services, developers have no insight on the relationships and performance of these services. This poses a number of major challenges, including performance optimization and root cause analysis.

To have real-time clarity into service performance across tiers, LinkedIn built ubiquitous distributed tracing. For more information see the blog post on Apache Samza. This post describes how inCapacity, an internal LinkedIn tool, consumes results from Samza to build real-time call graphs that profile requests in a distributed architecture; the profile includes the request, associated webservers, and downstream tiers in the data center.

These distributed call graphs have helped unlock a whole new range of very useful tools; we now have tools for performance correlation and root cause analysis of service-oriented applications, efficiency analysis for cost, and resource headroom for capacity planning in the context of the web pages.

Read more here

Leave a Reply

All Tech News IN © 2011 & Main Blogger .