Twitter's Yao Yue on Latency, Performance Monitoring, & Caching at Scale

This week's podcasts features Yao Yue of Twitter. Yao spent the majority of her career working on caching systems at Twitter. She has since created a performance team that deals with edge performance outliers often exposed by the enormous scale of Twitter. In this podcast, she discusses standing up the performance team, thoughts on instrumenting applications, and interesting performance issues (and strategies for solving them) they’ve seen at Twitter. Why listen to this podcast: * Performance problems can be caused by a few machines running slowly causing cascading failure * Aggregating stats on a minute-by-minute basis can be an effective way of monitoring thousands of servers * Being able to record second-by-second is often too expensive to centrally aggregate, but can be stored locally * Distinguishing between request timeout and connection/network timeouts is important to prevent thundering herds * With larger scale organisations, having dedicated performance teams helps centralise skills to solve performance problems More on this: Quick scan our curated show notes on InfoQ http://bit.ly/2wnBemB You can also subscribe to the InfoQ newsletter to receive weekly updates on the hottest topics from professional software development. bit.ly/24x3IVq Subscribe: www.youtube.com/infoq Like InfoQ on Facebook: bit.ly/2jmlyG8 Follow on Twitter: twitter.com/InfoQ Follow on LinkedIn: www.linkedin.com/company/infoq Want to see extented shownotes? Check the landing page on InfoQ: http://bit.ly/2wnBemB