Avi Kivity discusses ScyllaDB, the many necessary design decisions, from the programming language and programming model through low-level details and up to the advanced cache design, and more.
Sergey Kuksenko discusses how Performance Monitoring Unit works, what Hardware Counters are, which tools have friendship with Java and how to use HWC for speeding up our Java applications.
Sayli Karmarkar discusses Winston, a monitoring and remediation platform built for Netflix engineers.
Tom Gianos and Dan Weeks discuss Netflix' overall big data platform architecture, focusing on Storage and Orchestration, and how they use Parquet on AWS S3 as their data warehouse storage layer.
Charity Majors talks about what it means to do quality operations and software engineering in the year 2016 and beyond, as well as the implications for engineering teams and social systems.
Mārtiņš Kalvāns and Matti Pehrs overview the Data Infrastructure at Spotify, diving into some of the data infrastructure components, such us Event Delivery, Datamon and Styx.
Chun-Ho Hung and Nikhil Garg discuss Quanta, Quora's counting system powering their high-volume near-real-time analytics, describing the architecture, design goals, constraints, and choices made.
Nikhil Garg talks about the various Machine Learning problems that are important for Quora to solve in order to keep the quality high at such a massive scale.
Daniel Tunkelang talks about what search looks like when viewed through a query understanding mindset. He focuses on query performance prediction, query rewriting, and search suggestions.
Marcin Grzejszczak and Reshmi Krishna describe how to do distributed tracing with Spring Cloud Sleuth and Zipkin, demoing incorporating these technologies into an existing stock trading application.
Adrian Cole overviews how to debug latency problems using call graphs created by Zipkin, taking a look at the ecosystem, including tools to trace Ruby, C#, Java and Spring Boot apps.
Tyler McMullen discusses load balancing techniques and algorithms such as Randomized Least-conns, Join-Idle-Queue, and Load Interpretation.
Featured Blog Post
Case Studies Post