Introducing Apache HTrace
Apache HTrace is a new incubator project which makes it easier to monitor and understand the performance of distributed systems. It aims to provide a truly end-to-end, cluster-wide view of how requests are processed in a production distributed system.
I'll talk about the core concepts and architecture behind HTrace, including trace spans and distributed tracing. HTrace supports multiple projects and programming languages. I'll discuss how distributed systems can use HTrace to get more insight into what is happening in production.
HTrace was motivated by real-world debugging experiences in distributed systems. I will talk about some of those issues and how HTrace addresses them. I'll talk about our experiences using HTrace in production in Apache Hadoop.
Finally, I'll discuss some of the new features that are on the horizon for HTrace, and how developers and users can get involved with the HTrace community.