JVM goes to BigData
6:00 - 7:00 Networking & Light Dinner
7:00 - 7:15 Announcements
7:15 - 8:45 Talk
8:45 Q&A & Dismiss
Slowly yet surely the JVM is going to Big Data! In this fun filled presentation we see what pieces of Java & JVM triumph or unravel in the battle for performance at high scale! Concurrency is the currency of scale on multi-core & the new generation of collections and non-blocking hashmaps are well worth the time taking a deep dive into.
We take a quick look at the next gen serialization techniques as well as implementation pitfalls around UUID. The achilles' heel for JVM remains Garbage Collection: a deep dive into the internals of the memory model, common GC algorithms and their tuning knobs is always a big draw. EC2 & cloud present us with a virtualized & unchartered territory for scaling the JVM.
We will leave some room for Q&A or fill it up with any asynchronous I/O that might queue up during the talk. A round of applause will be due to the various tools that are essentials for Java performance debugging.
About the speaker:
SriSatish Ambati is chief tinkerer of Java and Enterprise stacks and working on his stealth mode startup. He recently led engineering for the Cassandra Company, DataStax & before that for 7 years at the JVM company, Azul Systems. Over the course of a decade or so, he has actively supported, profiled and scaled hundreds of in-production and in-development Java, enterprise and database stacks for performance.
He uses these experiences to distil system trends and turbulences. SriSatish's talks have been well received at conferences & tech fairs including JavaOne, JBossWorld & ApacheCon and is now a regular speaker at SFJava. He sometimes leaves trail @srisatish.