Hardware Transactional Memory (HTM) is here. Again. It has finally become a common feature in commodity server hardware platforms. But what will we do with it? This session will explore the underlying mechanics that power HTM on current platforms, focusing on things developers need to understand when contemplating the use of HTM in new and existing code. We will discuss and demonstrate new speculative and optimistic locking mechanisms enabled by HTM, cover benefits and limitations, and speculate (pun intended) about both the near term and long term future impact of HTM on concurrency choices and everyday programming choices.

Cassandra is often used in environments where responsiveness is important. This session will discuss common challenges and concerns around response time sensitive deployments. Including Java's infamous GC behavior and things that can be done to address it. We will describe some patterns found in real world implementation, and demonstrate proven ways to contain and control response time behavior in Cassandra environments.