Scale Out and Conquer: Architectural Decisions Behind Distributed In-Memory Systems
- Track: HPC, Big Data, and Data Science devroom
- Room: H.1302 (Depage)
- Day: Sunday
- Start: 12:10
- End: 12:20
Distributed platforms, like Apache Ignite, rely on horizontal scalability. More machines in the cluster means greater performance of the application. Do we always get twice the speed after adding the second machine to the farm? Ten times faster after adding ten machines? Is that [always] true? What is the responsibility of the platform? And where do engineers’ responsibilities begin?
In this talk attendees will learn about the compromises and pitfalls architects face when designing distributed systems:
• Advantages and disadvantages of different data-sharding algorithms. • Effective data models for distributed environments. • Synchronization and coordination in distributed systems. • Local scalability issues of speeding up local processing on cluster nodes.
Speakers
| Akmal Chaudhri |