Vladimir Bacvanski Interview
summary
Distributed processing at scale improves throughput but networked microservices introduce latency, so the next optimization is to group services onto the same machine to regain efficiency. Big data and operational code converge, driving streaming architectures for near real-time big-data decisions that combine fast results with huge volumes. Functional languages reduce impedance mismatch and raise abstraction, yet a multi-paradigm approach lets teams use Scala/Akka/Spark and fall back to procedural optimizations when performance demands it.
AI-written summary · about
related talks
32mBig Data Processing : Where do we go next ?
25mSPARK AND AKKA FOR BIG DATA SYSTEMS, IN PRACTICE
47mStream All the Things!
02h 18mDistributed Systems: In the Daily Life of the Data Engineer
23mDesigning Robust and Scalable Distributed Applications
50mAddressing Recent Events
16m[Opening Keynote] Making Distributed Computing Easy
45mDeep dive into Unbounded Data Processing Systems