How to run Real Time processing on Big Data
summary
GigaSpaces XAP is an in-memory data grid that co-locates business logic with data to cut round trips to disk and achieve microsecond–millisecond response; it adds an SSD tier as key-value store to scale from gigabytes to terabytes without moving compute off RAM. Integrations include Kafka and Storm for event streams, and a change-API for delta updates. Real deployments: Kohl’s reimplemented inventory in ~4 months and hit top Black Friday performance; Avanza runs ~100 processing units and reports major cost and latency reductions.
AI-written summary · about
chapters (10)
- 0:00Start
- 1:33In-Memory Data Grid
- 5:58Real-Time Processing of Large Data Sets
- 6:38Challenge and Challenges of Peak Load Performance Business Continuity Tco Reduction and Real-Time Big Data Processing
- 9:09The Performance Challenge
- 11:23The Real Time Business Insights Challenges
- 12:44What in-Memory Data Grid Can Provide Us
- 23:30Complex Query Support
- 25:38Change Api Enhancement
- 29:44Multi-Site Data Replication
related talks
36mReal Time Big Data Analytics with Kafka, Storm, HBase #bbuzz
08mReal-Time Data Systems: Speed, Scale, and Resilience
33mReal-time Trade Data Processing and Machine Learning at Giga-Sca...
43mArchitecting for Speed & Scale
39mComplex Data Transformations Made Easy
01h 20mSupercharging Operations and Analytics: Using Spring XD to Support Analytics and CEP
30mFive Challenges in Real-time Stream Processing and Five Solutions
45mModern Data Architecture