Fluid - Build Data Orchestration in Kubernetes

Explore data orchestration in Kubernetes with Fluid in this 29-minute conference talk by Yang Che from Alibaba and Yuandong Xie from Tencent. Discover how Fluid addresses challenges in data-intensive tasks like big data and AI within cloud-native environments. Learn about efficient data abstraction techniques that provide data affinity scheduling, distributed cache engine acceleration, and multi-source data integration. Gain insights into how Fluid's data scheduling accelerates Big Data and AI workloads in Alibaba Cloud and Tencent Cloud. Dive into topics such as complicated data storage, I/O bottlenecks, locality-ignoring scheduling, and the Fluid architecture. Follow a quick start guide on creating datasets, running apps with data affinity, and auto-scaling datasets. Watch a demo and explore the roadmap for Fluid's future development. Understand how to join the community and contribute to this innovative project.

Intro
Agenda
Journey of A Data-driven Company
Technical Challenges Blocking Faster Adoption
st Challenge: Complicated Data Storage
nd Challenge: 1/0 Bottleneck
rd Challenge: Locality-ignoring Scheduling
What is Fluid, indeed
Fluid Architecture
A Quick Start on Fluid: (1) Create a "Dataset"
A Quick Start on Fluid: (2) Run Apps with Data Affinity
Quick Start on Fluid: Auto-scale Dataset
Demo
Roadmap
Plan
Community & Join Us