Using an in-memory storage platform to bridge big-data systems
Presented by:
Bin Fan
Bin Fan is the founding member of Alluxio Inc and the PMC member of Alluxio open source project. Prior to Alluxio, he worked for Google to build the next-generation storage infrastructure. Bin got his Ph.D. in Computer Science from Carnegie Mellon University on the design and implementation of distributed systems and algorithms.
No video of the event yet, sorry!
Today, the emerging cloud storages like Amazon S3, Azure’s Blob storage along with on-premises solutions like Swift, Minio or Ceph provide many enterprises with scalable, low-cost, fault-tolerant storage capacity. Founded at UC Berkeley’s AMPLab, Alluxio (formerly Tachyon) acts as a single source virtual data layer and enables applications to transparently access data using a consistent interface regardless of the real data source (on-premises, public clouds or the hybrid sources).
This proposal aims to connect PostgreSQL, one of the most advanced open-source RDMBs, to Alluxio through its Foreign Data Wrappers (FDWs). With this connector, PostgreSQL can easily access data from different data sources without adding any new code or complexity. In addition, Alluxio also provides intelligent caching and data management to deliver fast performance, data consistency and high availability to the SQL engine. We believe Alluxio will be a great tool to bridge the gap between accessibility and performance when using these cloud or object stores.
- Date:
- 2018 October 15 13:00 PDT
- Duration:
- 50 min
- Room:
- Winchester 2
- Conference:
- Silicon Valley
- Language:
- Track:
- Data
- Difficulty:
- Medium