Alluxio (formerly Tachyon):
Accessing Data Anywhere with Unified Namespace
Jiri Simsa
June 15, 2016 @ Alluxio Meetup (hosted by Intel)
About Me
• Software Engineer @ Alluxio, Inc.
• PMC Member and Maintainer of Alluxio Open Source Project
• Ph.D. from Carnegie Mellon University (Parallel Data Lab)
• Worked at Google before joining Alluxio
• Twitter: @jsimsa, Github: jsimsa
2
Outline
• Motivation
• Unified Namespace
• Use Cases
• Demo
3
Big Data Ecosystem
4
Big Data Ecosystem
5
Big Data Ecosystem
6
Alluxio Benefits
• Future-proofing your applications
–applications can communicate with different storage
systems, both existing and new, using the same
namespace and interface
–seamless integration between applications and new
storage systems enables faster innovation
• Enabling new workloads
–one-time effort to enable an application to access many
different types of storage systems and a storage system
to be accessed by many different types of applications
7
Outline
• Motivation
• Unified Namespace
• Use Cases
• Demo
8
Unified Namespace
an abstraction that makes it possible for
applications to access different storage
systems through the same interface
9
Transparent Naming
•Operations over persisted Alluxio objects
mapped transparently to underlying storage
•Alluxio paths are preserved in storage layer
Alluxio Storage System (HDFS, S3, …)
alluxio://host:port/
Data Users
Reports Sales Alice Bob
hdfs://host:port/
Data Users
Reports Sales Alice Bob
10
Multiple Storage Systems
•Unified namespace for multiple data sources
•Sharing of data across storage systems
•API for on-the-fly mounting / unmounting
Alluxio
Storage System A
alluxio://host:port/
Data Users
Alice Bob
hdfs://host:port/
Users
Alice Bob
Storage System B
s3://host/bucket
Reports Sales
Reports Sales
11
Outline
• Motivation
• Unified Namespace
• Use Cases
• Demo
12
Multiple Storage / Compute
13
Changing Storage Backend
14
Changing Storage Backend
15
Outline
• Motivation
• Unified Namespace
• Use Cases
• Demo
16
Resources
• Alluxio Project: http://www.alluxio.org
• Development: https://github.com/Alluxio/alluxio
• Meet Friends: http://www.meetup.com/Alluxio
• Alluxio, Inc.: http://www.alluxio.com
• Contact us: info@alluxio.com
17
Backup Slides
18
Architecture Overview
19

Accessing Data Anywhere with Unified Namespace