Alluxio (formerly Tachyon): New Features and Demos

This is a past event

253 people went

Location visible to members


Alluxio (formerly Tachyon) features a chance to interact with other Alluxio ( users and developers, along with four presentations. Registration is required.

a) Ziya Ma from Intel ( will be talking about optimizing storage solutions.

b) Haoyuan Li and Gene Pang from Alluxio ( will share new community developments, features and improvements in Alluxio 1.0 ( and 1.1.

c) Calvin Jia from Alluxio ( will demo and present the benefits of Spark and Alluxio with S3 (

d) Jiri Simsa from Alluxio ( will dive into Alluxio's unified namespace ( feature and illustrate how users can leverage it.


6:30 - 7:00: Food & Networking

7:00 - 8:00: Presentations

8:00 - 8:15: Q&A

8:15 - 8:30: Wind down

Food will be available starting at 6:30pm, presentations will begin at 7:00pm. Special thanks to Intel for hosting.

Optimizing Storage Solution for Big Data


Big data ecosystem is moving with massive energy, customers are from healthcare, retail, transportation, and other fields are benefiting significantly from the business insights derived. As the data growth continues, storage technologies and distributed memory systems are becoming even more important for real time decision making and insight discovery. Intel is excited to work with developer communities on Alluxio and to optimize Alluxio solutions on Intel platform. In this talk, Ziya will discuss Intel’s optimization work in the area, open source contribution and industry use cases.


Ziya Ma is vice president in the Software and Services Group and director of big data technologies at Intel Corporation. She is responsible for optimizing big data solutions on the Intel® architecture platform, leading open source efforts in the Apache community, and bringing about optimal big data analytics experiences for Intel customers. Her team works closely with internal product teams, the open source community, the industry and academia to further Intel’s efforts in the big data field.

Ma spent the first 10 years of her Intel career in the Technology and Manufacturing Group, holding various management positions related to the development of embedded software for factory equipment, manufacturing execution systems, process-control systems, user interfaces and business intelligence solutions. Before assuming her current position in 2014, Ma was the product development software director at Intel IT. Prior to joining Intel in 2000, Ma was a software engineer in the semiconductor product division at Motorola Inc.

Alluxio, formerly Tachyon, is Entering a New Era -- New Features and Improvements in Alluxio 1.0 and 1.1.


Alluxio is a memory speed virtual distributed storage system. It originated from AMPLab, UC Berkeley in 2012, the same lab produced Apache Mesos and Apache Spark. Soon later, it became an open source project and is deployed at many companies. Since then, Alluxio has attracted more than 250 contributors from over 50 institutions. Since 2015, Alluxio creators and top committers founded a company to further accelerate the development of Alluxio.

As the first meetup after the rebranding from Tachyon to Alluxio, we will first present exciting updates and new developments of the community. Followed by many new features and improvements in Alluxio 1.0 and 1.1 releases. These features include new Alluxio APIs, improved storage system integrations, usability features, and performance improvements.


Haoyuan Li is founder and CEO of Alluxio (formerly Tachyon Nexus). He is a computer science PhD candidate at AMPLab, UC Berkeley, where he co-created Alluxio. He is a founding committer of Apache Spark. Before the AMPLab, he worked at Conviva and Google. Haoyuan has an MS from Cornell University and a BS from Peking University.

Gene Pang is a software engineer at Alluxio and one of the top contributors to the Alluxio project. He recently graduated with a Ph.D. from the AMPLab at UC Berkeley, working on distributed database systems. Before starting at Berkeley, he worked at Google and has an M.S. from Stanford University, and B.S. from Cornell University.

Spark + Alluxio + S3


Enabling and improving the integrations between different systems in the Big Data ecosystem is a main focus of Alluxio. The most common stack is compute frameworks on top of Alluxio and under storage systems below Alluxio. Using this architecture brings significant benefits to both sides of Alluxio:

Compute frameworks benefit from a level of abstraction and performance gain, allowing for fast data access without considering the storage type.

Under storage systems can be easily integrated with Big Data applications and suddenly can be treated as fast storage.

This presentation will outline the benefits Alluxio brings to the stack and give a demo of some of these advantages with Spark, Alluxio, and S3.


Calvin Jia is the top contributor to the Alluxio project and one of the earliest contributors. He started on the project as an undergraduate working in UC Berkeley’s AMPLab. He is currently a software engineer at Alluxio. Calvin has a BS from the University of California, Berkeley.

Unified Namespace


Alluxio's unified namespace is an abstraction that makes it possible to access multiple independent storage systems through the same namespace and interface. Leveraging Alluxio’s unified namespace provides the following 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: integrating an application or a storage system with Alluxio is a one-time effort which enables the application to access many different types of storage systems and the storage system to be accessed by many different types of applications


Jiri Simsa is a software engineer at Alluxio. Prior to Alluxio, he was a software engineer at Google, working on a framework for building decentralized, multi-system, and secure applications. Jiri holds a Ph.D. degree in computer science from Carnegie Mellon University.