Open Source Memory Speed Virtual Distributed Storage

Alluxio, formerly Tachyon, enables any application to interact with any data from any storage system at memory speed.

Get Started Download

What's New


Alluxio Exploration and Application Practice

Beijing Meetup · Jan 20, 2018


Apache Kylin and Alluxio

Shanghai Meetup · Jan 21, 2018


Powering Robotics Clouds with Alluxio

Strata San Jose · Mar 7, 2018

Unified Namespace

Alluxio's unified namespace provides applications the same file system APIs to access your data in any storage like SANs, distributed file systems or object stores.

Memory Speed

Alluxio's memory centric architecture enables applications to have memory speed I/O.

Efficient Data Sharing

Alluxio enables easy and efficient sharing of data across frameworks and applications at memory speed.

Framework Flexibility

Alluxio supports various existing frameworks, such as Spark, MapReduce, Flink, and its filesystem API seamlessly works with future frameworks and applications.

Tiered Storage

Alluxio tiered storage architecture makes our users efficiently leverage storage media other than memory, such as SSD, HDD, and others.

Run Everywhere

Alluxio runs well in cloud, on-premise, and hybrid cloud environments.

Customizable Data Management

Alluxio provides customizable and pluggable policies for defining data management behavior that best fits your workloads and needs

Hadoop Compatible

Alluxio provides Hadoop compatible file system interface. Any Hadoop applications can run on Alluxio without any code change.

Linear Scalability

Industry deployments demonstrates scalability to thousands of nodes.

Between Computation Frameworks and Storage Systems

Alluxio users can work with frameworks of their choice. Additionally, Alluxio enables new workloads across different storage systems.

Various frameworks can share data efficiently among each other. Alluxio's unified namespace enables applications to interact data in any storage system at memory speed. This future proven architecture enables users to extract value from data in any storage faster.

Strong Community

Alluxio has attracted contributors from over 100 institutions, including Alibaba, Alluxio, Baidu, CMU, Google, IBM, Intel, NJU, Red Hat, UC Berkeley and Yahoo. The project is the storage layer of the Berkeley Data Analytics Stack (BDAS) and also part of the Fedora distribution. If you'd like to join the community, or contribute to Alluxio, learn how to contribute.

Number of Contributors to Alluxio


More Than 20,000 Contributions

More Than 2,800 Stars

Need help? Ask a Question