• Home

Alluxio Enterprise Edition and Community Edition Unified View of Enterprise Data Available

Allowing big data compute framework to access data in any storage system at memory speed
This is a Press Release edited by on 2016.11.04

AddThis Social Bookmark Button

Alluxio, Inc. (formerly Tachyon) announced availability of its product portfolio, Alluxio Enterprise Edition (AEE) and Alluxio Community Edition (ACE).

Click to enlarge


Alluxio provides a unified view of enterprise data that spans disparate storage systems, locations and clouds, allowing any big data compute framework to access data in any storage system at memory speed. Today it runs critical workloads in Global 2000 companies such as Alibaba Group Holding Ltd. , Baidu, Inc., Barclay's Bank Plc, CERN, ESRI, Huawei Technologies Co., Ltd., Intel Corp., and Juniper Networks, Inc..

The proliferation of big data compute frameworks has created a severe challenge to enterprises seeking to extract value from data stored in their disparate storage systems that span devices, locations and even across public/private clouds. Today's high-performance applications demand real-time responses, driving a massive industry shift to in-memory file systems. Company's unified global namespace allows any compute framework to access disparate storage systems on premise and in the cloud at memory speed.

Community Edition and Enterprise Edition are tested and certified versions of the open source software originally developed at UC Berkeley's AMPLab. The software supercharges storage and gives customers an easy-to-install integrated package. Also included is an administrative interface called the Alluxio Manager, that makes it simple to deploy, manage and monitor Alluxio clusters at any scale. The Enterprise Edition adds mission-critical features such as enterprise security, data replication and enterprise-grade support and professional services to ensure success for the largest and most demanding customers.

"Our software is in production today at some of the largest sites in the world, unifying data at memory speeds," said Haoyuan Li, co-creator Alluxio project and founding CEO, Alluxio. "Our Enterprise and Community Editions make it much easier for the broadest range of users to take advantage of the performance and data unification benefits of Alluxio. We help customers unlock data that is trapped in scores of disparate storage systems by connecting them to the world's most powerful big data frameworks with ease, delivering convenience and reliability with unprecedented performance."

Alluxio Community Edition (ACE)
It is easy for new users to try the solution. It is available free of charge, and is designed to accelerate the adoption of the core technology. ACE users can quickly realize many of the same benefits of the solution as those enjoyed by some of the world's largest companies. These companies use the firm's solution to run big data applications across disparate storage systems at terabyte and petabyte scales - at memory speed.

Available for free download, Community Edition is a certified and tested distribution of Alluxio open source, packaged and ready to deploy.

Community Edition includes:

  • Proven Alluxio open source software, packaged, and certified by the company;

  • Drivers for a continually-expanding range of storage systems that today includes Amazon S3, Google Cloud Storage, Red Hat GlusterFS, Red Hat Ceph, Apache HDFS, Huawei FusionStorage, OpenStack Swift ;

  • Support for a continually-expanding range of big data computation frameworks that today includes Apache Spark, Apache Flink, Apache Storm, Apache Hadoop, Apache Mapreduce, Apache Samza, Apache Flink;

  • Alluxio Manager is a graphical administrative interface that simplifies installing, managing and monitoring Alluxio clusters. It delivers a convenient, intuitive and user-friendly way to deploy Alluxio across specified cluster nodes without having to install software manually, update automation scripts or rely on third-party tools.

Enterprise Edition
It is available at tiered pricing levels depending on enterprise customer requirements for features, service and support. It is designed for customers who want to run the solution in production environments with critical enterprise features such as advanced HA, replication and security - all backed by enterprise support and professional services.

Enterprise Edition includes all the components of Community Edition plus:

  • Kerberos-based, end-to-end security that integrates with leading enterprise authentication solutions;

  • Replication of data on load/read for dramatic performance gains;

  • HA via replication of data on write;

  • Enterprise support and professional services with choices of 8x5 or round-the-clock 24/7 support.

Alluxio Manager screenshot
Click to enlarge


Alluxio proven in enterprise
The solution proves its value in production scenarios where customers need to analyze vast amounts of data in real-time. It overcomes I/O limitations for running big data workloads that have to access remote storage. In addition, it allows big data workloads to share data at memory speed for orders of magnitude higher performance in running jobs. Finally, it provides a unified view of storage by transparently managing data across disparate storage systems.

Examples enterprises adopting Alluxio include:

  • Baidu, the Google of China, wanted employees to be able to do ad-hoc interactive queries on petabytes of data to get insights into customers and their business. Before Alluxio, the data was stored in different data centers and I/O choked performance. Spanning all of these storage systems and locations, the solution slashed query times from 15 minutes to 30s, a 30X performance improvement. Case study (registration required).

  • Barclay's, the 280-year-old global banking powerhouse, wanted to train proprietary models to improve risk management with machine learning and faster data queries but needed to perform its analysis all in memory to meet regulatory requirements that banned writing customer data to disk. The solution reduced iteration workflow time from hours to seconds by sharing data across jobs at in-memory speeds. Case study (registration required).

  • Qunar, China's number one e-travel site, wanted to deploy real-time machine learning algorithms to run on more than four terabytes of data to improve ad delivery. By efficiently managing data across disparate storage systems, the solution helped Qunar see a 15X boost in performance with peaks of up to 300X. Case study (registration required).