Tags : Browse Projects

Alluxio, formerly Tachyon, is a memory speed virtual distributed storage enabling reliable data sharing at memory-speed across cluster jobs. Alluxio lies between computation frameworks, such as Spark, MapReduce, or Flink, and various storage systems, such as Amazon S3, OpenStack Swift, GlusterFS ... [More] , HDFS, or Ceph. Alluxio brings significant performance improvement and bridges new workloads with data stored in traditional storage. Alluxio is Hadoop compatible. Existing Spark and MapReduce programs can run on top of it without code changes. The project is deployed at multiple companies. With less than three years open source history, Alluxio has attracted more than 600 contributors from over 200 institutions, including Alibaba, Alluxio, Baidu, IBM, Intel, Red Hat, and UC Berkeley. [Less]