epiC is an Elastic, Power-aware, data-Intensive Cloud platform. The objectives are to design and implement an efficient multi-tenancy cloud system for supporting high throughout low latency transactions and high performance reliable query processing, with online analytics capability.
The whole system contains four main components: VBS, ES2, E3 and BigLog.
The system research work is supporting by MOE.
1 VBS is a file system federation, which is specially designed for supporting different file systems by leveraging both performance and utilization. Supported file systems include legacy systems(POSIX), HDFS/GFS(read-only), Key-value stores(append-only) and mission critical storage(memory-resident).
2 ES2 is particularly designed for write-intensive applications. Meanwhile, it also provides a hybrid storage mechanism to support both OLTP and OLAP. Mainstream Key-Value store systems, including HBase and Cassandra, are compatible with ES2.
3 E3 is a programming framework for simplifying parallel heterogeneous data processing on large clusters. It allows analysts to reuse existing data analytical programs and coordinate those programs to produce the final results.
4 Biglog is an extention of Datalog to support data processing on a mixture of strucutured and unstructured data. It is a declarative logic programming language to express complex queries in epiC.