Vault

Vault

Vault

An OpenStack implementation of Parallel Database as a Service

Features

Run entirely on OpenStack

Users and administrators can provision and manage multiple parallel database instances with ease.

Extremely low operation cost

Vault is built using shared-process multi-tenancy. Different from using the virtual machine technology, Vault enables the sharing of cluster computers and database installations among clients. Operating a parallel database cloud now can save up to 80% resources (e.g., cluster computers, database licenses, electricity) without jeopardizing the security and performance.

Performance SLA guarantee

Ensuring a tenant query performance with SLA

Support Vertica

Publications

Parallel Analytics as-a-Service

Petrie Wong, Andy He, Eric Lo. In Proceedings of ACM SIGMOD Conference, 2013.

Thrifty: Offering Parallel Database as a Service using the Shared-Process Approach

Petrie Wong, Andy He, Ziqiang Feng, Wenjian Xu, Eric Lo. In Proceedings of ACM SIGMOD Conference, 2015.

Efficient Pattern-Based Aggregation on Sequence Data

Zhian He, Petrie Wong, Ben Kao, Eric Lo, Reynold Cheng, Ziqiang Feng. In IEEE Transactions on Knowledge and Data Engineering, Volume 29

InferSpark: Statistical Inference at Scale

Zhuoyue Zhao, Eric Lo, Kenny Q. Zhu, Chris Liu.

Closest Interval Join Using MapReduce

Qiang Zhang, Andy He, Chris Liu, Eric Lo. In DSAA 2016.

Fast Multi-Column Sorting in Main-Memory Column-Stores

Wenjian Xu, Ziqiang Feng, Eric Lo. In Proceedings of ACM SIGMOD Conference, 2016.

ByteSlice: Pushing the Envelop of Main Memory Data Processing with a New Storage Layout

Ziqiang Feng, Eric Lo, Ben Kao, Wenjian Xu. In Proceedings of ACM SIGMOD Conference, 2015.

Accelerating aggregation using intra-cycle parallelism

Ziqiang Feng, Eric Lo. In ICDE, 2015.

Query Optimization over Cloud Data Market

Yu Li, Eric Lo, Man Lung Yiu, Wenjian Xu. In EDBT, 2015.

Contributors

Chris Liu
Eric Lo (PI)
Julian Ip
Lily Zhang
Petrie Wong

Acknowledgements

We are extremely grateful to HP and Greenplum for the support of free academic license of Vertica and Greenplum, respectively. This project is funded by Hong Kong Government Innovative Technology Fund and AWS Research Award.

Documentation

Please see the linked pages for more details about Vault: https://github.com/vault-team/vault-website/wiki

Code released under the Apache License 2.0.