"Replex: A Scalable, Highly Available Multi-Index Store"; https://www.usenix.org/conference/atc16/technical-sessions/presentation/tai

"Replex: A Scalable, Highly Available Multi-Index Store", Amy Tai, VMware Research and Princeton University; Michael Wei, VMware Research and University of California, San Diego; Michael J. Freedman, Princeton University; Ittai Abraham and Dahlia Malkhi, VMware Research. Best paper award, Usenix ATC 2016. Replex is a datastore that enables efficient querying on multiple keys by rethinking data placement. For the full paper and for Amy's ATC presentation, see https://www.usenix.org/conference/atc16/technical-sessions/presentation/tai