Kate, BryanKohler, EdwardKester, Michael SNarula, NehaMao, YandongMorris, Robert2015-09-212014Kate, Bryan, Eddie Kohler, Michael S. Kester, Neha Narula, Yandong Mao, and Robert Morris. 2014. "Easy Freshness with Pequod Cache Joins." In Proceedings of 11th USENIX Symposium on Networked Systems Design & Implementation (NSDI '14), Seattle, WA, April 2-4, 2014: 415-428.978-1-931971-09-6http://nrs.harvard.edu/urn-3:HUL.InstRepos:22718234Pequod is a distributed application-level key-value cache that supports declaratively defined, incrementally maintained, dynamic, partially-materialized views. These views, which we call cache joins, can simplify application development by shifting the burden of view maintenance onto the cache. Cache joins define relationships among key ranges; using cache joins, Pequod calculates views on demand, incrementally updates them as required, and in many cases improves performance by reducing client communication. To build Pequod, we had to design a view abstraction for volatile, relationless key-value caches and make it work across servers in a distributed system. Pequod performs as well as other inmemory key-value caches and, like those caches, outperforms databases with view support.en-USConference Paper2015-09-21