The backends of today’s Internet services rely heavily on caching at various layers both to provide faster service to common requests and to reduce load on back-end components. Cache placement is especially challenging given the diversity of workloads handled by widely deployed Internet services. This paper presents FLUXO, an analysis technique that automatically optimizes cache placement. Our experiments have shown that near-optimal cache placements vary significantly based on input distribution. Categories and Subject Descriptors H.3.5 [Online Information Services]: Web-based services; D.4.2 [Storage Management]: Distributed memories; D.4.7 [Operating Systems]: Distributed systems; D.3.2 [Language Classifications]: Data-flow languages General Terms Algorithms, Design, Experimentation, Languages, Management, Performance Keywords Caching, simulation, optimization, dataflow model, Internet services, cloud computing
Alexander Rasmussen, Emre Kiciman, V. Benjamin Liv