Pocket: Elastic Ephemeral Storage for Serverless Analytics

By A. Klimovic, Ya-wen Wang, Patrick Stuedi, A. Trivedi, Jonas Pfefferle, Christos Kozyrakis. USENIX Symposium on Operating Systems Design and Implementation, 2018

375 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b0d99d995b841f32590fcfde1d17a12a60c81584

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Johann Schleier-Smith
Simon Shillaker
Vikram Sreekanti
Peter R. Pietzuch
Anurag Khandelwal
Eric Jonas
Joseph Gonzalez
Chia-che Tsai

Citations in the corpus

Catalyzer: Sub-millisecond Startup for Serverless Computing with Initialization-less Booting (2020, methodology): “Executing serverless functions with low latency is critical for user experience [21, 24, 28, 32, 38], and is still a significant challenge for virtualization-based sandbox design.”
What serverless computing is and should become (2021, background): “17 Approaches to addressing these challenges include temporary data storage for analytics 21 as well as stateful cloud functions that integrate caching and provide consistency guarantees.”
Faasm: Lightweight Isolation for Efficient Stateful Serverless Computing (2020, background): “na [76] is a distributed KVS that achieves lower latency and more granular autoscaling than Redis; Tuba [9] provides an autoscaling KVS that operates within application-deﬁned constraints; and Pocket [37] is a granular autoscaled storage system built speciﬁcally for a serverless environments. Crucia”
Cloud Programming Simplified: A Berkeley View on Serverless Computing (2019, background): “Another recent effort, Pocket [44], aims to provide the abstraction of ephemeral storage, but also lacks autoscaling, requiring applications to allocate storage a priori.”