SAND: Towards High-Performance Serverless Computing

By Istemi Ekin Akkus, Ruichuan Chen, Ivica Rimac, Manuel Stein, Klaus Satzke, Andre Beck, Paarijaat Aditya, Volker Hilt. 2018

479 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

Cloud Programming Simplified: A Berkeley View on Serverless Computing (2019, methodology): “As such, applications are left with no choice but to either (1) manage a VM-based system that provides notifications, as in ElastiCache and SAND [45], or (2) implement their own notification mechanism, such as in ExCamera [26], that enables cloud functions to communicate with each other via a long-r”
AI for Next Generation Computing: Emerging Trends and Future Directions (2022, unknown): “It is the purpose of serverless computing to guarantee hat the finest serverless technologies are used so that the investment is minimised and the return is highest [126].”
SOCK: Rapid Task Provisioning with Serverless-Optimized Containers (2018, unknown): “[1] also leverage this technique to efficiently launch multiple lambdas in the same container when the lambdas belong to the same application.”
Catalyzer: Sub-millisecond Startup for Serverless Computing with Initialization-less Booting (2020, background): “Many systems adopt the idea of caching for serverless function startup [17, 39, 40].”
Serverless in the Wild: Characterizing and Optimizing the Serverless Workload at a Large Cloud Provider (2020, methodology): “SAND [3] uses application-level sandboxing to prevent the cold start latency for subsequent function invocations within an application.”
Faasm: Lightweight Isolation for Efficient Stateful Serverless Computing (2020, background): “PyWren [42] reuses containers to execute multiple functions; Crucial [12] shares a single instance of the Java virtual machine (JVM) between functions; SAND [1] executes multiple functions in long-lived containers, which also run an additional message-passing service; and Cloudburst [75] takes a sim”
FaasCache: keeping serverless computing alive with greedy-dual caching (2021, background): “łheavyž workloads with high memory footprint and large initialization overheads such as highly parallel numerical computing (such as matrix operations [38], scientific computing [49], and machine learning [16].”