Enabling In-Vitro Serverless Systems Research

Dmitrii Ustiugov, Dohyun Park, Lazar Cvetković, Mihajlo Djokic, Hongyu Hè, Boris Grot, Ana Klimovic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Serverless is an increasingly popular cloud computing paradigm that has stimulated new systems research opportunities. However, developing and evaluating serverless systems in a research setting (i.e., “in-vitro”, without access to a largescale production cluster and real workloads) is challenging yet vital for innovation. Recently, several serverless providers have released production traces consisting of large sets of functions with their invocation inter-arrival time, execution time, and memory footprint distributions. However, executing the workload synthesized from these traces requires a massive cluster, making experiments expensive and timeconsuming. In this work, we show how to use the data available in production traces to construct workload summaries of configurable scales that remain highly representative of the original trace characteristics and can be used to evaluate serverless systems in-vitro. Compared to random sampling of functions from the original trace, our method can generate summaries of up to 10× higher representativity, measured as the average of the Wasserstein distances of the distributions of interest (e.g., function execution time and invocation interarrival time) from the respective distributions in the original trace. We release our toolchain that enables researchers to synthesize representative workload summaries and show how it can be used to evaluate the performance of serverless systems at diverse load scale factors.
Original languageEnglish
Title of host publicationWORDS '23: Proceedings of the 4th Workshop on Resource Disaggregation and Serverless
PublisherACM
Pages1-7
Number of pages7
ISBN (Electronic)9798400702501
DOIs
Publication statusPublished - 23 Oct 2023
Event4th Workshop on Resource Disaggregation and Serverless (WORDS 2023) - Koblenz, Germany
Duration: 23 Oct 2023 → …
Conference number: 4
https://www.wordsworkshop.org/

Workshop

Workshop4th Workshop on Resource Disaggregation and Serverless (WORDS 2023)
Abbreviated titleWORDS 2023
Country/TerritoryGermany
CityKoblenz
Period23/10/23 → …
Internet address

Fingerprint

Dive into the research topics of 'Enabling In-Vitro Serverless Systems Research'. Together they form a unique fingerprint.

Cite this