Proceedings of the 9th International Conference on Cloud Computing and Services Science 2019
DOI: 10.5220/0007757304790487
|View full text |Cite
|
Sign up to set email alerts
|

Function-as-a-Service Benchmarking Framework

Abstract: Cloud Service Providers deliver their products in form of "as-a-Service", which are typically categorized by the level of abstraction. This approach hides the implementation details and shows only functionality to the user. However, the problem is that it is hard to measure the performance of Cloud services, because they behave like black boxes. Especially with Function-as-a-Service it is even more difficult because it completely hides server and infrastructure management from users by design. Cloud Service Pr… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1

Citation Types

0
4
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
3
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(4 citation statements)
references
References 11 publications
0
4
0
Order By: Relevance
“…The individual aspects are answered, but their inter-relations were not approached in detail. Pellegrini and others [37] focused on measuring routing properties which was done via a proxy function to understand the inner platform routing. Since the implementation is not open sourced and due to some missing information about the configuration of the experiment, the paper is only partly interpretable.…”
Section: Related Approachesmentioning
confidence: 99%
“…The individual aspects are answered, but their inter-relations were not approached in detail. Pellegrini and others [37] focused on measuring routing properties which was done via a proxy function to understand the inner platform routing. Since the implementation is not open sourced and due to some missing information about the configuration of the experiment, the paper is only partly interpretable.…”
Section: Related Approachesmentioning
confidence: 99%
“…Their framework, however, was not focused on performance analysis. Roland et al leveraged proxy functions between the client and target FaaS function to support performance profiling [17]. Proxy functions are deployed to the same FaaS platform as the target function.…”
Section: Faas Framework and Toolsmentioning
confidence: 99%
“…Nevertheless, they argued that microbenchmarking is important but not sufficient for the requirements real world use cases present. Authors of other real world experiments like SeBS [48] and BeFaaS [91] enforced that argument but are aware that real world use cases [167] 2018 Benchmarking Heterogeneous Cloud Functions Pawlik et al [211] 2018 Performance evaluation of parallel cloud functions Wang et al [282] 2018 Peeking Behind the Curtains of Serverless Platforms Bortolini & Obelheiro [29] 2019 Investigating Performance and Cost in Function-as-a-Service Platforms Giménez-Alventosa et al [86] 2019 A framework and a performance assessment for serverless MapReduce on AWS Lambda Kim & Lee [121] 2019 FunctionBench: A Suite of Workloads for Serverless Cloud Function Service Kim & Lee [122] 2019 Practical Cloud Workloads for Serverless FaaS Pellegrini et al [214] 2019 Function-as-a-Service Benchmarking Framework Copik et al [48] 2020 SeBS: A Serverless Benchmark Suite for Function-as-a-Service Computing Kuhlenkamp at al. [139] 2020 Benchmarking Elasticity of FaaS Platforms as a Foundation for Objective-driven Design of Serverless Applications Maissen et al [166] 2020 FaaSdom: a benchmark suite for serverless computing Martins et al [189] 2020 Benchmarking Serverless Computing Platforms Yu et al [293] 2020 Characterizing serverless platforms with serverlessbench Grambow et al [91] 2021 BeFaaS: An Application-Centric Benchmarking Framework for FaaS Platforms Lin & Khazaei [154] 2021 Modeling and Optimization of Performance and Cost of Serverless Applications Pons and López [17] 2021 Benchmarking Parallelism in FaaS Platforms Ristov et al [231] 2022 are often not that precise in their conclusions due to noise in the collected data.…”
Section: Introductionmentioning
confidence: 99%
“…Since they only executed a single function (prime number search) on a single memory setting, their insights on how different cloud function configurations influence the execution behavior of a function is limited, but related to understanding the impact of the application workload on the number of instances [179]. A different approach to assess routing properties and the number of instances is to implement a proxy [214] to understand the inner workings of platforms.…”
Section: Introductionmentioning
confidence: 99%