Serverless execution of scientific workflows: Experiments with HyperFlow, AWS Lambda and Google Cloud Functions

Malawski, Maciej; Gajek, Adam; Zima, Adam; Baliś, Bartosz; Figiela, Kamil

doi:10.1016/j.future.2017.10.029

Cited by 140 publications

(86 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The first one is our new suite, designed specifically for this research, based on Serverless Framework. The second one uses our HyperFlow workflow engine . The reason for having two suites was that one of them, namely the HyperFlow, has been already used before to run preliminary experiments on cloud functions, and it allows us to execute workflows that can have many parallel tasks.…”

Section: Benchmarking Framework For Cloud Functionsmentioning

confidence: 99%

“…For running parallel benchmarking experiments, we adapted HyperFlow workflow engine. HyperFlow was earlier integrated with Google Cloud Functions, and for this work, it was extended to support AWS Lambda. HyperFlow is a lightweight workflow engine based on Node.js, and it can orchestrate complex large‐scale scientific workflows, including directed acyclic graphs (DAG).…”

Section: Benchmarking Framework For Cloud Functionsmentioning

confidence: 99%

“…Similar scenarios can be observed in potential scientific use cases, where cloud functions can process compute-intensive tasks from, eg, scientific workflows. 1,17 Similar use cases can be seen in, eg, genomics data processing pipelines, where cloud functions (lambdas) can be run in parallel to work on individual data items from a large dataset. 22 In this case, also the download-process-upload pattern is prevalent.…”

Section: Motivating Use Casesmentioning

confidence: 99%

“…The subscriber has to choose one of available functions sizes that affects RAM, CPU, and IO allocation. Cloud functions are typically executed in a Node.js environment, but they also allow running custom binary code, which gives an opportunity for using them not only for Web or event‐driven applications but also for some compute‐intensive tasks as presented in our earlier work …”

Section: Introductionmentioning

confidence: 99%

“…We have developed a framework for performance evaluation of cloud functions and applied it to all the major cloud function providers: AWS Lambda, Azure Functions, Google Cloud Functions, and IBM Cloud Functions. Moreover, we used our existing scientific workflow engine HyperFlow, which has been recently extended to support cloud functions, to run parallel workflow benchmarks. We report on the initial results of the performance evaluation, and we discuss the discovered insights into resource allocation policies.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Performance evaluation of heterogeneous cloud functions

Figiela

Gajek

Zima

et al. 2018

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary Cloud Functions, often called Function‐as‐a‐Service (FaaS), pioneered by AWS Lambda, are an increasingly popular method of running distributed applications. As in other cloud offerings, cloud functions are heterogeneous due to variations in underlying hardware, runtime systems, as well as resource management and billing models. In this paper, we focus on performance evaluation of cloud functions, taking into account heterogeneity aspects. We developed a cloud function benchmarking framework, consisting of one suite based on Serverless Framework and one based on HyperFlow. We deployed the CPU‐intensive benchmarks: Mersenne Twister and Linpack. We measured the data transfer times between cloud functions and storage, and we measured the lifetime of the runtime environment. We evaluated all the major cloud function providers: AWS Lambda, Azure Functions, Google Cloud Functions, and IBM Cloud Functions. We made our results available online and continuously updated. We report on the results of the performance evaluation, and we discuss the discovered insights into resource allocation policies.

show abstract

Section: Benchmarking Framework For Cloud Functionsmentioning

confidence: 99%

Section: Benchmarking Framework For Cloud Functionsmentioning

confidence: 99%

Section: Motivating Use Casesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Performance evaluation of heterogeneous cloud functions

Figiela

Gajek

Zima

et al. 2018

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

show abstract

Workflow aware analytical model to predict performance and cost of serverless execution

Kumari

Sahoo

Behera

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummaryServerless computing has emerged as a powerful deployment model based on the Function‐as‐a‐Service (FaaS) paradigm, where applications are orchestrated through a set of independent functions. The function orchestration within an application can be represented through a serverless workflow, which defines the overall execution plan of the application. To ensure the quality of service for serverless computing platforms, it is essential to develop performance and cost models that can predict the service quality that can be obtained from deploying and executing applications in the cloud platform. While several analytical models have been developed for various cloud deployment frameworks in recent years, there has been a lack of performance and cost analysis models for serverless computing platforms. The existing performance and cost monitoring tools available in serverless frameworks face several challenges, such as complexity, lack of transparency, and incomplete monitoring data. In this paper, we fill the gap by proposing an efficient workflow‐based analytical model that can estimate the end‐to‐end response time and cost of the serverless execution plan. The proposed model can handle complex structures like loop, cycles, self‐loop, and parallel substructures that exist in serverless workflows. Additionally, we propose a heuristic optimization algorithm to identify the optimal resource configuration to achieve the optimal response time under a given budget constraint. We evaluated the effectiveness of the proposed model by considering seven serverless applications in both AWS Lambda and Microsoft Azure platforms. We compared the accuracy of the proposed model with the real values of response time and cost obtained in AWS Lambda and Microsoft Azure serverless platforms. The proposed performance and cost model in the AWS Lambda platform has been observed to have an average accuracy of 99.2% and 98.7% respectively. In the Microsoft Azure platform, the average accuracy of the performance and cost model has been observed to be 98.6% and 98.2% respectively.

show abstract

Quantum and blockchain based Serverless edge computing: A vision, model, new trends and future directions

Gill

2021

Internet Technology Letters

View full text Add to dashboard Cite

Serverless computing has become an important cloud model delivering service to users based on the amount of resources consumed by the Internet of Things (IoT) applications. Edge computing can be utilized for Serverless computing to process small or deadline oriented jobs efficiently at edge devices helping to reduce latency. Furthermore, security and computation speed have become important challenges for Serverless edge computing. Blockchain and Quantum computing can be used to provide secure and reliable edge Serverless service while also improving security and computation speed respectively. This letter identifies and integrates various emerging paradigms to develop a conceptual model for Quantum and Blockchain based Serverless edge computing. Promising future research directions and open challenges are also discussed.

show abstract

Serverless execution of scientific workflows: Experiments with HyperFlow, AWS Lambda and Google Cloud Functions

Cited by 140 publications

References 11 publications

Performance evaluation of heterogeneous cloud functions

Performance evaluation of heterogeneous cloud functions

Workflow aware analytical model to predict performance and cost of serverless execution

Quantum and blockchain based Serverless edge computing: A vision, model, new trends and future directions

Contact Info

Product

Resources

About