Towards Latency Sensitive Cloud Native Applications: A Performance Study on AWS

Pelle, István; Czentye, János; Dóka, János; Sonkoly, Balázs

doi:10.1109/cloud.2019.00054

Cited by 59 publications

(38 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We benchmarked these scenarios on both of our edge nodes. In accordance with our previous measurements in [28] using the same methodology as here, invoking a function in the central cloud from the edge is the slowest, taking 125-231 ms to complete. In terms of latency, this invocation type is one of the slowest of available AWS Lambda calls and is 20-30 ms slower than asynchronous SDK calls between Lambda functions.…”

Section: B Performance Of Aws Greengrasssupporting

confidence: 89%

“…Comparing the above results with those given by [28], we can conclude, that using AWS IoT Greengrass solutions result in relatively low latency only when the cloud functions are not involved. If an application requires low latency as well as edge and cloud functions, it is better to use SDK calls between them instead of relying on AWS IoT.…”

Section: B Performance Of Aws Greengrasssupporting

confidence: 59%

“…In our previous works [7], [28], we provided a comprehensive performance study of delay characteristics of AWS FaaS and CaaS offerings, based on short-and long-term experiments. Here, we give a summary on them focusing on our main findings with regards to AWS Lambda.…”

Section: A Performance Of Aws Lambdamentioning

confidence: 99%

“…In case of latency sensitive applications, the most important performance features to measure are flavor dependent computation proficiency and invocation latency. In order to investigate these aspects with AWS Greengrass, we repeated the respective benchmarks discussed in [28]. We used two different edge nodes to execute the tests: a local server with four Intel Xeon E5-2650 v3 CPU cores, 6 GiB of memory running Ubuntu 18.04 and an Amazon EC2 t2.micro instance with 1 vCPU and 1 GiB memory running the same OS in the eu-west-1 (Ireland) AWS region.…”

Section: B Performance Of Aws Greengrassmentioning

confidence: 99%

See 3 more Smart Citations

Operating Latency Sensitive Applications on Public Serverless Edge Cloud Platforms

Pelle

Czentye

Dóka

et al. 2021

IEEE Internet Things J.

Self Cite

View full text Add to dashboard Cite

Section: B Performance Of Aws Greengrasssupporting

confidence: 89%

Section: B Performance Of Aws Greengrasssupporting

confidence: 59%

Section: A Performance Of Aws Lambdamentioning

confidence: 99%

Section: B Performance Of Aws Greengrassmentioning

confidence: 99%

See 2 more Smart Citations

Operating Latency Sensitive Applications on Public Serverless Edge Cloud Platforms

Pelle

Czentye

Dóka

et al. 2021

IEEE Internet Things J.

Self Cite

View full text Add to dashboard Cite

“…They developed a system that pulls from a Docker container to deploy a specified image on Lambda to find a workaround for the stateful component, but they also reported throughput difficulties. Pelle [21] also used a measurement framework to capture delay characteristics and applied it to a latency-sensitive drone control application. Although they did not publish their methodology, their results may still serve for comparison.…”

Section: Literature Review and Related Workmentioning

confidence: 99%

A Traffic Analysis on Serverless Computing Based on the Example of a File Upload Stream on AWS Lambda

Müller

Chrysoulas

Pitropakis

et al. 2020

BDCC

View full text Add to dashboard Cite

The shift towards microservisation which can be observed in recent developments of the cloud landscape for applications has led towards the emergence of the Function as a Service (FaaS) concept, also called Serverless. This term describes the event-driven, reactive programming paradigm of functional components in container instances, which are scaled, deployed, executed and billed by the cloud provider on demand. However, increasing reports of issues of Serverless services have shown significant obscurity regarding its reliability. In particular, developers and especially system administrators struggle with latency compliance. In this paper, following a systematic literature review, the performance indicators influencing traffic and the effective delivery of the provider’s underlying infrastructure are determined by carrying out empirical measurements based on the example of a File Upload Stream on Amazon’s Web Service Cloud. This popular example was used as an experimental baseline in this study, based on different incoming request rates. Different parameters were used to monitor and evaluate changes through the function’s logs. It has been found that the so-called Cold-Start, meaning the time to provide a new instance, can increase the Round-Trip-Time by 15%, on average. Cold-Start happens after an instance has not been called for around 15 min, or after around 2 h have passed, which marks the end of the instance’s lifetime. The research shows how the numbers have changed in comparison to earlier related work, as Serverless is a fast-growing field of development. Furthermore, emphasis is given towards future research to improve the technology, algorithms, and support for developers.

show abstract

Towards a Blockchain and Fog-Based Proactive Data Distribution Framework for ICN

Mazumdar¹,

Dreibholz²

2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Towards Latency Sensitive Cloud Native Applications: A Performance Study on AWS

Cited by 59 publications

References 4 publications

Operating Latency Sensitive Applications on Public Serverless Edge Cloud Platforms

Operating Latency Sensitive Applications on Public Serverless Edge Cloud Platforms

A Traffic Analysis on Serverless Computing Based on the Example of a File Upload Stream on AWS Lambda

Towards a Blockchain and Fog-Based Proactive Data Distribution Framework for ICN

Contact Info

Product

Resources

About