2018 IEEE 26th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS 2018
DOI: 10.1109/mascots.2018.00030
|View full text |Cite
|
Sign up to set email alerts
|

TeaStore: A Micro-Service Reference Application for Benchmarking, Modeling and Resource Management Research

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
23
0

Year Published

2020
2020
2022
2022

Publication Types

Select...
4
3
2

Relationship

0
9

Authors

Journals

citations
Cited by 92 publications
(30 citation statements)
references
References 35 publications
1
23
0
Order By: Relevance
“…The TeaStore is an online store for tea and tea related utilities [34]. The TeaStore benchmark application has been used as a distributed system for evaluating and extracting software performance models, for testing single and multi-tier auto-scalers, and for software energy-efficiency analysis and management.…”
Section: The Teastore Benchmark For Performance and Scalability Bench...mentioning
confidence: 99%
“…The TeaStore is an online store for tea and tea related utilities [34]. The TeaStore benchmark application has been used as a distributed system for evaluating and extracting software performance models, for testing single and multi-tier auto-scalers, and for software energy-efficiency analysis and management.…”
Section: The Teastore Benchmark For Performance and Scalability Bench...mentioning
confidence: 99%
“…Other works employ the SPEC Cloud Group metrics to report on the performance of newly-proposed autoscalers [4], [16]- [18]. Similar to [16] and [17], we use a microservices application as one of our test applications. However, our work is focused strictly on the Kubernetes autoscaler and not on general-purpose autoscalers.…”
Section: Related Workmentioning
confidence: 99%
“…In E2, we use a microservices-based test and reference application -TeaStore [17] -composed of six services. We chose this application as a representative because Kubernetes is preferred to run microservices as it makes it easy to run the loosely coupled, self-contained components using containers and also provides abstractions for service discovery.…”
Section: A Applications and Workloadsmentioning
confidence: 99%
“…This includes studying the implications of various factors including the speed of bottleneck detection, VM startup time, resource/service discovery and load balancing as well as the granularity of resource allocations and duration of cooling down times. A self-scaling architecture would be mainly evaluated against an appropriate elasticity benchmark [6] using a set of reference applications (such as [8]). I plan to start from Mirage unikernels as an extreme case of lightweight execution units and compare to a representative spectrum of deployment options including VMs, containers, and other approaches to kernel specialization.…”
Section: Research Proposalmentioning
confidence: 99%