Analyzing Replacement Policies in List-Based Caches with Non-Uniform Access Costs

Casale, Giuliano

doi:10.1109/infocom.2018.8485894

Cited by 10 publications

(3 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we consider more large-scale settings, compared to Section 4.2, that include up to 128 functions. The function popularity is controlled by different values of the Zipf parameter that are common in cache based studies [Cas18]. We consider all combinations of number of functions (N ), Zipf parameter (η) and arrival rate (λ).…”

Section: Model Validationmentioning

confidence: 99%

Model-based Resource Management for Fine-grained Services

Gias

2022

SIGMETRICS Perform. Eval. Rev.

View full text Add to dashboard Cite

Brief Biography: Alim Ul Gias is currently a Research Associate at the Centre for Parallel Computing (CPC), University of Westminster. He completed his PhD from Imperial College London in 2022. Before starting his PhD, Alim was a lecturer at Institute of Information Technology (IIT), University of Dhaka (DU). He completed his bachelor's and master's program from the same institute. His current research focuses on different Quality of Service (QoS) aspects of cloud-native applications e.g., microservices. In particular, he aims to address the performance and resource management challenges concenrining the microservices architecture.

show abstract

Section: Model Validationmentioning

confidence: 99%

Model-based Resource Management for Fine-grained Services

Gias

2022

SIGMETRICS Perform. Eval. Rev.

View full text Add to dashboard Cite

show abstract

“…Here, we consider more large-scale settings, compared to Section II, that include up to 128 functions. The function popularity is controlled by different values of the Zipf parameter that are common in cache based studies [21]. We consider all combinations of number of functions (N ), Zipf parameter (η) and arrival rate (λ).…”

Section: Model Validationmentioning

confidence: 99%

COCOA: Cold Start Aware Capacity Planning for Function-as-a-Service Platforms

Gias

Casale

2020

2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)

Self Cite

View full text Add to dashboard Cite

Function-as-a-Service (FaaS) has become increasingly popular in the software industry due to the implied cost-savings in event-driven workloads and its synergy with DevOps. To size an on-premise FaaS platform, it is important to estimate the required CPU and memory capacity to serve the expected loads. Given the service-level agreements, it is however challenging to take the cold start issue into account during the sizing process. We have investigated the similarity of this problem with the hit rate improvement problem in Time to Live (TTL) caches and concluded that solutions for TTL cache, although potentially applicable, lead to over-provisioning in FaaS. Thus, we propose a novel approach, COCOA, to solve this issue. COCOA uses a queueing-based approach to assess the effect of cold starts on FaaS response times. It also considers different memory consumption values depending on whether the function is idle or in execution. Using an event-driven FaaS simulator, FaasSim, that we have developed, we show that COCOA can reduce overprovisioning by over 70% under some of the workloads we have considered, while satisfying the service-level agreements.

show abstract

“…We have considered more large-scale settings compared to Section II that includes up to 128 functions. We have also considered different popularity parameters which are common in cache based studies [22]. We have considered each of the combinations of number of functions (N ), Zipf parameters(η) and arrival rates (λ) from the table.…”

Section: Model Validationmentioning

confidence: 99%

COCOA: Cold Start Aware Capacity Planning for Function-as-a-Service Platforms

Gias¹,

Casale²

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Function-as-a-Service (FaaS) is increasingly popular in the software industry due to the implied cost-savings in eventdriven workloads and its synergy with DevOps. To size an onpremise FaaS platform, it is important to estimate the required CPU and memory capacity to serve the expected loads. Given the service-level agreements, it is however challenging to take the cold start issue into account during the sizing process. We have investigated the similarity of this problem with the hit rate improvement problem in TTL caches and concluded that solutions for TTL cache, although potentially applicable, lead to over-provisioning in FaaS. Thus, we propose a novel approach, COCOA, to solve this issue. COCOA uses a queueing-based approach to assess the effect of cold starts on FaaS response times. It also considers different memory consumption values depending on whether the function is idle or in execution. Using an event-driven FaaS simulator, FaasSim, we have developed, we show that COCOA can reduce over-provisioning by over 70% in some workloads, while satisfying the service-level agreements.

show abstract

Analyzing Replacement Policies in List-Based Caches with Non-Uniform Access Costs

Cited by 10 publications

References 30 publications

Model-based Resource Management for Fine-grained Services

Model-based Resource Management for Fine-grained Services

COCOA: Cold Start Aware Capacity Planning for Function-as-a-Service Platforms

COCOA: Cold Start Aware Capacity Planning for Function-as-a-Service Platforms

Contact Info

Product

Resources

About