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

Gias, A.U. and Casale, G. 2020. COCOA: Cold Start Aware Capacity Planning for Function-as-a-Service Platforms. 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems. Nice, France 17 - 18 Nov 2020 IEEE . https://doi.org/10.1109/mascots50786.2020.9285966

TitleCOCOA: Cold Start Aware Capacity Planning for Function-as-a-Service Platforms
AuthorsGias, A.U. and Casale, G.
TypeConference paper
Abstract

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.

Year2020
Conference28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems
PublisherIEEE
Publication dates
Published21 Dec 2020
JournalProceedings - IEEE Computer Society's Annual International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunications Systems, MASCOTS
ISSN1526-7539
Digital Object Identifier (DOI)https://doi.org/10.1109/mascots50786.2020.9285966
Web address (URL)http://www.scopus.com/inward/record.url?eid=2-s2.0-85098847952&partnerID=MN8TOARS

Related outputs

SampleHST: Efficient On-the-Fly Selection of Distributed Traces
Ul Gias, Alim, Gao, Yicheng, Sheldon, Matthew, Perusquía, José A., O’Brien, Owen and Casale, Giuliano 2023. SampleHST: Efficient On-the-Fly Selection of Distributed Traces. NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium. Miami, FL, USA 08 - 12 May 2023 IEEE . https://doi.org/10.1109/noms56928.2023.10154383

Model-based Resource Management for Fine-grained Services
Gias, Alim Ul 2023. Model-based Resource Management for Fine-grained Services. ACM SIGMETRICS Performance Evaluation Review. 50 (3), pp. 28-31. https://doi.org/10.1145/3579342.3579350

Quality-Aware DevOps Research: Where Do We Stand?
Ahmad Alnafessah, Gias, A.U., Runan Wang, Lulai Zhu, Giuliano Casale and Antonio Filieri 2021. Quality-Aware DevOps Research: Where Do We Stand? IEEE Access. 9, pp. 44476 - 44489. https://doi.org/10.1109/access.2021.3064867

Performance engineering for microservices and serverless applications: The RADON approach
Gias, A.U., Van Hoorn, A., Zhu, L., Casale, G., Düllmann, T.F. and Wurster, M. 2020. Performance engineering for microservices and serverless applications: The RADON approach. ICPE '20: Companion of the ACM/SPEC International Conference on Performance Engineering. Edmonton AB Canada 25 - 30 Apr 2020 ACM. https://doi.org/10.1145/3375555.3383120

ATOM: Model-driven autoscaling for microservices
Gias, A.U., Casale, G. and Woodside, M. 2019. ATOM: Model-driven autoscaling for microservices. 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS). Dallas, TX, USA 07 - 10 Jul 2019 IEEE . https://doi.org/10.1109/icdcs.2019.00197

Achieving better requirements to code traceability: which refactoring should be done first?
Faiz, F., Easmin, R. and Gias, A.U. 2016. Achieving better requirements to code traceability: which refactoring should be done first? 10th International Conference on the Quality of Information and Communications Technology, QUATIC 2016. Lisbon, Portugal 06 - 09 Sep 2016 IEEE . https://doi.org/10.1109/quatic.2016.012

Approximating social ties based on call logs: Whom should we prioritize?
Erfan, M., Gias, A.U., Sarwar, S.M. and Sakib, K. 2015. Approximating social ties based on call logs: Whom should we prioritize? 4th International Conference on Analysis of Images, Social Networks and Texts, AIST 2015. Yekaterinburg; Russian Federation 09 - 11 Apr 2015

A partial order assimilation approach for software requirements prioritization
Easmin, R., Gias, A.U. and Khaled, S.M. 2014. A partial order assimilation approach for software requirements prioritization. 2014 International Conference on Informatics, Electronics & Vision (ICIEV). Dhaka, Bangladesh 23 - 24 May 2014 IEEE . https://doi.org/10.1109/iciev.2014.6850776

A formal approach to verify software scalability requirements using set theory and Hoare triple
Gias, A.U., Tabassum, M.R., Ami, A.S., Imran, A., Ibrahim, M., Rahman, R. and Sakib, K. 2014. A formal approach to verify software scalability requirements using set theory and Hoare triple. 16th International Conference on Computer and Information Technology (ICCIT). Khulna, Bangladesh 08 - 10 Mar 2014 IEEE . https://doi.org/10.1109/iccitechn.2014.6997367

Optimizing software design migration from structured programming to object oriented paradigm
Siddik, S., Gias, A.U. and Khaled, S.M. 2014. Optimizing software design migration from structured programming to object oriented paradigm. 16th International Conference on Computer and Information Technology. Fijian Resort and Spa, Fiji 08 - 10 Mar 2014 https://doi.org/10.1109/iccitechn.2014.6997320

An attribute selection process for software defect prediction
Khan, J.I., Gias, A.U., Siddik, Md.S., Rahman, Md.H., Khaled, S.M. and Shoyaib, M. 2014. An attribute selection process for software defect prediction. 2014 International Conference on Informatics, Electronics & Vision (ICIEV). Dhaka, Bangladesh 23 - 24 May 2014 IEEE . https://doi.org/10.1109/iciev.2014.6850791

In silico analysis of salt responsive survival associated motifs in rice promoter
Easmin, R., Tabrejee, S., Rowshon, L., Gias, A.U., Chowdhuryy, M.M.K. and Khaled, S.M. 2014. In silico analysis of salt responsive survival associated motifs in rice promoter. The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014). Dhaka, Bangladesh 18 - 20 Dec 2014 IEEE . https://doi.org/10.1109/skima.2014.7083535

Approximating object based architecture for legacy software written in procedural languages using Variable Neighborhood Search
Selim, M., Siddik, M.S., Rahman, T., Gias, A.U. and Khaled, S.M. 2014. Approximating object based architecture for legacy software written in procedural languages using Variable Neighborhood Search. The 8th International Conference on Software, Knowledge, Information Management and Applications (SKIMA 2014). Dhaka, Bangladesh 18 - 20 Dec 2014 IEEE . https://doi.org/10.1109/skima.2014.7083558

An adaptive bayesian approach for URL selection to test performance of large scale web-based systems
Gias, A.U. and Sakib, K. 2014. An adaptive bayesian approach for URL selection to test performance of large scale web-based systems. 36th International Conference on Software Engineering. Hyderabad, India 31 May - 07 Jun 2014 IEEE . https://doi.org/10.1145/2591062.2591139

A direction of migrating procedural paradigm to object based architecture by forming cluster of functions using local search heuristics
Siddik, Md.S., Gias, A.U., Selim, Md., Khaled, S.M. and Sakib, K. 2014. A direction of migrating procedural paradigm to object based architecture by forming cluster of functions using local search heuristics. 2014 International Conference on Informatics, Electronics & Vision (ICIEV). Dhaka, Bangladesh 23 - 24 May 2014 IEEE . https://doi.org/10.1109/iciev.2014.6850767

Cloud-Niagara: A high availability and low overhead fault tolerance middleware for the cloud
Imran, A., Gias, A.U., Rahman, R., Seal, A., Rahman, T., Ishraque, F. and Sakib, K. 2014. Cloud-Niagara: A high availability and low overhead fault tolerance middleware for the cloud. 16th International Conference on Computer and Information Technology (ICCIT). Khulna, Bangladesh 08 - 10 Mar 2014 IEEE . https://doi.org/10.1109/iccitechn.2014.6997344

An empirical investigation of cost-resource optimization for running real-life applications in open source cloud
Imran, A., Gias, A.U. and Sakib, K. 2012. An empirical investigation of cost-resource optimization for running real-life applications in open source cloud. 2012 International Conference on High Performance Computing & Simulation (HPCS). Madrid, Spain 02 - 06 Jul 2012 IEEE . https://doi.org/10.1109/HPCSim.2012.6267002

Comparative study of statistical skin detection algorithms for sub-continental human images
Tabassum, M.R., Gias, A.U., Kamal, M.M., Islam, S., Muctadir, H.M., Ibrahim, M., Shakir, A.K., Imran, A., Islam, S., Rabbani, M.G., Khaled, S.M., Islam, M.S. and Begum, Z. 2010. Comparative study of statistical skin detection algorithms for sub-continental human images. Information Technology Journal. 9 (4), pp. 811-817. https://doi.org/10.3923/itj.2010.811.817

Combinatorial color space models for skin detection in sub-continental human images
Khaled, S.M., Saiful Islam, Md., Rabbani, Md.G., Tabassum, M.R., Gias, A.U., Kamal, Md.M., Muctadir, H.M., Shakir, A.K., Imran, A. and Islam, S. 2009. Combinatorial color space models for skin detection in sub-continental human images. First International Visual Informatics Conference, IVIC 2009. Kuala Lumpur, Malaysia 11 - 13 Nov 2009 Springer. https://doi.org/10.1007/978-3-642-05036-7_50

Permalink - https://westminsterresearch.westminster.ac.uk/item/vz3qx/cocoa-cold-start-aware-capacity-planning-for-function-as-a-service-platforms


Share this

Usage statistics

46 total views
0 total downloads
These values cover views and downloads from WestminsterResearch and are for the period from September 2nd 2018, when this repository was created.