Abstract
Edge clouds have become a de-facto paradigm to deliver low and stable networks to delay-critical applications such as Web services and AR/VR. A unique form of edge clouds is those crowdsourced from third parties, e.g., idle PCs or workstations. Such crowdsourced edge platforms can better sink computations closer to users, reduce the purchase cost, and eliminates the carbon generated during manufacturing. Yet, they also face the challenge of out-of-control hardware, e.g., a server dropping in/out anytime. In this paper, we perform the first-of-its-kind measurement of Quality of Service (QoS) for a large-scale crowdsourced edge platform, which covers over 10,000 edge servers, 100,000 users and 10,000,000 user requests. The measurement takes a holistic QoS view: First, we look at how much hardware resources are provided by edge servers, how much time they are available for service deployment, how geographic distance affects network performance, and what are the major abnormal behaviors. Second, we analyze the factors affecting service stability and quantify the resource utilization pattern of containerized services hosted on those edge servers. Third, we investigate the spatial and temporal features of user requests handled by the platform. Many useful and somehow surprising findings are obtained through the above measurements. We also derive insightful implications that could help edge platforms and edge applications to better deliver their services to users.
Similar content being viewed by others
Data Availibility
Not applicable.
Code Availability
Codes related to the model generator in this research are available.
Notes
Abbreviated as edge platform in the following.
PPIO Edge Cloud, Paiou Cloud Computing (Shanghai) Co., Ltd., https://www.ppio.cn.
ESMG focuses on providing a modelling approach that approximates real business application scenarios rather than an optimal deployment solution for edge servers.
Due to the limited amount of data for ISP-D, the credibility of its performance analysis is low.
Since our dataset does not contain the actual routing data of the transmission, we calculate the straight-line distance by computing the geographic coordinates as an approximate substitute.
The numbers here and below correspond to the indexes in Figure 12.
References
Lv, Z.: Virtual reality in the context of internet of things. Neural Comput. Appl. 32(13), 9593–9602 (2020)
Ren, P., Liu, L., Qiao, X., Chen, J.: Distributed edge system orchestration for Web-based mobile augmented reality services. IEEE Trans. Serv, Comput (2022)
Khan, M.A., Sayed, H.E., Malik, S., Zia, T., Khan, J., Alkaabi, N., Ignatious, H.: Level-5 autonomous driving—are we there yet? a review of research literature. ACM Comput. Surv. 55(2) (2022)
Shen, S., Ren, Y., Ju, Y., Wang, X., Wang, W., Leung, V.C.: Edgematrix: A resource-redefined scheduling framework for sla-guaranteed multi-tier edge-cloud computing systems. IEEE J. Sel, Areas Commun (2022)
Liu, Z., Song, J., Qiu, C., Wang, X., Chen, X., He, Q., Sheng, H.: Hastening stream offloading of inference via multi-exit dnns in mobile edge computing. IEEE Trans. Mob, Comput (2022)
Meulen, R., et al.: What edge computing means for infrastructure and operations leaders. Smarter with Gartner (2018)
Azure MEC (2020). https://docs.microsoft.com/en-us/azure/private-multi-access-edge-compute-mec/overview. Accessed 1 Apr 2022
AWS Local Zones (2020). https://aws.amazon.com/cn/about-aws/global-infrastructure/localzones/. Accessed 1 Apr 2022
How an IoT Edge device can be used as a gateway (2022). https://learn.microsoft.com/en-us/azure/iot-edge/iot-edge-as-gateway?view=iotedge-1.4. Accessed 1 Apr 2022
Analytics on the edge using IBM Cloud Pak for Data (2020). https://www.ibm.com/blogs/journey-to-ai/2020/05/analytics-on-the-edge-using-ibm-cloud-pak-for-data/?_ga=2.207148885.771206213.1610462457-287655082.1610462457. Accessed 1 Apr 2022
Ercan, M., Malmodin, J., Bergmark, P., Kimfalk, E., Nilsson, E.: Life cycle assessment of a smartphone. In: ICT for Sustainability 2016, pp. 124–133 (2016). Atlantis Press
Dream, build, and transform with Google Cloud (2011). https://cloud.google.com/. Accessed 1 Apr 2022
Amazon Web Services (2004). https://aws.amazon.com/. Accessed 1 Apr 2022
Cidon, I., Khamisy, A., Sidi, M.: Analysis of packet loss processes in high-speed networks. IEEE Trans. Inf. Theory 39(1), 98–108 (1993)
Docker overview (2021). https://docs.docker.com/get-started/overview/. Accessed 1 Apr 2022
Kubernetes Documentation (2022). https://kubernetes.io/docs/home/. Accessed 1 Apr 2022
Hedhli, A., Mezni, H.: A survey of service placement in cloud environments. J. Grid Comput. 19(3), 1–32 (2021)
Chang, W., Wang, P.: Write-aware replica placement for cloud computing. IEEE J. Sel. Areas Commun. 37(3), 656–667 (2019)
Slimani, S., Hamrouni, T., Ben Charrada, F.: Service-oriented replication strategies for improving quality-of-service in cloud computing: a survey. Clust. Comput. 24(1), 361–392 (2021)
Benesty, J., Chen, J., Huang, Y., Cohen, I.: Pearson correlation coefficient. In: Noise Reduction in Speech Processing, pp. 1–4. Springer
Abdi, H.: Multiple correlation coefficient. Encyclopedia of measurement and statistics 648, 651 (2007)
Gallager, R.: Poisson processes. In: Discrete Stochastic Processes, pp. 31–55. Springer
Sadeghi, M., Barati, M.: Performance analysis of poisson and exponential distribution queuing model in local area network. In: 2012 International Conference on Computer and Communication Engineering (ICCCE), pp. 499–503 (2012). https://doi.org/10.1109/ICCCE.2012.6271237
Tyagi, R.R., Aurzada, F., Lee, K.-D., Reisslein, M.: Connection establishment in lte-a networks: Justification of poisson process modeling. IEEE Systems Journal 11(4), 2383–2394 (2017). https://doi.org/10.1109/JSYST.2014.2387371
Hagihara, S., Fushihara, Y., Shimakawa, M., Tomoishi, M., Yonezaki, N.: Web server access trend analysis based on the poisson distribution. In: Proceedings of the 6th International Conference on Software and Computer Applications, pp. 256–261 (2017)
Rajaram, S., Graepel, T., Herbrich, R.: Poisson-networks: A model for structured poisson processes. In: International Workshop on Artificial Intelligence and Statistics, pp. 277–284 (2005). PMLR
Narayanan, A., Zhang, X., Zhu, R., Hassan, A., Jin, S., Zhu, X., Zhang, X., Rybkin, D., et al.: A variegated look at 5g in the wild: performance, power, and qoe implications. In: ACM SIGCOMM, pp. 610–625 (2021)
Wang, Z., Li, Z., Liu, G., Chen, Y., Wu, Q., Cheng, G.: Examination of wan traffic characteristics in a large-scale data center network. In: ACM IMC, pp. 1–14 (2021)
Schlinker, B., Cunha, I., Chiu, Y., Sundaresan, S., Katz-Bassett, E.: Internet performance from facebook’s edge. In: ACM IMC, pp. 179–194 (2019)
Mok, R., Zou, H., Yang, R., Koch, T., Katz-Bassett, E., Claffy, K.: Measuring the network performance of google cloud platform. In: ACM IMC, pp. 54–61 (2021)
Johnson, M., Liang, J., Lin, M., Singanamalla, S., Heimerl, K.: Whale watching in inland indonesia: Analyzing a small, remote, internet-based community cellular network. In: WWW, pp. 1483–1494 (2021)
Xu, E., Zheng, M., Qin, F., Xu, Y., Wu, J.: Lessons and actions: What we learned from 10k SSD-Related storage system failures. In: USENIX ATC, pp. 961–976 (2019)
Fida, M., Acar, E., Elmokashfi, A.: Multiway reliability analysis of mobile broadband networks. In: ACM IMC, pp. 358–364 (2019)
Xu, M., Fu, Z., Ma, X., Zhang, L., Li, Y., Qian, F., Wang, S., Li, K., Yang, J., Liu, X.: From cloud to edge: a first look at public edge platforms. In: ACM IMC, pp. 37–53 (2021)
Rafique, W., Qi, L., Yaqoob, I., Imran, M., Rasool, R., Dou, W.: Complementing iot services through software defined networking and edge computing: A comprehensive survey. IEEE Commun. Surv. Tutor. 22(3), 1761–1804 (2020)
Zhang, Y., Liu, J., Wang, C., Wei, H.: Decomposable intelligence on cloud-edge iot framework for live video analytics. IEEE Internet Things J. 7(9), 8860–8873 (2020)
Jiang, X., Yu, F., Song, T.n., Leung, V.: A survey on multi-access edge computing applied to video streaming: some research issues and challenges. IEEE Commun. Surv. Tutor. 23(2), 871–903 (2021)
Mu, P., Zheng, J., Luan, T., Zhu, L., Dong, M., Su, Z.: Amis: Edge computing based adaptive mobile video streaming. In: IEEE INFOCOM, pp. 1–10 (2021). IEEE
Gao, Y., Zhang, C., Xie, Z., Qi, Z., Zhou, J.: Cost-efficient and quality of experience-aware player request scheduling and rendering server allocation for edge computing assisted multiplayer cloud gaming. IEEE Internet Things J. (2021)
KubeEdge: Kubernetes native edge computing framework (project under CNCF) (2019). https://github.com/kubeedge/kubeedge. Accessed 1 Apr 2022
OpenYurt: Extending your native kubernetes to edge (2020). https://github.com/alibaba/openyurt. Accessed 1 Apr 2022
Baetyl: Extend cloud computing, data and service seamlessly to edge devices (2019). https://github.com/baetyl/baetyl. Accessed 1 Apr 2022
Cortez, E., Bonde, A., Muzio, A., Russinovich, M., Fontoura, M., Bianchini, R.: Resource central: Understanding and predicting workloads for improved resource management in large cloud platforms. In: Symposium on Operating Systems Principles, pp. 153–167 (2017)
Borg cluster traces (2019). https://github.com/google/cluster-data. Accessed 1 Apr 2022
Alibaba Cluster Trace (2020). https://github.com/alibaba/clusterdata. Accessed 1 Apr 2022
Funding
This research was supported by the National Key R &D Program of China (Grant 2021ZD0113001), the Guangdong Pearl River Talent Recruitment Program (Grant 2019ZT08X603), the Guangdong Pearl River Talent Plan (Grant 2019JC01X235), Shenzhen Science and Technology Innovation Commission (Grant R2020A045), the Canadian Natural Sciences and Engineering Research Council (Grant RGPIN-2019-06348), the National Science Foundation of China (Grant 62072332), the China NSFC (Youth) (Grant 62002260), the China Postdoctoral Science Foundation (Grant 2020M670654), and the Tianjin Xinchuang Haihe Lab (Grant 22HHXCJC00002).
Author information
Authors and Affiliations
Contributions
Yicheng Feng and Shihao Shen were primarily responsible for the writing of the paper, conducting experimental tests, and plotting experimental graphs. Mengwei Xu, Cheng Zhang, Xin Wang, Xiaofei Wang, Wenyu Wang and Victor C.M. Leung provided guidance on the design and writing of the paper. All authors reviewed the manuscript.
Corresponding author
Ethics declarations
Ethical approval
This article does not contain any studies involving human participants and/or animals by any of the authors.
Competing interests
The authors declare that they have no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Feng, Y., Shen, S., Xu, M. et al. A large-scale holistic measurement of crowdsourced edge cloud platform. World Wide Web 26, 3561–3584 (2023). https://doi.org/10.1007/s11280-023-01201-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11280-023-01201-y