請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/19184
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 劉邦鋒 | |
dc.contributor.author | You-Long Tsai | en |
dc.contributor.author | 蔡佑隆 | zh_TW |
dc.date.accessioned | 2021-06-08T01:47:56Z | - |
dc.date.copyright | 2016-10-14 | |
dc.date.issued | 2016 | |
dc.date.submitted | 2016-08-03 | |
dc.identifier.citation | [1] The internet traffic archive. http://ita.ee.lbl.gov/.
[2] Michael Armbrust, O Fox, Rean Griffith, Anthony D Joseph, Y Katz, Andy Konwinski, Gunho Lee, David Patterson, Ariel Rabkin, Ion Stoica, et al. M.: Above the clouds: a berkeley view of cloud computing. 2009. [3] Raymond Keith Clark. Scheduling dependent real-time activities. PhD thesis, Carnegie Mellon University, 1990. [4] Tharam Dillon, Chen Wu, and Elizabeth Chang. Cloud computing: issues and challenges. In Advanced Information Networking and Applications (AINA), 2010 24th IEEE International Conference on, pages 27–33. Ieee, 2010. [5] Matangini Chattopadhyay Diptangshu Pandit, Samiran Chattopadhyay and Nabendu Chaki. Resource allocation in cloud using simulated annealing. In Applications and Innovations in Mobile Computing (AIMoC), pages 21–27. IEEE, 2014. [6] Docker. https://www.docker.com/. [7] Saurabh Kumar Garg, Srinivasa K Gopalaiyengar, and Rajkumar Buyya. Sla-based resource provisioning for heterogeneous workloads in a virtualized cloud datacenter. In Algorithms and Architectures for Parallel Processing, pages 371–384. Springer, 2011. [8] Martin T Hagan, Howard B Demuth, Mark H Beale, et al. Neural network design. Pws Pub. Boston, 1996. [9] Heapster. https://github.com/kubernetes/heapster. [10] JBoss. http://www.jboss.org/. [11] JMeter. http://jmeter.apache.org/. [12] Kubernetes. http://kubernetes.io/. [13] Jian Li, Sen Su, Xiang Cheng, Meina Song, Liyu Ma, and Jie Wang. Cost-efficient coordinated scheduling for leasing cloud resources on hybrid workloads. Parallel Computing, 44:1–17, 2015. [14] Shuo Liu, Gang Quan, and Shangping Ren. On-line scheduling of real-time services for cloud computing. In Services (SERVICES-1), 2010 6th World Congress on, pages 459–464. IEEE, 2010. [15] Openshift. https://www.openshift.com/. [16] Kubernetes Scheduler. http://kubernetes.io/docs/user-guide/ compute-resources/#how-pods-with-resource-requests arescheduled. [17] Openshift Scheduler. https://docs.openshift.com/enterprise/ 3.0/admin_guide/scheduler.html#available-priorityfunctions. [18] Docker Swarm Scheduler Strategies. https://docs.docker.com/swarm/scheduler/strategy/. [19] TicketMonster. http://www.ticketmonster.com/. [20] Abhishek Verma, Luis Pedrosa, Madhukar Korupolu, David Oppenheimer, Eric Tune, and John Wilkes. Large-scale cluster management at google with borg. In Proceedings of the Tenth European Conference on Computer Systems, page 18. ACM, 2015. [21] Linlin Wu, Saurabh Kumar Garg, and Rajkumar Buyya. Sla-based resource allocation for software as a service provider (saas) in cloud computing environments. In Cluster, Cloud and Grid Computing (CCGrid), 2011 11th IEEE/ACM International Symposium on, pages 195–204. IEEE, 2011. [22] Chee Shin Yeo and Rajkumar Buyya. Service level agreement based allocation of cluster resources: Handling penalty to enhance utility. In Cluster Computing, 2005. IEEE International, pages 1–10. IEEE, 2005. [23] Yue Yu, Shangping Ren, Nianen Chen, and Xing Wang. Profit and penalty aware (pp-aware) scheduling for tasks with variable task execution time. In Proceedings of the 2010 ACM Symposium on Applied Computing, pages 334–339. ACM, 2010. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/19184 | - |
dc.description.abstract | 在這篇論文中,我們提出了決定應用程式的適合的容器大小以減少容器成本,還有根據資源用量及服務層級協義動態調整容器數量的一個雲端資源管理的架構。我們提出了一個考慮開啟/關閉/執行/調整容器的成本模型,跟一個根據資源需求變化動態調整執行容器的數量以最小化總成本的動態規劃演算法。我們也提出了一個跟動態規劃一樣有效調整容器數量但需要更少計算時間的貪心方法。我們的實驗結果証實了貪心方法是有效而且有效率的。我們也證實了前一天的一個小時的好的容器大小會是今天同一個小時的容器大小的很好的近似。也就是說,根據我們得到的歷史蹤跡,最好的容器大小展現了時間相似。 | zh_TW |
dc.description.abstract | In this paper we present a cloud resource management framework that determines a proper container size for each application in order to reduce the container cost, then dynamically adjusts the number of containers based on resource usage and application service level agreement. We propose a cost model that consider starting/stopping/running/adjusting containers, and propose a dynamic programming algorithm to adjust the number of running containers so as to minimize the total cost when the resource requirement changes dynamically. We also propose a greedy method that effectively adjusts the number of containers as the dynamic programming does, but requires much less computation time. Our experiment confirms that the greedy method is both effective and efficient. We also confirm that the a good container size for the same hour yesterday is a good approximation for the same hour today. That is, the number of best container size exhibits temporal similarity, according to the historical trace we obtained. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T01:47:56Z (GMT). No. of bitstreams: 1 ntu-105-R03922106-1.pdf: 1328721 bytes, checksum: 3452269bd7a3dedaf8f2ceb82aab6ddc (MD5) Previous issue date: 2016 | en |
dc.description.tableofcontents | 口試委員會審定書 i
Acknowledgement ii Chinese Abstract iii Abstract iv Contents v List of Figures vii 1 Introduction 1 2 Related Work 4 3 System Architecture 6 3.1 Openshift . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 3.1.1 Docker . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.1.2 Kubernetes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.2 Monitor . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 3.3 Container Manager . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.3.1 Container Number . . . . . . . . . . . . . . . . . . . . . . . . . 9 3.3.2 Container Size . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 3.4 Scheduler . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 4 Container Optimization Problem 12 4.1 Problem Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12 4.2 Dynamic Programming . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 4.3 Greedy Method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 4.4 Container Pricing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 5 Experiment 18 5.1 Benchmark . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 5.2 Workload Traces . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 5.3 The Greedy v.s. Dynamic Programming . . . . . . . . . . . . . . . . . . 19 5.4 Temporal Similarity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 6 Conclusion 23 Bibliography 24 | |
dc.language.iso | en | |
dc.title | 基於服務層級協議及應用效能之容器大小及數量調整系統 | zh_TW |
dc.title | Container Number and Size Management System Based on SLA
and Application Performance | en |
dc.type | Thesis | |
dc.date.schoolyear | 104-2 | |
dc.description.degree | 碩士 | |
dc.contributor.coadvisor | 吳真貞 | |
dc.contributor.oralexamcommittee | 洪鼎詠 | |
dc.subject.keyword | 雲端計算,客戶端- 服務器系統,容器,服務層級協議, | zh_TW |
dc.subject.keyword | Cloud computing,Client-sever systems,Container,Service level agreement, | en |
dc.relation.page | 26 | |
dc.identifier.doi | 10.6342/NTU201601866 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2016-08-04 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
顯示於系所單位: | 資訊工程學系 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-105-1.pdf 目前未授權公開取用 | 1.3 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。