簡易檢索 / 詳目顯示

研究生: 李沛旭
Fransiscus Asisi Bimo Adisatrio
論文名稱: 基於Openstack能源監控系統的實現與優化
Implementation and Optimization of Openstack-based Energy Monitoring Service
指導教授: 鄭瑞光
Ray-Guang Cheng
口試委員: 黃琴雅
Chin-Ya Huang
呂政修
Jenq-Shiou Leu
學位類別: 碩士
Master
系所名稱: 電資學院 - 電子工程系
Department of Electronic and Computer Engineering
論文出版年: 2019
畢業學年度: 107
語文別: 英文
論文頁數: 31
中文關鍵詞: Openstack虛擬化架構KVMHypervisor
外文關鍵詞: Openstack, KVM, Hypervisor, Virtual Infrastructure
相關次數: 點閱:238下載:0
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

開發校園監控系統有一定的局限性,其中之一就是資源有限。 要在單台計算機中部署監控系統,需要進行虛擬化以確保每個程序在不衝突的情況下運行。 作為開源私有雲之一,Openstack提供了部署虛擬機的簡便性,以支持其上的服務。 它管理計算資源池並支持構建隔離的虛擬化環境。 作為Web監控系統,Smart Meter可以從虛擬化中受益,使計算資源更加靈活,並根據需求進行定制。 要在單個計算機中部署Openstack,需要自定義部署以適應物理環境。 本文提供了使用虛擬化基礎架構使用Openstack部署的監控系統的證據性能。


Develop a monitoring system for campus has some requirement to fulfill, one of them is limited amount of resource. To deploy monitoring system in a single machine, need virtualization to ensure each program will run without conflict with each other. As one of open source private cloud, Openstack offers simplicity to deploy virtual machine to support services on top of it. It manages computational resource pool and enable to build isolated virtualize environment. As a web monitoring system, Smart Campus get benefits from virtualization to use computational resources more flexible and custom based on demand. To deploy Openstack in a single machine needs to customize the deployment to fits the physical environment. This paper provides the evidence performance on monitoring system deployed using Openstack that using virtual infrastructure. The results show that OpenStack over dedicated hardware performs much better than OpenStack over virtual infrastructure.

論文摘要 4 Abstract 6 Table of Contents 7 List of Fig. s 8 List of Tables 9 Chapter 1 Introduction 10 Chapter 2 System Architecture 13 Chapter 3 Implementation 15 Chapter 4 Optimization 20 3-1 Disable Kernel same-page Memory (KSM) 20 3-2 CPU Pinning 21 Chapter 5 Experiment Results 24 Chapter 6 Conclusion 30 References 31

[1]. Thingworx Platform Product Brief, Available: https://www.ptc.com/en/resources/iot/product-brief/Thingworx-platform
[2]. Openstack, Available: https://en.wikipedia.org/wiki/OpenStack
[3]. Mongo database, Available: https://docs.mongodb.com/
[4]. G. Chen, A. Gillen, “KVM for Server Virtualization: An open Source Solution Comes of Age,” IDC. 2011.
[5]. "KSM tries again". Available: lwn.net.kernel.org.
[6]. Welcome to NGINX Wiki!, Available: https://www.nginx.com/resources/wiki/
[7]. A. Podzimek ; L. Bulej ; L. Y. Chen ; W. Binder ; P. Tuma “Analyzing the Impact of CPU Pinning and Partial CPU Loads on Performance and Energy Efficiency,” 2015 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing
[8]. R. Nasim and A. J. Kassler, "Deploying OpenStack: Virtual Infrastructure or Dedicated Hardware," 2014 IEEE 38th International Computer Software and Applications Conference Workshops, Vasteras, 2014, pp. 84-89.
[9]. Arcangeli, Andrea, Izik Eidus, and Chris Wright. "Increasing memory density by using KSM." In Proceedings of the linux symposium, pp. 19-28. 2009.
[10]. A. Kivity, Y. amay, D. Laor, U. Lublin, A. Liguory. “kvm: the Linux Virtual Machine Monitor,” 2007 Linux Symposium. 2007
[11]. H. Lee “Virtualization Basics: Understanding Techniques and Fundamentals”
[12]. M. Eder, "Hypervisor-vs. container-based virtualization", Proceedings of the seminars “Future Internet” (FI) and “Innovative Internet Technologies and Mobile Communications” (IITM), July 2016
[13]. J. Z Kusek, R. C. Rist, “Ten Steps to a Results-Based Monitoring and Evaluation System, Washington, DC: The World Bank, 2004, pp. 108–110.
[14]. A . Vaibhav , K. Devanjal, M. Kamelia., “Log-Based Cloud Monitoring System for OpenStack”, 2018 IEEE Fourth International Conference on Big Data Computing Service and Applications

QR CODE