Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/18374
Title: | 異質性伺服器叢集下之工作分配與排程 Job Dispatching and Scheduling under Heterogeneous Clusters |
Authors: | Ting-Chou Lin 林廷舟 |
Advisor: | 劉邦鋒 |
Keyword: | 工作排程,異質性伺服器叢集,資源分配, Job/Task Scheduling,Heterogeneous Clusters,Resource Allocation, |
Publication Year : | 2014 |
Degree: | 碩士 |
Abstract: | 越來越多的企業與機構開始建造自己的資料中心作為私有雲
(private cloud)使用。在這些資料中心裡,機器的性質與能力會因為新 採購與被淘汰而有所不同,但由於採購通常只會在年度或半年度時進 行,在這中間,機器的數量是固定的。在這樣的異質性環境下,根據 不同工作(job)的資源需求與特性去進行排程,使得它們可以盡量在 其要求的時間限制前完成是很重要的。 在本論文中,我們提出了一個雲端資源管理框架以動態的調配在系 統中各個工作所能夠使用的運算節點(node)數量,進而達到有效率 整個系統的運算資源。 Many enterprises or institutes are building private clouds by establishing their own data center. In such data centers, the physical machines can be different due to annual upgrades, but the amount of machine are fixed for most of the time. In such heterogeneous environment, scheduling jobs with different resource requirements and characteristic in order to meet different timing constraints is important. In this paper, we proposed a cloud resource management framework to dynamically adjust the number of computation nodes for every job in the system. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/18374 |
Fulltext Rights: | 未授權 |
Appears in Collections: | 資訊網路與多媒體研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-103-1.pdf Restricted Access | 996.43 kB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.