在資料中心的小流量加速及大流量降速負載平衡策略;Fast Mice And Slow Elephant Load Balancing Strategy For Datacenter Network

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/81193

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/81193

Title:	在資料中心的小流量加速及大流量降速負載平衡策略;Fast Mice And Slow Elephant Load Balancing Strategy For Datacenter Network
Authors:	黃上銘;Huang, Shang-Ming
Contributors:	資訊工程學系
Keywords:	資料中心;資料中心負載平衡;datacenter;datacenter load balancing
Date:	2019-07-26
Issue Date:	2019-09-03 15:38:59 (UTC+8)
Publisher:	國立中央大學
Abstract:	在現在的資料中心有相當大比例的流量是小流量的資料傳遞。在許多資料中心當中大流量和小流量的資料傳遞有著相同的權重，但即使小流量完成資料傳輸的時間較短，相同的權重仍會讓小流量的資料傳輸花費較多時間來傳遞單一封包，也因此相同權重的負載平衡的策略會不公平的對待小流量的資料傳遞。在我們的方法當中透過觀察 Flowlet 大小的特性代表著傳輸路線的壅塞情形及流量大小，來鎖定部分大流量的資料傳遞，並且透過負載平衡策略的改變，將占用不壅塞路徑的大流量的資料傳遞改由較為壅塞的路徑傳輸，保留更多的資源給小流量的資料傳遞，同時部過度剝削大流量資掉傳遞的資源，來改善大流量和小流量資料傳遞之間的不公平，並且進一步的提升小流量資料傳遞的效能;In modern datacenter network, mice flows are big part in overall traffic. Most load balancing algorithm give the same priority to mice flow and elephant flow while making load balance decision. Even mice flow have small flow completion time. Such equal priority strategy let mice flow take more time to transmit a single packet than elephant flow. In this paper, we propose a fast mice and slow elephant load balancing algorithm which can first locate elephant flow overuse uncongested route by factors affect flowlet size and elephant flows are abusing uncongested path are routed to congested path to improve the imbalance between mice flow and elephant flow and further increase the throughput of mice flow.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	91	View/Open

社群 sharing

Loading...