![]() |
|
以作者查詢圖書館館藏 、以作者查詢臺灣博碩士 、以作者查詢全國書目 、勘誤回報 、線上人數:45 、訪客IP:3.133.139.242
姓名 曾博彥(Po-Yen Tseng) 查詢紙本館藏 畢業系所 資訊工程學系 論文名稱 基於BFD 的路徑偵錯方法
(Path failure detection based on BFD)相關論文 檔案 [Endnote RIS 格式]
[Bibtex 格式]
[相關文章]
[文章引用]
[完整記錄]
[館藏目錄]
[檢視]
[下載]
- 本電子論文使用權限為同意立即開放。
- 已達開放權限電子全文僅授權使用者為學術研究之目的,進行個人非營利性質之檢索、閱讀、列印。
- 請遵守中華民國著作權法之相關規定,切勿任意重製、散佈、改作、轉貼、播送,以免觸法。
摘要(中) 近年來,負載平衡常被使用於改善資料中心的整體效能或是資料流
的完成時間。然而當發生斷線的時候,會導致TCP 封包的遺失,這種
情況在TCP 的重傳機制下會導致資料流的完成時間遽增。其中進行負
載平衡的交換器若是不能及時偵測得知斷線的訊息,就會增加TCP 封
包的遺失數量。在本篇論文中,相比於傳統的鏈路狀態路由協定以及
集中式管理網路狀態的工具,我們提出一個建構在BFD 上的偵測演算
法讓交換器能及時得知斷線的發生。藉由模擬軟體OMNET++,我們
去評估我們的方法與定期偵測在效能上的差異。摘要(英) Dynamic load balancing is a popular technique to improve overall throughput
or flow completion time in data center. Flow completion time represents
the time from a flow starting to transmit the first packet to the last packet
received. However, TCP retransmission protocol will incur longer flow completion
time when packet loss. And link failure is a common phenomenon
in data center. It will incur large packet loss if sender doing load balancing
is not able to timely acquire failure information of outgoing link. Compared
with recent link-state routing protocol and management tool, we propose an
algorithm based on BFD to enable network device doing load balancing to
timely know which outgoing path is unavailable. By simulation, we show
our technique can more fast detect the failure than pure periodical probing.
ii關鍵字(中) ★ 路徑偵錯 關鍵字(英) ★ BFD 論文目次 中文摘要 i
Abstract ii
Contents iii
List of Figures v
List of Tables vi
1 Introduction 1
2 Related work 3
2.1 Instantaneity 3
2.1.1 Routing protocol-based 3
2.1.2 Management tool-based 3
2.1.3 Keep-Alive mechanism 4
2.2 Problem statement 5
3 Design 8
3.1 Overview 8
3.1.1 Detection algorithm 10
3.1.2 Threshold on Inter Arrival Time 11
3.1.3 The detail of the proposed detection algorithm 12
3.2 Liveness Detection Mechanism 14
iii
3.2.1 Unidirectional link 15
3.2.2 Bidirectional link 16
4 Simulation 18
4.1 Simulation Environments 18
4.1.1 Topologies 18
4.1.2 Traffic patterns 19
4.1.3 Baseline parameters setting 19
4.2 Simulation Results 20
4.2.1 Set algorithm parameter (WAV G, WADJ and B) 20
4.2.2 Instantaneity 22
4.2.3 Cost of test packets 25
4.2.4 TCP Packet loss 25
4.2.5 The number of affected mice flow 27
5 Conclusion and Future Work 28
Bibliography 29參考文獻
[1] Mohammad Alizadeh, Albert Greenberg, David A Maltz, Jitendra Padhye, Parveen
Patel, Balaji Prabhakar, Sudipta Sengupta, and Murari Sridharan. Data center tcp
(dctcp). ACM SIGCOMM Computer Communication Review, 40(4):63–74, 2010.
[2] Theophilus Benson, Aditya Akella, and David A Maltz. Network traffic characteristics
of data centers in the wild. Proceedings of the 10th ACM SIGCOMM conference
on Internet measurement, pages 267–280, 2010.
[3] Marissa mayer at web 2.0., 2006. http://glinden.blogspot.ca/2006/
11/marissa-mayer-at-web-20.html.
[4] Amazon found every 100ms of latency cost them 1% in sales. http:
//blog.gigaspaces.com/amazon-foundevery-100ms-oflatency-
cost-them-1-in-sales/.
[5] Phillipa Gill, Navendu Jain, and Nachiappan Nagappan. Understanding network
failures in data centers: measurement, analysis, and implications. ACM SIGCOMM
Computer Communication Review, 41(4):350–361, 2011.
[6] Theophilus Benson, Ashok Anand, Aditya Akella, and Ming Zhang. Understanding
data center traffic characteristics. ACM SIGCOMM Computer Communication
Review, 40(1):92–99, 2010.
[7] Keqiang He, Junaid Khalid, Aaron Gember-Jacobson, Sourav Das, Chaithan
Prakash, Aditya Akella, Li Erran Li, and Marina Thottan. Measuring control plane
29
latency in sdn-enabled switches. Proceedings of the 1st ACM SIGCOMM Symposium
on Software Defined Networking Research, page 25, 2015.
[8] Snmp rfc 3416. https://www.rfc-editor.org/rfc/rfc3416.txt.
[9] Teemu Koponen, Martin Casado, Natasha Gude, Jeremy Stribling, Leon Poutievski,
Min Zhu, Rajiv Ramanathan, Yuichiro Iwata, Hiroaki Inoue, Takayuki Hama, et al.
Onix: A distributed control platform for large-scale production networks. OSDI,
10:1–6, 2010.
[10] Keepalive. https://en.wikipedia.org/wiki/Keepalive.
[11] Bfd rfc5880. https://tools.ietf.org/html/rfc5880.
[12] Danfeng Shan, Fengyuan Ren, Peng Cheng, and Ran Shu. Micro-burst in data centers:
Observations, implications, and applications. arXiv preprint arXiv:1604.07621,
2016.
[13] Microbursts, jitter and buffers. https://www.arista.com/assets/data/
pdf/TechBulletins/AristaMicrobursts.pdf.指導教授 張貴雲(Guey-Yun Chang) 審核日期 2017-8-7 推文 plurk
funp
live
udn
HD
myshare
netvibes
friend
youpush
delicious
baidu
網路書籤 Google bookmarks
del.icio.us
hemidemi
myshare