本文選題：云計算 + TCP�。� 參考：《廣西師范大學(xué)》2013年碩士論文

【摘要】：隨著云計算技術(shù)的不斷成熟,數(shù)據(jù)中心也隨之發(fā)展�，F(xiàn)在數(shù)據(jù)中心已不再只是一個簡單的服務(wù)器統(tǒng)一托管、維護(hù)的場所,它已逐漸演變成了一個集大數(shù)據(jù)量運(yùn)算和存儲為一體的高性能計算機(jī)的集中地。數(shù)據(jù)被存儲在大型的數(shù)據(jù)中心,通過廣域網(wǎng)存取,Google, Yahoo, IBM, Microsoft, Amazon.com等都在這類數(shù)據(jù)中心提供存、取、處理數(shù)據(jù)服務(wù)。云計算的廣泛應(yīng)用和產(chǎn)業(yè)發(fā)展也極大的推動數(shù)據(jù)中心的發(fā)展。 現(xiàn)代數(shù)據(jù)中心網(wǎng)絡(luò)獨(dú)特的工作負(fù)載、速度和規(guī)模,違背了TCP最初依據(jù)的一些基本假設(shè)。因此,在高帶寬、低延遲的數(shù)據(jù)中心環(huán)境中使用TCP協(xié)議時,出現(xiàn)了‘'Incast'問題。在數(shù)據(jù)中心網(wǎng)絡(luò)中,為了提高性能和可靠性,數(shù)據(jù)分散存儲在多臺服務(wù)器上。在多對一通信模式中,多個發(fā)送端通過以太網(wǎng)交換機(jī)與一個接收端通信,接收端向多個發(fā)送端請求數(shù)據(jù),發(fā)送端響應(yīng)請求并向接收端發(fā)送數(shù)據(jù),如果發(fā)送的數(shù)據(jù)包超過交換機(jī)的緩沖能力,將導(dǎo)致大量的數(shù)據(jù)包丟失甚至引發(fā)超時,從而使得傳輸鏈路帶寬在超時周期處于空閑狀態(tài)。在高帶寬、低延時的數(shù)據(jù)中心網(wǎng)絡(luò)中,鏈路帶寬不能被充分利用將導(dǎo)致吞吐量嚴(yán)重下降。因此,如何從根本上以低開銷解決該問題,是一個具有實(shí)際應(yīng)用價值的重要課題。為了能夠以低開銷徹底解決該問題,本文在分析現(xiàn)有的TCP Incast解決方案和TCP Incast分析模型的基礎(chǔ)上,圍繞TCP Incast吞吐量崩潰和鏈路層上使用量化擁塞通知(Quantized Congestion Notification, QCN)協(xié)議中數(shù)據(jù)流共享瓶頸鏈路存在的不公平性等問題展開了深入研究。具體的研究內(nèi)容以及取得的成果如下： (1)介紹TCP Incast產(chǎn)生的背景和數(shù)據(jù)中心的一些典型應(yīng)用及其存在的問題,分析TCP Incast產(chǎn)生原因并詳細(xì)闡述了TCP Incast的研究現(xiàn)狀,對現(xiàn)有的應(yīng)用層、傳輸層和鏈路層上方案進(jìn)行深入分析,并在開銷和實(shí)用性上比較其優(yōu)缺點(diǎn)。應(yīng)用層和傳輸層的解決方案一定程度上可以緩解TCP Incast,但不能從根本上解決TCP Incast問題,鏈路層上的解決方案可以從根本上解決TCP Incast,但是在實(shí)際環(huán)境中性能很差。 (2)深入分析了現(xiàn)存的三個典型的TCP Incast模型,即基于管道的TCP Incast模型、基于數(shù)據(jù)塊的TCP Incast模型和基于輪次的TCP Incast模型。分析三種模型的相同點(diǎn)和不同點(diǎn),并從交換隊列管理機(jī)制、TCP版本、TCP擁塞控制階段、實(shí)現(xiàn)復(fù)雜度和驗證方式等多個方面比較其性能的優(yōu)劣性。通過實(shí)驗驗證這三個模型,基于輪次的TCP Incast模型不僅提出了引起TCP Incast的根本原因,而且精確反映TCP Incast吞吐量的變化趨勢,對于研究TCP Incast問題具有重要的指導(dǎo)意義。 (3)著重研究了鏈路層端到端量化擁塞通知算法(Quantized Congestion Notification, QCN),針對數(shù)據(jù)中心網(wǎng)絡(luò)中的鏈路層量化擁塞通知算法QCN數(shù)據(jù)流之間存在不公平性問題,提出了一種增強(qiáng)的量化擁塞通知算法(Ehanced Quantized Congestion Notification, EQCN)。該算法對QCN的交換機(jī)和發(fā)送端同時進(jìn)行改進(jìn),交換機(jī)端按照一定的概率對收到的數(shù)據(jù)包進(jìn)行采樣,當(dāng)一個被采樣數(shù)據(jù)包到達(dá)時,EQCN交換機(jī)檢測當(dāng)前緩沖區(qū)隊列長度并計算一個反應(yīng)當(dāng)前擁塞程度的反饋值,當(dāng)發(fā)送擁塞時,交換機(jī)生成一個攜帶該反饋值的擁塞反饋信息,并向所有超過共享鏈路平均帶寬的數(shù)據(jù)流的源端發(fā)送該擁塞反饋信息。發(fā)送端的速率限制器采用動態(tài)門限,使速率增加階段的門限值與當(dāng)前發(fā)送速率成正比,速率高的數(shù)據(jù)流,門限值也高,EQCN算法對交換機(jī)和發(fā)送端的改進(jìn)共同提高了數(shù)據(jù)流共享瓶頸鏈路的公平性。最后,通過實(shí)驗進(jìn)行驗證,實(shí)驗結(jié)果表明該算法顯著提高了TCP Incast吞吐量。 (4)使用NS-2網(wǎng)絡(luò)仿真工具搭建仿真平臺,對QCN數(shù)據(jù)流之間的不公平和提出的EQCN算法進(jìn)行仿真模擬,實(shí)驗結(jié)果表明QCN數(shù)據(jù)流之間存在不公平性,本文提出的EQCN算法能夠提高數(shù)據(jù)流之間的公平性,顯著提高TCP Incast吞吐量。
[Abstract]:With the growing maturity of cloud computing technology, the data center has also developed. Now the data center is no longer just a simple server unified hosting, maintenance site, it has gradually evolved into a collection of high performance computers with large data operations and storage. Data is stored in large data centers. Over the wide area network access, Google, Yahoo, IBM, Microsoft, Amazon.com, etc. all provide, take, and process data services in this kind of data center. The wide application of cloud computing and the development of industry also greatly promote the development of the data center.
The unique workload, speed and size of the modern data center network violates some basic assumptions originally based on TCP. Therefore, when the TCP protocol is used in a high bandwidth, low delay data center environment, a ''Incast' problem 'appears. In the data center network, data are stored in multiple servers for high performance and reliability. In a multi to one communication mode, multiple sending ends communicate with a receiver through an Ethernet switch, the receiver requests data to multiple sender, sends the response request and sends data to the receiver. If the packet is over the buffer capacity of the switch, a large number of data packets will be lost or even timeout is caused. The transmission link bandwidth is idle in the timeout period. In a high bandwidth, low delay data center network, the link bandwidth can not be fully utilized will lead to a serious decline in throughput. Therefore, how to solve the problem at a low cost fundamentally is an important subject of practical value. To solve this problem, based on the analysis of existing TCP Incast solutions and TCP Incast analysis models, this paper focuses on the problems of the TCP Incast throughput crash and the unfairness of the existing bottleneck links in the data stream sharing bottleneck in the Quantized Congestion Notification (QCN) protocol (Quantized Congestion Notification, QCN) protocol on the link layer. The specific research contents and achievements are as follows:
(1) introduce the background of TCP Incast and some typical applications of data center and the existing problems, analyze the causes of TCP Incast and elaborate the research status of TCP Incast, analyze the existing application layer, transmission layer and link layer, and compare their advantages and disadvantages in overhead and practicability. Application layer and transmission Layer solutions can alleviate TCP Incast to a certain extent, but can not fundamentally solve the TCP Incast problem. The solution on the link layer can fundamentally solve TCP Incast, but the performance is very poor in the actual environment.
(2) in-depth analysis of three existing typical TCP Incast models, the TCP Incast model based on pipeline, the TCP Incast model based on the data block and the TCP Incast model based on the rotation, analyze the similarities and differences of the three models, and realize the complexity and the verification mode from the exchange queue management mechanism, TCP edition, TCP congestion control stage. The performance is compared with other aspects. Through experiments, the three models are verified. The TCP Incast model based on the rotation not only puts forward the fundamental cause of the TCP Incast, but also accurately reflects the change trend of TCP Incast throughput, which is of great guiding significance for the study of the TCP Incast problem.
(3) focus on the link layer end to end congestion notification algorithm (Quantized Congestion Notification, QCN). For the link layer quantization congestion notification algorithm in the data center network, there is an unfair problem between QCN data streams, and an enhanced quantization plug notification algorithm (Ehanced Quantized Congestion Notification) is proposed. EQCN). The algorithm improves the switch and sending end of QCN at the same time. The switch side samples the received packets according to a certain probability. When a sampled data packet arrives, the EQCN switch detects the current buffer queue length and calculates a feedback value that reacts to the current congestion level. When the congestion is sent, the switch is born. It is a congestion feedback information that carries the feedback value, and sends the congestion feedback information to all the sources of the data stream that exceeds the average bandwidth of the shared link. The rate limiter of the transmitter uses the dynamic threshold to make the threshold value of the rate increasing phase proportional to the current transmission rate, the high rate data stream and the high threshold value, the EQCN algorithm. The improvement of the switch and the sending end improves the fairness of the data stream sharing bottleneck link. Finally, the experiment is carried out to verify the results, and the experimental results show that the algorithm improves the throughput of TCP Incast significantly.
(4) using the NS-2 network simulation tool to build a simulation platform, simulate the unfairness between QCN data streams and the proposed EQCN algorithm. The experimental results show that there is an unfairness between the QCN data streams. The EQCN algorithm proposed in this paper can improve the fairness between the data streams and improve the throughput of the TCP Incast significantly.

【學(xué)位授予單位】：廣西師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2013
【分類號】：TP308

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 江南;數(shù)據(jù)中心如何應(yīng)付管理挑戰(zhàn)[J];互聯(lián)網(wǎng)周刊;2001年40期

2 ;簡化管理挑戰(zhàn)——惠普推實(shí)用數(shù)據(jù)中心解決方案[J];每周電腦報;2001年67期

3 李慶莉;去數(shù)據(jù)中心看一看——中國銀行華北信息中心計劃處處長云恩善談數(shù)據(jù)中心運(yùn)行、管理[J];中國金融電腦;2002年12期

4 馬天蔚;;數(shù)據(jù)中心按需造[J];每周電腦報;2002年25期

5 戚麗,蔣東興,武海平,馮珂;校園數(shù)據(jù)中心建設(shè)與管理方法的探索[J];教育信息化;2002年S1期

6 何俊山;您企業(yè)的數(shù)據(jù)中心2003了嗎?[J];微電腦世界;2003年17期

7 ;挖潛數(shù)據(jù)中心[J];金融電子化;2004年07期

8 王琨月;;數(shù)據(jù)中心業(yè)務(wù)就緒[J];每周電腦報;2004年21期

9 包東智;新熱點(diǎn):創(chuàng)建下一代數(shù)據(jù)中心[J];上海信息化;2005年10期

10 ;把握數(shù)據(jù)中心建設(shè)五大看點(diǎn)[J];中國計算機(jī)用戶;2005年10期

相關(guān)會議論文 前10條

1 姚，

本文編號：1831368