本文選題：云計(jì)算　切入點(diǎn)：數(shù)據(jù)中心網(wǎng)絡(luò)　出處：《北京郵電大學(xué)》2013年博士論文

【摘要】：近幾年,云計(jì)算蓬勃發(fā)展并得到了產(chǎn)業(yè)界和學(xué)術(shù)界的廣泛關(guān)注,已經(jīng)成為信息化建設(shè)領(lǐng)域的熱點(diǎn)和未來(lái)趨勢(shì)。與此同時(shí),許多新的互聯(lián)網(wǎng)在線業(yè)務(wù)(如搜索、社交網(wǎng)絡(luò)、即時(shí)通信等)的用戶量也在迅速增長(zhǎng)。在云計(jì)算和互聯(lián)網(wǎng)在線業(yè)務(wù)的快速發(fā)展過(guò)程中,作為信息化基礎(chǔ)設(shè)施的數(shù)據(jù)中心一直處于核心地位。隨著業(yè)務(wù)的發(fā)展和新技術(shù)的使用,數(shù)據(jù)中心正在發(fā)生和形成重大的變化及趨勢(shì),由此給數(shù)據(jù)中心網(wǎng)絡(luò)(Data Center Networks, DCN)帶來(lái)了新的挑戰(zhàn)和問(wèn)題。首先,新興的業(yè)務(wù)需要服務(wù)器之間進(jìn)行大量的一對(duì)多和多對(duì)多的通信,其結(jié)果是數(shù)據(jù)中心的內(nèi)部流量急劇增長(zhǎng)并呈現(xiàn)出不同于互聯(lián)網(wǎng)流量的新特性。在當(dāng)前技術(shù)條件下,數(shù)據(jù)中心網(wǎng)絡(luò)會(huì)頻繁發(fā)生擁塞,導(dǎo)致丟包增多、時(shí)延增大和吞吐量下降,嚴(yán)重影響業(yè)務(wù)的性能和服務(wù)質(zhì)量。其次,虛擬化技術(shù)給數(shù)據(jù)中心網(wǎng)絡(luò)帶來(lái)了新的挑戰(zhàn),虛擬機(jī)遷移帶來(lái)的流量會(huì)加重網(wǎng)絡(luò)負(fù)載甚至造成網(wǎng)絡(luò)擁塞。由此可見(jiàn),數(shù)據(jù)中心網(wǎng)絡(luò)在新的業(yè)務(wù)模式和新技術(shù)發(fā)展趨勢(shì)下已經(jīng)不能滿足需求。為保證業(yè)務(wù)的性能及服務(wù)質(zhì)量,數(shù)據(jù)中心網(wǎng)絡(luò)的流量管理和優(yōu)化問(wèn)題已成為當(dāng)前亟待解決的重要問(wèn)題。 本文首先系統(tǒng)總結(jié)了數(shù)據(jù)中心網(wǎng)絡(luò)的相關(guān)研究背景和最新進(jìn)展,對(duì)當(dāng)前的數(shù)據(jù)中心網(wǎng)絡(luò)各層的相關(guān)技術(shù)做了比較全面的歸納和總結(jié)。接著,以數(shù)據(jù)中心網(wǎng)絡(luò)流量作為切入點(diǎn),從數(shù)據(jù)中心網(wǎng)絡(luò)的新特性出發(fā),分別從網(wǎng)絡(luò)層次的低到高,研究了數(shù)據(jù)中心網(wǎng)絡(luò)的流量管理和優(yōu)化問(wèn)題,包括流量工程、傳輸層協(xié)議的優(yōu)化與改進(jìn)、多虛擬機(jī)遷移調(diào)度等四個(gè)方面,以減少數(shù)據(jù)中心網(wǎng)絡(luò)的擁塞,優(yōu)化網(wǎng)絡(luò)資源的使用,從而提升業(yè)務(wù)的性能。具體如下： (一)研究了數(shù)據(jù)中心網(wǎng)絡(luò)常見(jiàn)的場(chǎng)景“以太網(wǎng)鏈路聚合”中的流量?jī)?yōu)化問(wèn)題。在數(shù)據(jù)中心網(wǎng)絡(luò)流量工程中,只是將被聚合的物理鏈路看做是一條鏈路,沒(méi)有考慮到這些被聚合的物理鏈路之間如何均衡流量。而目前以太網(wǎng)鏈路聚合的流量分配算法也是基于會(huì)話的,不適用于數(shù)據(jù)中心網(wǎng)絡(luò)環(huán)境。本文首先分析基于幀的流量分配算法造成幀亂序的原因,發(fā)現(xiàn)這些因素在數(shù)據(jù)中心網(wǎng)絡(luò)環(huán)境下都不再成立或者可以避免。因此,本文提出一個(gè)基于字節(jié)計(jì)數(shù)的幀級(jí)別流量分配算法,該算法可以達(dá)到最優(yōu)的負(fù)載均衡,同時(shí)不會(huì)造成亂序。唯一需要滿足的條件是同一個(gè)會(huì)話的幀大小要一致,而該條件在數(shù)據(jù)中心環(huán)境下很容易滿足。 (二)研究了TCP協(xié)議在數(shù)據(jù)中心網(wǎng)絡(luò)面臨的兩個(gè)問(wèn)題：TCP擴(kuò)展限制(Scaling Limit)和TCP Incast吞吐量崩潰。數(shù)據(jù)中心帶寬高、時(shí)延小且出現(xiàn)了新的通信模式,面向廣域網(wǎng)設(shè)計(jì)的TCP在數(shù)據(jù)中心網(wǎng)絡(luò)環(huán)境面臨著性能差的問(wèn)題。本文提出通過(guò)減小分組長(zhǎng)度來(lái)優(yōu)化TCP性能。分組長(zhǎng)度越小,鏈路和交換機(jī)緩存區(qū)可以承載的分組越多,TCP擁塞控制的粒度也越小,同時(shí)丟包可能性也越小,從而達(dá)到優(yōu)化TCP性能的目的,包括減輕TCP擴(kuò)展限制和緩解TCP Incast吞吐量崩潰。減小分組的好處是可以很方便在現(xiàn)有硬件和軟件上實(shí)現(xiàn),只需要在服務(wù)器或交換機(jī)上做簡(jiǎn)單配置即可。 (三)研究了能提供截止時(shí)間知曉(deadline-aware)傳輸服務(wù)的改進(jìn)TCP協(xié)議。數(shù)據(jù)中心內(nèi)的很多流都有截止時(shí)間,而占了數(shù)據(jù)中心大部分流量的TCP協(xié)議不能提供截止時(shí)間知曉的傳輸服務(wù)。本文提出了一種截止時(shí)間知曉的改進(jìn)TCP協(xié)議,稱為DATCP (Deadline-Aware TCP),來(lái)為數(shù)據(jù)中心承載的應(yīng)用提供截止時(shí)間知曉的傳輸服務(wù)。DATCP根據(jù)流的期望速率和實(shí)際吞吐量之差來(lái)動(dòng)態(tài)調(diào)整其其擁塞控制參數(shù),來(lái)滿足流的截止時(shí)間需求。DATCP只需對(duì)標(biāo)準(zhǔn)TCP做少量修改,并利用現(xiàn)有商品化數(shù)據(jù)中心交換機(jī)普遍支持的顯示擁塞通知ECN機(jī)制。 (四)研究了虛擬化數(shù)據(jù)中心常見(jiàn)的多虛擬機(jī)遷移調(diào)度問(wèn)題。前面都是從網(wǎng)絡(luò)角度來(lái)優(yōu)化流量的,這在互聯(lián)網(wǎng)研究領(lǐng)域是普遍的。而在數(shù)據(jù)中心網(wǎng)絡(luò),直接控制流量分布來(lái)實(shí)現(xiàn)流量管理和優(yōu)化更直接有效。本文通過(guò)計(jì)算出一個(gè)合適的虛擬機(jī)遷移的調(diào)度順序,來(lái)最小化虛擬機(jī)遷移的持續(xù)時(shí)間。多個(gè)虛擬機(jī)同時(shí)遷移(VM shuffle)調(diào)度問(wèn)題被建模成一個(gè)作業(yè)調(diào)度的最優(yōu)化問(wèn)題,該問(wèn)題等價(jià)于旅行商問(wèn)題。由于該問(wèn)題是NP-難,本文設(shè)計(jì)了兩個(gè)調(diào)度算法：基于模擬退火的離線算法和基于貪婪方式的在線算法。兩個(gè)算法的基本想法都是計(jì)算一個(gè)合適的虛擬機(jī)調(diào)度順序,優(yōu)先遷移給其他虛擬機(jī)帶來(lái)最大好處的虛擬機(jī),為后續(xù)遷移虛擬機(jī)提供更大的可用帶寬,這樣所有虛擬機(jī)的遷移持續(xù)時(shí)間就會(huì)減小,從而最小化多虛擬機(jī)遷移對(duì)數(shù)據(jù)中心造成的影響。
[Abstract]:In recent years, rapid development of cloud computing and has received wide attention from industry and academia, has become a hot topic in the field of information technology and the trend in the future. At the same time, many new Internet online business (such as search, social networking, instant messaging and so on) the number of users is increasing rapidly. In the process of rapid development of cloud computing the Internet and online business, as the information infrastructure of the data center has been at the core. With the use of business development and new technology, data center is the occurrence and formation of major changes and trends, to the data center network (Data Center Networks, DCN) brings new challenges and problems. First of all, the emerging business needs a large number of servers and many to many communication, the result is the internal flow of data center and the rapid growth of Internet traffic is different from New features. In the current technical conditions, the data center network congestion occur frequently, cause packet loss increase, delay and throughput degradation, seriously affect the performance and quality of service business. Secondly, virtualization technology has brought new challenges to the data center network, virtual machine migration to bring traffic will increase the network load and even cause network congestion. Thus, the data center network in the development of business mode and under the new trend of new technology can not meet the demand. In order to ensure the service performance and quality of service, traffic management and data center network optimization has become an important issue to be solved.
This paper first summarizes the related research background and latest development of the data center network, the relevant technology of each layer of the network data center to do a more comprehensive and summarized. Then, the data center network traffic as a starting point, starting from the characteristics of the new data center network, separately from the network level to low high, traffic management and optimization of the data center network, including traffic engineering, optimization and improvement of transmission protocol, the four aspects of virtual machine migration scheduling, in order to reduce the congestion of data center network, optimize the use of cyber source, so as to enhance business performance. The details are as follows:
(a) the flow optimization problem scene "data center network common Ethernet link aggregation". In the data center network traffic engineering, only the physical link is regarded as a link aggregation, without considering the physical link between these are aggregated as He Junheng flow. And traffic allocation algorithm at Ethernet link the polymerization is also based on the session, does not apply to the data center network environment. This paper first analyzes the traffic allocation algorithm based on frame frame causes out of order, it was found that these factors in the data center network environment are no longer valid or can be avoided. Therefore, this paper proposes a frame level traffic allocation algorithm based on the byte count. The algorithm can achieve optimal load balancing, without causing disorder. The only need to meet the condition that the frame size of the same session to be consistent, and the conditions It is easy to meet in the data center environment.
(two) of the TCP agreement in the two problems in the data center network: TCP (Scaling Limit) expansion limit and TCP Incast throughput collapse. The data center of high bandwidth, small delay and the emergence of new communication mode, Wan oriented design of the TCP in the data center network environment is facing the problem of poor performance in this paper. Put forward to optimize the performance of TCP by reducing the packet length. The packet length is smaller, more packet link and switch buffer can bear, the size of TCP congestion control and packet loss is smaller and less likely, so as to achieve the purpose of optimization of TCP can reduce TCP, including expansion limit and mitigate TCP Incast throughput decreases collapse. Group benefits can be easily realized in the existing hardware and software, only need to do a simple configuration to the server or switch.
(three) the study can provide the deadline aware (Deadline-Aware) improved TCP protocol services. A lot of flow within the data center has a deadline, and accounted for most of the traffic data center TCP protocol can not provide Business Hours cutoff transmission known. This paper presents an improved TCP protocol deadline aware, said DATCP (Deadline-Aware TCP), provided by knowledge transfer service.DATCP according to the flow rate and the difference between the actual throughput expected to dynamically adjust its congestion control parameters used to load the data center, to meet the deadline demand flow.DATCP only make minor modifications to the standard TCP, and the use of existing commercial data general support of the center switch display ECN congestion notification mechanism.
(four) the virtual machine common virtualized data center migration scheduling problem. In front of all is to optimize traffic from the network point of view, this research field is common on the Internet. And in the data center network, traffic management and optimization to achieve a more direct effective direct control flow through the calculation of a distribution. The proper migration of virtual machine scheduling in order to minimize the duration of virtual machine migration. Multiple virtual machines (VM shuffle) at the same time migration scheduling problem is modeled as a scheduling optimization problem, the problem is equivalent to the traveling salesman problem. Because the problem is NP- hard, this paper designs two scheduling algorithm based on the off-line simulated annealing algorithm and greedy algorithm based on online mode. The basic idea of the two algorithms are calculated with an appropriate virtual machine scheduling, priority to other virtual machine migration brings the biggest The benefits of the virtual machine provide greater available bandwidth for subsequent migration virtual machines, so that the migration time of all virtual machines will be reduced, so as to minimize the impact of multi virtual machine migration on data centers.

【學(xué)位授予單位】：北京郵電大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2013
【分類號(hào)】：TP308;TP393.06

【參考文獻(xiàn)】

相關(guān)期刊論文 前4條

1 丁澤柳;郭得科;申建偉;羅愛(ài)民;羅雪山;;面向云計(jì)算的數(shù)據(jù)中心網(wǎng)絡(luò)拓?fù)溲芯縖J];國(guó)防科技大學(xué)學(xué)報(bào);2011年06期

2 王聰;王翠榮;王興偉;蔣定德;;面向云計(jì)算的數(shù)據(jù)中心網(wǎng)絡(luò)體系結(jié)構(gòu)設(shè)計(jì)[J];計(jì)算機(jī)研究與發(fā)展;2012年02期

3 劉曉茜;楊壽保;郭良敏;王淑玲;宋滸;;雪花結(jié)構(gòu):一種新型數(shù)據(jù)中心網(wǎng)絡(luò)結(jié)構(gòu)[J];計(jì)算機(jī)學(xué)報(bào);2011年01期

4 魏祥麟;陳鳴;范建華;張國(guó)敏;盧紫毅;;數(shù)據(jù)中心網(wǎng)絡(luò)的體系結(jié)構(gòu)[J];軟件學(xué)報(bào);2013年02期

，

本文編號(hào)：1722156