本文選題：云計(jì)算 + SLA��； 參考：《山東大學(xué)》2016年碩士論文

【摘要】：SaaS(軟件即服務(wù))以其“單實(shí)例多租賃”的特點(diǎn)為越來越多的用戶所接受,在這種服務(wù)模式下,一個應(yīng)用實(shí)例可以為多個租戶提供服務(wù),減少了服務(wù)提供商為每個租戶維護(hù)獨(dú)立應(yīng)用實(shí)例的服務(wù)成本,并且應(yīng)用具有十分靈活的擴(kuò)展性。但是,相對一般單租戶的應(yīng)用,多租戶應(yīng)用中每個租戶可以定制個性化需求,其業(yè)務(wù)特性變得復(fù)雜,這就使得不同的租戶對于數(shù)據(jù)庫服務(wù)性能有著不同的要求,包括服務(wù)吞吐量、平均響應(yīng)時(shí)間等。為確保SaaS應(yīng)用的數(shù)據(jù)庫服務(wù)質(zhì)量,每個租戶會與SaaS數(shù)據(jù)庫服務(wù)提供商之間協(xié)商簽訂服務(wù)水平協(xié)議(Service-Level Agreement, SLA)。參照雙方的SLA協(xié)議約束,SaaS數(shù)據(jù)庫服務(wù)提供商提供的服務(wù)想要獲得收益,必須能使租戶數(shù)據(jù)庫作業(yè)的響應(yīng)時(shí)間等性能滿足協(xié)議標(biāo)準(zhǔn),否則受到相應(yīng)的違約處罰。因此,SaaS數(shù)據(jù)庫服務(wù)提供商需要進(jìn)行資源的均衡配置和租戶作業(yè)執(zhí)行順序的制定,以滿足租戶個性化性能需求,另外,在應(yīng)用實(shí)例的運(yùn)行過程中服務(wù)提供商需要進(jìn)行集群資源監(jiān)測以及性能優(yōu)化,保證盡可能為完成租戶作業(yè)的提供充足的資源環(huán)境。云計(jì)算環(huán)境下SaaS服務(wù)質(zhì)量的控制需要綜合考慮多方面的因素。首先,多租戶應(yīng)用通常具有多熱點(diǎn)、多混合的負(fù)載特征。多熱點(diǎn)主要體現(xiàn)在不同租戶的業(yè)務(wù)熱點(diǎn)和峰值不同,熱點(diǎn)表示租戶的業(yè)務(wù)高峰期和持續(xù)時(shí)間,峰值表示租戶作業(yè)最大的負(fù)載壓力,不同租戶的熱點(diǎn)和峰值也是相互獨(dú)立的；多混合體現(xiàn)在不同租戶具有不同的負(fù)載特征,并且混合在一起會產(chǎn)生更加復(fù)雜的負(fù)載壓力。這二者使得SaaS數(shù)據(jù)庫服務(wù)提供商預(yù)測租戶負(fù)載壓力和構(gòu)建作業(yè)調(diào)度模型變的復(fù)雜。其次,租戶因?yàn)闃I(yè)務(wù)特性的不同對于10、MEM和CPU資源的需求程度不一樣,有些租戶業(yè)務(wù)偏重計(jì)算會消耗較多的CPU資源,有些租戶的業(yè)務(wù)需要進(jìn)行表的大量關(guān)聯(lián)并緩存大量數(shù)據(jù),還有一些租戶業(yè)務(wù)頻繁讀寫硬盤,并且,多租戶應(yīng)用中多個租戶的總體負(fù)載并不是單純的每個租戶負(fù)載壓力的疊加,這也加重了對租戶負(fù)載壓力的預(yù)測和對節(jié)點(diǎn)資源性能承受能力的判斷的困難程度。然后,租戶的數(shù)據(jù)在數(shù)據(jù)庫系統(tǒng)中共享存儲資源,各個租戶在相同數(shù)據(jù)節(jié)點(diǎn)上執(zhí)行作業(yè)時(shí)候就會產(chǎn)生資源競爭,一般情況下租戶的復(fù)雜的數(shù)據(jù)庫作業(yè)響應(yīng)時(shí)間長,簡單的數(shù)據(jù)庫作業(yè)響應(yīng)時(shí)間短,不合理的執(zhí)行順序會使得某些租戶的長作業(yè)長時(shí)間占用數(shù)據(jù)節(jié)點(diǎn)的資源引起其他租戶短作業(yè)違反SLA約束。因此,如何利用租戶數(shù)據(jù)組織的特點(diǎn),合理均衡租戶的負(fù)載壓力,為每個數(shù)據(jù)節(jié)點(diǎn)中租戶的作業(yè)制定有效的執(zhí)行順序,是眾多數(shù)據(jù)庫服務(wù)提供商實(shí)現(xiàn)總體SLA利益最大化的目的的有效途徑。本文對多租戶應(yīng)用的分布式數(shù)據(jù)庫系統(tǒng)里的作業(yè)處理進(jìn)行了系統(tǒng)研究,提出了一個基于無中心數(shù)據(jù)架構(gòu)的兩階段作業(yè)調(diào)度框架AdaptiveSLA,在分布式數(shù)據(jù)庫既有數(shù)據(jù)放置的情況下,對各數(shù)據(jù)節(jié)點(diǎn)接收的應(yīng)用服務(wù)器發(fā)送過來的租戶作業(yè)進(jìn)行兩階段調(diào)度,實(shí)現(xiàn)數(shù)據(jù)服務(wù)提供商SLA整體利益最大化,并盡可能減少執(zhí)行作業(yè)過程中移動數(shù)據(jù)的代價(jià)。首先,在系統(tǒng)初始化階段,本文使用機(jī)器學(xué)習(xí)算法構(gòu)建數(shù)據(jù)節(jié)點(diǎn)上的租戶性能需求預(yù)測模型。然后,調(diào)度的第一階段是數(shù)據(jù)節(jié)點(diǎn)在接收應(yīng)用服務(wù)器發(fā)送的數(shù)據(jù)庫作業(yè)的過程中,周期性使用危機(jī)探測器進(jìn)行節(jié)點(diǎn)的危機(jī)探測,如果危機(jī)探測器探測到節(jié)點(diǎn)發(fā)生了性能危機(jī),數(shù)據(jù)節(jié)點(diǎn)使用滑動窗口協(xié)議為后續(xù)到達(dá)的租戶作業(yè)找到最合適的調(diào)度目標(biāo)以緩解節(jié)點(diǎn)的性能危機(jī)；最后,調(diào)度的第二階段是在數(shù)據(jù)節(jié)點(diǎn)在執(zhí)行租戶的數(shù)據(jù)庫作業(yè)的時(shí)候,綜合考慮作業(yè)SLA約束的響應(yīng)時(shí)間和執(zhí)行時(shí)間為作業(yè)制定執(zhí)行次序,使盡可能多的作業(yè)能在規(guī)定的時(shí)間完成,增加服務(wù)提供商的收益減少違約賠償,以此達(dá)到數(shù)據(jù)服務(wù)提供商整體SLA利益最大化的目的。并且,為驗(yàn)證論文方法的有效性和可行性,本文設(shè)計(jì)了多組實(shí)驗(yàn)評估了使用的方法和模型,證明論文方法有效的達(dá)到了數(shù)據(jù)服務(wù)提供商SLA整體收益提升的目標(biāo)。
[Abstract]:SaaS (software as a service) is accepted by more and more users with its "single instance multi tenancy" feature. In this service mode, an application instance can provide services for multiple tenants, reducing service providers' service costs for each tenant to maintain an independent application instance, and the application has a very flexible scalability. Compared with the general single tenant, each tenant can customize the personalized requirement in the multi tenant application, and its business characteristics become complicated. This makes the different tenants have different requirements for the performance of the database service, including the service throughput, the average response time, etc. to ensure the quality of the database service of the SaaS application, each tenant will The service level protocol (Service-Level Agreement, SLA) is negotiated with the SaaS database service provider. According to the SLA protocol constraints of both parties, the services provided by the SaaS database service provider want to gain the benefit, and the response time of the tenant database operation must be able to meet the protocol standards, otherwise the corresponding breach of contract will be available. Therefore, the SaaS database service provider needs a balanced allocation of resources and the formulation of the execution order of the tenant operation to meet the tenant's personalized performance requirements. In addition, the service provider needs to monitor and optimize the performance of the cluster resources during the operation of the application instance to ensure that the tenant is completed as much as possible. The control of the quality of the SaaS service in the cloud computing environment requires a comprehensive consideration of many factors. First, multi tenant applications usually have multi hot and mixed load characteristics. The hot spots are mainly reflected in the different tenants' business hot spots and peak values. The hot spots indicate the peak and duration of the tenants' business, the peak expression The maximum load pressure of the tenant job, the different tenants' hot spots and peaks are also independent; multi - mix embodies the different tenants with different load characteristics and is mixed together to produce more complex load pressure. These two make the SaaS database service provider pretest the tenant load pressure and build the job scheduling model Secondly, the tenants are different for 10, MEM and CPU resources because of the different business characteristics. Some tenant businesses tend to calculate more CPU resources, some tenants need to carry out a large number of associations and cache a large number of data, and some tenant services frequently read and write hard disks, and many tenant applications are used. The overall load of more than one tenant is not a simple overlay of each tenant load pressure, which also aggravates the predictor of the tenant load pressure and the difficulty of judging the capability of the node resource performance. Then, the tenant's data shares the storage resources in the database system, and the tenants perform the job on the same data node. In general, the complex database job response time is long, the simple database job response time is short, the unreasonable execution order will cause the long operation of some tenants to occupy the data nodes for a long time to cause other tenant short jobs to violate the SLA constraints. According to the characteristics of the organization, it is an effective way for many database service providers to achieve the goal of maximizing the overall SLA benefits for each database service provider. This paper makes a systematic study on the job handling in the distributed data base system for multi tenant applications. A two stage job scheduling framework AdaptiveSLA based on no center data architecture is proposed. In the case of distributed data storage, the tenant operation sent by the application server received by each data node is scheduled for two stages, and the overall benefit of the data service provider SLA is maximized and reduced as much as possible. Firstly, in the initialization stage of the system, this paper uses machine learning algorithm to construct the tenant performance requirement prediction model on the data node. Then, the first phase of the scheduling is that the data node is used in the process of receiving the database sent by the application server, and the periodic use of the crisis detector is made. If the crisis detector detects that the node has a performance crisis, the data node uses a sliding window protocol to find the most appropriate scheduling target for the subsequent tenant operation to alleviate the performance crisis of the node. Finally, the second phase of the scheduling is when the node is executing the database operation of the tenant. At the same time, considering the response time and execution time of the job SLA constraints to work out the execution order for the job, so that as many jobs can be completed at the specified time, increase the revenue of the service provider to reduce the default compensation, so as to achieve the purpose of maximizing the overall SLA benefit of the data service provider, and to verify the validity of the method of the paper. And feasibility, this paper designs several groups of experiments to evaluate the methods and models used, and proves that the method of the paper effectively achieves the goal of improving the overall revenue of the data service provider SLA.

【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP393.09

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 李陽春;電信公司的新型服務(wù)模式——SLA服務(wù)[J];廣東通信技術(shù);2002年05期

2 ;SLA:安全防范的“保險(xiǎn)單”[J];互聯(lián)網(wǎng)周刊;2002年35期

3 錢瓊芬;李春林;熊家軍;李強(qiáng);;云計(jì)算中的SLA管理技術(shù)研究[J];電信科學(xué);2012年10期

4 ;別忘了簽合同 SLA可提供幀中繼性能保障[J];每周電腦報(bào);1998年25期

5 王文凡;趙卓;王麗娟;;云計(jì)算環(huán)境下SLA自動管理的現(xiàn)狀及問題[J];現(xiàn)代計(jì)算機(jī)(專業(yè)版);2013年01期

6 劉擁軍;張慶杰;陳靜;趙赫;;構(gòu)建集團(tuán)客戶通信網(wǎng)絡(luò)保障SLA體系[J];通信企業(yè)管理;2013年10期

7 吳勁松;支勇;;以SLA規(guī)范服務(wù)質(zhì)量 廣州電信實(shí)踐主備數(shù)據(jù)中心全外包[J];通信世界;2010年32期

8 謝喜秋,黃娟;在ATM網(wǎng)絡(luò)中如何管理SLA[J];廣東通信技術(shù);2001年09期

9 張春芳,李紅輝,汪齊賢,孫文輝;服務(wù)等級協(xié)議SLA及其實(shí)現(xiàn)模型研究[J];計(jì)算機(jī)應(yīng)用研究;2005年09期

10 吳雪波;電信SLA的實(shí)施和管理[J];浙江萬里學(xué)院學(xué)報(bào);2005年02期

相關(guān)會議論文 前4條

1 李華;;豬主要組織相容性復(fù)合體物(SLA)的研究概況[A];全國首屆動物生物技術(shù)學(xué)術(shù)研討會論文集[C];2004年

2 于輝;劉榮輝;李華;左啟禎;李巖;吳珍芳;;5個豬種SLA微衛(wèi)星遺傳多樣性[A];全國生物遺傳多樣性高峰論壇會刊[C];2012年

3 劉榮輝;李華;左啟禎;于輝;趙紅娟;;三品種小型豬與云南野豬白細(xì)胞抗原復(fù)合物(SLA)微衛(wèi)星的遺傳多樣性[A];第十屆中國實(shí)驗(yàn)動物科學(xué)年會論文集[C];2012年

4 匡斌;;SLA:如何跳出概念的泥潭[A];通信發(fā)展戰(zhàn)略與業(yè)務(wù)管理創(chuàng)新學(xué)術(shù)研討會論文集[C];2005年

相關(guān)重要報(bào)紙文章 前5條

1 本報(bào)記者 姚穎;深圳電信首推SLA服務(wù) 引領(lǐng)等值服務(wù)新理念[N];通信信息報(bào);2002年

2 記者 韓曉民;深圳電信率先推出SLA服務(wù)[N];人民郵電;2002年

3 ;SLA，電信運(yùn)營商難掘的一桶金[N];網(wǎng)絡(luò)世界;2003年

4 于翔;SLA達(dá)成需IT與業(yè)務(wù)目標(biāo)協(xié)調(diào)一致[N];網(wǎng)絡(luò)世界;2008年

5 王陸軍、趙常明;中國網(wǎng)通兩種手段實(shí)現(xiàn)SLA[N];中國計(jì)算機(jī)報(bào);2003年

相關(guān)博士學(xué)位論文 前1條

1 張奕奎;SLA管理關(guān)鍵技術(shù)及其在下一代互聯(lián)網(wǎng)中的應(yīng)用[D];北京郵電大學(xué);2007年

相關(guān)碩士學(xué)位論文 前7條

1 王振坤;基于SLA的多租戶數(shù)據(jù)服務(wù)利益最大化問題研究[D];山東大學(xué);2016年

2 吳莎;基于云環(huán)境的SLA及任務(wù)調(diào)度算法的研究與實(shí)現(xiàn)[D];西北大學(xué);2013年

3 劉劍;基于策略的異構(gòu)/融合網(wǎng)絡(luò)SLA管理的研究與實(shí)現(xiàn)[D];北京郵電大學(xué);2011年

4 唐瑜;SLA參數(shù)管理在網(wǎng)絡(luò)動態(tài)監(jiān)測系統(tǒng)中的研究與實(shí)現(xiàn)[D];電子科技大學(xué);2008年

5 孫丹;SLA口語問題與語言障礙對比研究[D];哈爾濱理工大學(xué);2007年

6 張俊;基于SLA原型和化學(xué)鍍銅工藝的電火花加工電極制造技術(shù)研究[D];蘭州理工大學(xué);2006年

7 徐晶;SLA監(jiān)測系統(tǒng)的研究與實(shí)現(xiàn)[D];華中科技大學(xué);2004年

，

本文編號：1845538