【作者】 赵伟；

【导师】 郑玲； 魏广朝；

【作者基本信息】 华北电力大学(北京) ， 工程硕士（专业学位）， 2017， 硕士

【摘要】 伴随着云计算技术的广泛应用,互联网及物联网技术的不断快速发展,大数据时代信息数据量出现了爆发性增长的态势,传统架构下的存储系统已经难以满足不同行业的信息系统在兼容性、统一管理、扩展性、安全性、差异化服务等方面的需求。在云计算应用场景下,海量的数据被集中存储在一起,随着数据量的飞速递增以及存储规模的不断扩大,数据读写性能瓶颈变得十分严重,因此对存储系统的I/O性能、总体容量、可扩展性和可管理性等方面提出更高的要求。因为存储厂商在各自存储设备的实现方式上长期存在技术差异和严重的技术壁垒,传统架构存储系统大多是单一、封闭、集成的系统,只支持特定软件和硬件的组合,存储系统缺乏灵活性,无法充分利用不断涌现的新硬件产品的能力和新平台,并且只能进行有限度的扩展,无法满足用户快速增长的数据存储的需要。同时,不同存储系统之间只能实现非常有限的统一监控,而无法形成完整统一、有效调度、全局管理的存储资源池。当今许多企业的数据中心都在经历从传统数据中心到云架构的转型,在转型过程中,存储架构成了关键的环节。软件定义存储从提出以来,就被广泛认为是下一代存储技术发展方向,软件定义存储是将硬件驱动从存储技术中剥离出来,通过软件定义反向驱动硬件,将与存储相关的控制工作都放置在相对于物理存储硬件的外部软件中,可以提供包括存储虚拟化,存储资源动态管理等功能。用户可以利用软件定义技术,来打破厂商之间的限制壁垒,消除专用平台限制,建设可灵活扩展低成本的面向云计算的存储系统。本文软件定义存储的模型研究旨在利用新的软件定义存储技术设计一套适用于电力系统的软件定义存储模型,通过软件定义的方式实现存储系统软硬件的解耦,使其具备灵活的配置策略、多元化的存储供给能力以及存储资源的高效管理。更多还原

【Abstract】 With the popularity of cloud computing technology,the rapid development of Internet technology and the Internet of things,big data era of information data volume has seen explosive growth,the traditional storage system under the framework of the information system has been difficult to meet the different industries in the unified management,compatibility,scalability,security,and other aspects of the demand for differentiated services.In the cloud computing application scenarios,massive data are concentrated together with the amount of data storage,the rapid increasing and expanding the scale of storage,data read and write performance bottlenecks become very serious,so the storage system of I/O performance and overall capacity,scalability and manageability,etc.put forward higher requirements.Because of the long-term storage vendors technical differences and serious technical barriers in the implementation of their respective storage devices,the traditional storage system architecture is mostly single and closed system,integration,combination only support specific software and hardware,storage system lacks flexibility and can not make full use of the ability of new hardware products continue to emerge and new platform.And can only be extended limited,unable to meet the needs of the rapid growth of users of data storage.At the same time,different storage systems can only achieve a very limited unified monitoring,but can not form a complete unified,effective scheduling,global management of storage resource pool.Today’s data centers in many enterprises are experiencing transformation from the traditional data center to the cloud architecture,in the transformation process,the storage rack constitutes a key link.From the software defined storage has been proposed,is widely regarded as a development direction of next generation storage technology,software defined storage is the hardware driver out of storage technology,defined by the software reverse drive hardware,control and storage are placed in relation to the physical storage hardware can provide external software,including storage storage virtualization,dynamic resource management and other functions.Users can use the software definition technology to break the barriers between manufacturers to eliminate the limitations of the special platform,the construction of a flexible expansion of low-cost cloud computing storage system.Study on the model of software defined storage is to use the new design software defined storage technology applied to a set of power system software defined storage model,decoupling hardware and software realization of storage system through software defined way,which has a storage supply capacity of flexible allocation strategy,diversified and efficient management of storage resources.更多还原