一种基于流水线的重复数据删除系统读性能优化方法  被引量:2

A Reading Performance Improvement Method in Deduplication Based on Pipeline

在线阅读下载全文

作  者:李超[1,2] 王树鹏[3] 云晓春[2,3] 周晓阳[1] 陈明[4,5] 

机构地区:[1]中国科学院计算技术研究所,北京100190 [2]国家计算机网络应急技术处理协调中心,北京100029 [3]中国科学院信息工程研究所,北京100029 [4]北京邮电大学,北京100876 [5]新乡学院,河南新乡453000

出  处:《计算机研究与发展》2013年第1期90-100,共11页Journal of Computer Research and Development

基  金:国家自然科学基金项目(61003260);国家"八六三"高技术研究发展计划基金项目(2009AA01A403;2007AA010501;2007AA01Z467;2007AA01Z474)

摘  要:重复数据删除技术已逐渐应用到以云计算为代表的主存储系统中,这些系统对读响应时间的高要求使读性能成为重复数据删除系统中需要解决的重要问题,而已有研究对如何提高重复数据删除系统读性能关注很少.针对这一问题,对重复数据删除系统中读取流程和性能瓶颈进行了量化分析,提出了一种基于流水线的数据读取模型,然后通过并行计算机制对模型进行了进一步的优化.基于这一模型设计实现了实验系统,通过实验证明:对于网络安全监测日志文本数据和虚拟机镜像文件,应用此模型后,重复数据删除系统读速度的提高可达5倍以上;基于流水线的数据读取模型适用性强,对提高不同消冗率的数据读速度均有明显作用.The applica cloud computing. In tion of data dedupli those systems, the because of the high demand o to reading performance in the and bottleneck in this area, additionally improve this rea cation has been extend f reading res area and ding theoretical analysis to evaluate its a paralleled and pipelined data experiments using three different reading perfor ponse time. H mance ed to the primary storage systems like has become a very important factor owever, not so much attention has been paid of data deduplication. In this pa propose a reading model base model using the mechanism of per, we analyze the reading process d on pipeline (RMBP). And we parallel calculation. Then we do effect in the improvement of reading speed. Furthermore, deduplication kinds of data system based on this reading model. W we design e also do in this system. The experimental results show that: the system using RMBP can increase the reading speed wi network security logs and the virtual machine image data higher reading different data roughput ; deduplicaiton RMBP can significantly impr ratio, and has good extensive th all kinds of the experimental data; for the , the system using RMBP can get a 5 times ove the reading performance in scenarios of applicability hence.

关 键 词:重复数据删除 主存储系统 读性能 流水线 优化 

分 类 号:TP333[自动化与计算机技术—计算机系统结构]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象