间隔执行的异步副本放置策略
|
摘要
副本技术旨在通过预测用户获取数据行为并在适当的地点放置副本来降低网络延迟以及减少网络带宽消耗。副本技术已经广泛用在了数据网格、云计算中。副本技术主要有两大过程:第一个过程通过收集用户对文件的请求来选择最合适的文件作为候选副本,第二个过程通过计算资源节点位置、容量、带宽等因素来决定将候选副本放置到哪一个资源节点,以使整个系统所产生的延迟和带宽消耗最少。通过重新定义流行度,提高了对大文件造成延迟的敏感性。采用分而治之的思想设计全局算法和局部算法,局部算法通过异步机制将文件访问记录传递给全局算法进行全局流行度计算,然后局部算法综合全局流行度信息计算得到最合适的候选副本,最后将候选副本放置到最合适的资源节点。通过模拟实验,利用高斯分布、幂律分布来模拟用户文件请求行为偏好,验证了所提出的策略相比IPFRF(improved popular file replicate first)算法,在一定程度上降低了平均文件延迟和平均带宽消耗。
Data replication technique reduces the network latency and network bandwidth by predicting the preference of users and placing file replicas to the nearest resource node of users in advance, which has been widely used in data grid and cloud computing. Two important steps involve in data replication, file selection and replica placement. File selection is responsible for predicting the preference and selecting the most popular files as the candidates of replicas. Replica placement is responsible for placing file replicas to the most suitable node in data grid by taking the location, capacity and bandwidth of the resource node into consideration to minimize the latency and bandwidth consumption of the entire system. By redefining the file popularity, this paper improves the algorithm.s sensitivity to large files. Then this paper designs an asynchronous algorithm with distributed ideas which consists of local algorithm and global algorithm. The local algorithm sends the file access records to the global algorithm to calculate the global file popularity through the asynchronous mechanism. Then, the local algorithm selects the candidates of replica using redefined file popularity. Finally, the candidates of replica will be placed to the most suitable resource node.The simulation experimental results show that the proposed strategy can reduce the average file latency and the average bandwidth consumption to a certain extent compared with the IPFRF(improved popular file replicate first) algorithm under the access patterns of Gauss distribution and power law distribution.
Data replication technique reduces the network latency and network bandwidth by predicting the preference of users and placing file replicas to the nearest resource node of users in advance, which has been widely used in data grid and cloud computing. Two important steps involve in data replication, file selection and replica placement. File selection is responsible for predicting the preference and selecting the most popular files as the candidates of replicas. Replica placement is responsible for placing file replicas to the most suitable node in data grid by taking the location, capacity and bandwidth of the resource node into consideration to minimize the latency and bandwidth consumption of the entire system. By redefining the file popularity, this paper improves the algorithm.s sensitivity to large files. Then this paper designs an asynchronous algorithm with distributed ideas which consists of local algorithm and global algorithm. The local algorithm sends the file access records to the global algorithm to calculate the global file popularity through the asynchronous mechanism. Then, the local algorithm selects the candidates of replica using redefined file popularity. Finally, the candidates of replica will be placed to the most suitable resource node.The simulation experimental results show that the proposed strategy can reduce the average file latency and the average bandwidth consumption to a certain extent compared with the IPFRF(improved popular file replicate first) algorithm under the access patterns of Gauss distribution and power law distribution.
引文
[1]Lee M C,Leu F Y,Chen Yingping.PFRF:an adaptive data replication algorithm based on star-topology data grids[J].Future Generation Computer Systems,2012,28(7):1045-1057.
[2]Bsoul M,Alsarhan A,Otoom A,et al.A dynamic replication strategy based on categorization for data grid[J].Multiagent and Grid Systems,2014,10(2):109-118.
[3]Li Hui.Realistic workload modeling and its performance impacts in large-scale escience grids[J].IEEE Transactions on Parallel and Distributed Systems,2010,21(4):480-493.
[4]Tierney B,Johnston W,Lee J,et al.A data intensive distributed computing architecture for grid applications[J].Future Generation Computer Systems,2000,16(5):473-481.
[5]LHC.Large hadron clollider project[EB/OL].[2008].http://lhc.web.cern.ch/lhc/.
[6]Allcock W E,Bester J,Bresnahan J,et al.Data management and transfer in high-performance computational grid environments[J].Parallel Computing,2002,28(5):749-771.
[7]Allcock B,Bester J,Bresnahan J,et al.Secure,efficient data transport and replica management for high-performance dataintensive computing[C]//Proceedings of the 18th IEEE Symposium on Mass Storage Systems,San Diego,Apr 17-20,2001.Washington:IEEE Computer Society,2001:13-28.
[8]Hamrouni T,Slimani S,Charrada F B.A survey of dynamic replication and replica selection strategies based on data mining techniques in data grids[J].Engineering Applications of Artificial Intelligence,2016,48:140-158.
[9]Milani B A,Navimipour N J.A comprehensive review of the data replication techniques in the cloud environments[J].Journal of Network and Computer Applications,2016,64:229-238.
[10]Bsoul M,Abdallah A E,Almakadmeh K,et al.A roundbased data replication strategy[J].IEEE Transactions on Parallel and Distributed Systems,2016,27(1):31-39.
[11]Grace R K,Manimegalai R.Dynamic replica placement and selection strategies in data grids a comprehensive survey[J].Journal of Parallel and Distributed Computing,2014,74(2):2099-2108.
[12]Chang R S,Chang Huiping.A dynamic data replication strategy using access-weights in data grids[J].The Journal of Supercomputing,2008,45(3):277-295.
[13]Sashi K,Thanamani A S.Dynamic replication in a data grid using a modified bhr region based algorithm[J].Future Generation Computer Systems,2011,27(2):202-210.
[14]Mansouri N,Dastghaibyfard G H.A dynamic replica management strategy in data grid[J].Journal of Network and Computer Applications,2012,35(4):1297-1303.
[15]Wang Zhe,Li Tao,Xiong Naixue,et al.A novel dynamic network data replication scheme based on historical access record and proactive deletion[J].The Journal of Supercomputing,2012,62(1):227-250.
[16]Ko S Y,Morales R,Gupta I.New worker-centric scheduling strategies for data-intensive grid applications[C]//LNCS 4834:Proceedings of the 8th International Middleware Conference on Middleware,Newport Beach,Nov 26-30,2007.Berlin,Heidelberg:Springer,2007:121-142.
[17]Meyer L,Annis J,Wilde M,et al.Planning spatial workflows to optimize grid performance[C]//Proceedings of the2006 ACM Symposium on Applied Computing,Dijon,Apr23-27,2006.New York:ACM,2006:786-790.
[18]Rasool Q,Li Jianzhong,Oreku G S,et al.Fair-share replication in data grid[J].Information Technology Journal,2008,7(5):776-782.
[19]Wu J J,Lin Yifang,Liu Pangfeng.Optimal replica placement in hierarchical data grids with locality assurance[J].Journal of Parallel and Distributed Computing,2008,68(12):1517-1538.
[2]Bsoul M,Alsarhan A,Otoom A,et al.A dynamic replication strategy based on categorization for data grid[J].Multiagent and Grid Systems,2014,10(2):109-118.
[3]Li Hui.Realistic workload modeling and its performance impacts in large-scale escience grids[J].IEEE Transactions on Parallel and Distributed Systems,2010,21(4):480-493.
[4]Tierney B,Johnston W,Lee J,et al.A data intensive distributed computing architecture for grid applications[J].Future Generation Computer Systems,2000,16(5):473-481.
[5]LHC.Large hadron clollider project[EB/OL].[2008].http://lhc.web.cern.ch/lhc/.
[6]Allcock W E,Bester J,Bresnahan J,et al.Data management and transfer in high-performance computational grid environments[J].Parallel Computing,2002,28(5):749-771.
[7]Allcock B,Bester J,Bresnahan J,et al.Secure,efficient data transport and replica management for high-performance dataintensive computing[C]//Proceedings of the 18th IEEE Symposium on Mass Storage Systems,San Diego,Apr 17-20,2001.Washington:IEEE Computer Society,2001:13-28.
[8]Hamrouni T,Slimani S,Charrada F B.A survey of dynamic replication and replica selection strategies based on data mining techniques in data grids[J].Engineering Applications of Artificial Intelligence,2016,48:140-158.
[9]Milani B A,Navimipour N J.A comprehensive review of the data replication techniques in the cloud environments[J].Journal of Network and Computer Applications,2016,64:229-238.
[10]Bsoul M,Abdallah A E,Almakadmeh K,et al.A roundbased data replication strategy[J].IEEE Transactions on Parallel and Distributed Systems,2016,27(1):31-39.
[11]Grace R K,Manimegalai R.Dynamic replica placement and selection strategies in data grids a comprehensive survey[J].Journal of Parallel and Distributed Computing,2014,74(2):2099-2108.
[12]Chang R S,Chang Huiping.A dynamic data replication strategy using access-weights in data grids[J].The Journal of Supercomputing,2008,45(3):277-295.
[13]Sashi K,Thanamani A S.Dynamic replication in a data grid using a modified bhr region based algorithm[J].Future Generation Computer Systems,2011,27(2):202-210.
[14]Mansouri N,Dastghaibyfard G H.A dynamic replica management strategy in data grid[J].Journal of Network and Computer Applications,2012,35(4):1297-1303.
[15]Wang Zhe,Li Tao,Xiong Naixue,et al.A novel dynamic network data replication scheme based on historical access record and proactive deletion[J].The Journal of Supercomputing,2012,62(1):227-250.
[16]Ko S Y,Morales R,Gupta I.New worker-centric scheduling strategies for data-intensive grid applications[C]//LNCS 4834:Proceedings of the 8th International Middleware Conference on Middleware,Newport Beach,Nov 26-30,2007.Berlin,Heidelberg:Springer,2007:121-142.
[17]Meyer L,Annis J,Wilde M,et al.Planning spatial workflows to optimize grid performance[C]//Proceedings of the2006 ACM Symposium on Applied Computing,Dijon,Apr23-27,2006.New York:ACM,2006:786-790.
[18]Rasool Q,Li Jianzhong,Oreku G S,et al.Fair-share replication in data grid[J].Information Technology Journal,2008,7(5):776-782.
[19]Wu J J,Lin Yifang,Liu Pangfeng.Optimal replica placement in hierarchical data grids with locality assurance[J].Journal of Parallel and Distributed Computing,2008,68(12):1517-1538.