{"title":"聚类数据的多站点检索","authors":"A. Tosun","doi":"10.1109/ICDCS.2008.72","DOIUrl":null,"url":null,"abstract":"Declustering techniques reduce query response times through parallel I/O by distributing data among multiple devices. Recently, replication based approaches were proposed to further reduce the response time. All of the replication based schemes assume that replication is done at a single site. In this paper, we consider replicated data stored at multiple sites. We formulate multi-site retrieval problem as a maximum flow problem and solve it using maximum flow techniques. We propose a low complexity online algorithm for the problem. We investigate the proposed scheme using various replication schemes, query types and query loads. Proposed scheme can easily be extended to nonuniform data and to any number of sites. Experimental results show that replication using orthogonal allocation performs the best under various settings.","PeriodicalId":240205,"journal":{"name":"2008 The 28th International Conference on Distributed Computing Systems","volume":"62 3 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2008-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":"{\"title\":\"Multi-Site Retrieval of Declustered Data\",\"authors\":\"A. Tosun\",\"doi\":\"10.1109/ICDCS.2008.72\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Declustering techniques reduce query response times through parallel I/O by distributing data among multiple devices. Recently, replication based approaches were proposed to further reduce the response time. All of the replication based schemes assume that replication is done at a single site. In this paper, we consider replicated data stored at multiple sites. We formulate multi-site retrieval problem as a maximum flow problem and solve it using maximum flow techniques. We propose a low complexity online algorithm for the problem. We investigate the proposed scheme using various replication schemes, query types and query loads. Proposed scheme can easily be extended to nonuniform data and to any number of sites. Experimental results show that replication using orthogonal allocation performs the best under various settings.\",\"PeriodicalId\":240205,\"journal\":{\"name\":\"2008 The 28th International Conference on Distributed Computing Systems\",\"volume\":\"62 3 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2008-06-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"7\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2008 The 28th International Conference on Distributed Computing Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICDCS.2008.72\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2008 The 28th International Conference on Distributed Computing Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICDCS.2008.72","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Declustering techniques reduce query response times through parallel I/O by distributing data among multiple devices. Recently, replication based approaches were proposed to further reduce the response time. All of the replication based schemes assume that replication is done at a single site. In this paper, we consider replicated data stored at multiple sites. We formulate multi-site retrieval problem as a maximum flow problem and solve it using maximum flow techniques. We propose a low complexity online algorithm for the problem. We investigate the proposed scheme using various replication schemes, query types and query loads. Proposed scheme can easily be extended to nonuniform data and to any number of sites. Experimental results show that replication using orthogonal allocation performs the best under various settings.