阵列存储系统地址空间溢出的有效维护

M. Omar, K. Hasan
{"title":"阵列存储系统地址空间溢出的有效维护","authors":"M. Omar, K. Hasan","doi":"10.1109/PDCAT.2016.040","DOIUrl":null,"url":null,"abstract":"Array based storage and retrieval systems are demanded in many high dimensional systems like Big data for their easy maintenance. However, the lack of scalability of the conventional approaches degrades with the dynamic size of data sets as they entail reallocation in order to preserve expanded data velocity. To maintain the velocity of data, the storage system must be scalable enough by allowing subjective expansion on the boundary of array dimension. Again, for an array based storage system, if the number of dimension and length of each dimension of the array is very high then the required address space overflows and hence it is impossible to allocate such a big array in the memory. The index array offers a dynamic storage scheme for preserving expanded data velocity by employing indices for each dimension. In this paper we demonstrate a scalable array storage scheme that divides expanded data size into segments. Hence it is able to maintain overflow and can improve the storage utilization than the conventional one. The system converts the n dimensions of the array into 2 dimensions, hence it involves only 2 indices which ensures lower cost of index computation and higher data locality.","PeriodicalId":203925,"journal":{"name":"2016 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Towards an Efficient Maintenance of Address Space Overflow for Array Based Storage System\",\"authors\":\"M. Omar, K. Hasan\",\"doi\":\"10.1109/PDCAT.2016.040\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Array based storage and retrieval systems are demanded in many high dimensional systems like Big data for their easy maintenance. However, the lack of scalability of the conventional approaches degrades with the dynamic size of data sets as they entail reallocation in order to preserve expanded data velocity. To maintain the velocity of data, the storage system must be scalable enough by allowing subjective expansion on the boundary of array dimension. Again, for an array based storage system, if the number of dimension and length of each dimension of the array is very high then the required address space overflows and hence it is impossible to allocate such a big array in the memory. The index array offers a dynamic storage scheme for preserving expanded data velocity by employing indices for each dimension. In this paper we demonstrate a scalable array storage scheme that divides expanded data size into segments. Hence it is able to maintain overflow and can improve the storage utilization than the conventional one. The system converts the n dimensions of the array into 2 dimensions, hence it involves only 2 indices which ensures lower cost of index computation and higher data locality.\",\"PeriodicalId\":203925,\"journal\":{\"name\":\"2016 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)\",\"volume\":\"29 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/PDCAT.2016.040\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PDCAT.2016.040","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3

摘要

在大数据等高维系统中,需要基于阵列的存储和检索系统,因为它们易于维护。然而,缺乏可伸缩性的传统方法随着数据集的动态大小而退化,因为它们需要重新分配以保持扩展的数据速度。为了保持数据的速度,存储系统必须具有足够的可扩展性,允许在阵列维度的边界上进行主观扩展。同样,对于基于数组的存储系统,如果数组的维数和每个维的长度非常高,那么所需的地址空间就会溢出,因此不可能在内存中分配如此大的数组。索引数组提供了一种动态存储方案,通过为每个维度使用索引来保持扩展的数据速度。在本文中,我们演示了一种可扩展的阵列存储方案,该方案将扩展的数据大小划分为段。因此,它能够保持溢出,并比传统的存储利用率提高。系统将数组的n维转换为2维,因此只涉及2个索引,从而保证了较低的索引计算成本和较高的数据局部性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Towards an Efficient Maintenance of Address Space Overflow for Array Based Storage System
Array based storage and retrieval systems are demanded in many high dimensional systems like Big data for their easy maintenance. However, the lack of scalability of the conventional approaches degrades with the dynamic size of data sets as they entail reallocation in order to preserve expanded data velocity. To maintain the velocity of data, the storage system must be scalable enough by allowing subjective expansion on the boundary of array dimension. Again, for an array based storage system, if the number of dimension and length of each dimension of the array is very high then the required address space overflows and hence it is impossible to allocate such a big array in the memory. The index array offers a dynamic storage scheme for preserving expanded data velocity by employing indices for each dimension. In this paper we demonstrate a scalable array storage scheme that divides expanded data size into segments. Hence it is able to maintain overflow and can improve the storage utilization than the conventional one. The system converts the n dimensions of the array into 2 dimensions, hence it involves only 2 indices which ensures lower cost of index computation and higher data locality.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
A Learning-Based System for Monitoring Electrical Load in Smart Grid A Domain-Independent Hybrid Approach for Automatic Taxonomy Induction CUDA-Based Parallel Implementation of IBM Word Alignment Algorithm for Statistical Machine Translation Optimal Scheduling Algorithm of MapReduce Tasks Based on QoS in the Hybrid Cloud Pre-Impact Fall Detection Based on Wearable Device Using Dynamic Threshold Model
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1