分段位图索引.docVIP

结合分段位图和B+树的云数据索引机制研究( 贺智明张慧云 (江西理工大学 信息工程学院，江西 赣州，341000) 摘要 云数据索引技术是当今IT领域的研究热点。位图索引因其简单有效的优势被广泛应用于海量数据的分析处理。针对位图索引数据存储空间大，检索效率低的问题，提出了一种结合分段位图和B+树的云数据索引机制（简称BBI索引）。BBI索引在索引创建时按照一定的基数对元组数据进行分段，以段为单位建立位图索引，索引数据量的决定因子由属性值的取值范围转变为分段数与基数的乘积大大减少了索引数据量；同时，在每个数据节点上建立B+树，避免了数据检索时对非结果数据的逐个遍历，显著提高了数据的检索效率。实验结果表明，BBI索引是一种性能较优的云数据索引机制。 关键词 云数据索引；分段位图索引；B+树；并行执行；索引排序 中图分类号P311 文献标志码 Research On Cloud Data Indexing Mechanism Based On Segmented Bitmap And B+ Tree HE Zhiming,ZHANG Huiyun*,MAO Yimin (Faculty of Information Engineering,Jiangxi Universuty of Science and Technology,Ganzhou Jiangxi 341000,China) Abstract The index technology of cloud data is the hotspot in IT field nowadays. Due to the advantages of simple and effective, bitmap index is widely used to analyze and process massive data. In order to solve the large storage space of indexing data in bitmap index and low efficiency during retrieving, developed a cloud data index mechanism combined Segmented bitmap and B+ tree(BBI).BBI index divides data into several segments based on a certain number when the index is created, bitmap index by segment , the decision factor of the index data quantity is changed from the range of attribute values to the product of the segments and certain number,which greatly reduces the storage space of the index data; Furthermore, the B+ tree is built on each data node, the unnecessary computing expenses on local nodes can be avoided according to the global distribution Information, therefore, retrieving efficiency can be greatly improved. The experimental results show that the BBI index is a better data index in cloud data index mechanism. Keywords Cloud data index；Segmented bitmap index；B+ tree；Concurrent execution；Index sort 引言 近年来，随着互联网技术快速发展，社交网络、电子商务、物联网等产生的海量数据逐渐超出了传统数据存储载体的承受范围[1]。数据的结构、规模和形式都在发生着巨大的变化。云计算和大数据的出现，为这些庞大数据的存储处理和分析研究提供了技术支持，已逐渐成为IT领域的研究热点。 大数据索引技术是大数据研究的重要内容[2]。一个高效的数据索引方案可以使数据的检索变得简单高效，既缩小索引数据本身的存储空间也提高了数据检索的速度和命中率。目前，针对大数据存储方式的不同，主要的索引方案有双层索引[3]全局分