分级存储中数据迁移机制的实现-计算机系统结构专业论文.docxVIP

华中科技大学硕士学位论文 华 中 科 技 大 学 硕 士 学 位 论 文 II II Abstract Hierarchical storage is designed to realize that, the data with different heat value should be on the storage devices with different performance, maximize storage utilization . When the heat value of the data is changed , it will trigger data migrate to the storage devices which are better meet their current heat value. Therefor, for hierarchical storage system , design a data migration mechanism which is transparent and efficient to foreground application has important research value. It divided into three modules to design data migration process: heat statistics module , strategy matching module and data migration module. The heat statistic module is designed in the generic block layer to count access frequency, and design a heat evaluation method base on access frequency and time weighting value. The strategy matching module build client-specific policy rules and common to all clients policy rules, and design a threshold dynamic adjustment algorithm based on Physical Volume (PV) occupancy and an algorithm based on the load balancing of storage nodes to apply PV . The data migration module design three kinds of data migration algorithms, which can achieve re-migrate at breakpoint: (1) the simple data migration algorithm (SCP), just read the data out from source volume then write to destination volume; (2) the algorithm base on the kernel copy thread (kcopy) in Device-mapper , which implement data consistency; (3) the algorithm base on SCP , in which read process and write process can execute parallel. In order to protect the data consistency in data migration, we design and analysis two kind of consistency methods: a method based on record-write strategy , an other method based on piecewise processing. Finally , concrete realization of a prototype of the data migration mechanisms, and do some test to data migration , focus on the speed of data migration , and the impact to users in data migration pro