DocumentCode :
694741
Title :
Storage Space Reclaim Based on Cluster Bitmap in the New Technology File System
Author :
Chanying Qi ; Zhanhuai Li ; Xiao Zhang ; Huifeng Wang
Author_Institution :
Sch. of Comput. Sci., Northwestern Polytech. Univ., Xi´an, China
fYear :
2013
fDate :
7-8 Dec. 2013
Firstpage :
306
Lastpage :
312
Abstract :
Thin provisioning is widely used to improve the utilization ratio of storage space in the storage area network (SAN) environment. However, most of file systems only use the logical volume offered by iSCSI protocol and does not support automatic reclaiming the space of thin provisioning. The most major problem is that block-level storage device is difficult to perceive the release behavior of the host application storage space. In order to solve the problem, we implement thin provisioning iSCSI storage service system (ThinPro iSCSI Server) to reclaim the space in the NTFS file system. By analyzing the chart structure about cluster bitmap, the prototype can identify the released space in the NTFS file system automatically and efficiently. It uses flexible reclaim strategy to improve the performing in the reclaim process, which can alleviate the influence of extra I/Os. By confirming the data consistency before reclaiming the free space, it can avoid the data inconsistent problem and make the method practically and robustly. Empirical results show that the method can delay the time of the capacity warning and reclaim free space effectively. Moreover, it can improve the utilization rate of storage greatly.
Keywords :
data integrity; storage management; NTFS file system; ThinPro iSCSI server; capacity warning time delay; chart structure analysis; cluster bitmap; data consistency; flexible reclaim strategy; storage space reclaiming; thin provisioning iSCSI storage service system; Delays; File systems; Linux; Protocols; Recycling; Servers; Storage area networks; NTFS file system; SAN; coherence; reclaiming storage; thin-provisioning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Science and Cloud Computing Companion (ISCC-C), 2013 International Conference on
Conference_Location :
Guangzhou
Type :
conf
DOI :
10.1109/ISCC-C.2013.126
Filename :
6973609
Link To Document :
بازگشت