DocumentCode :
659506
Title :
suvfs: A virtual file system in userspace that supports large files
Author :
Bhat, Wasim Ahmad ; Quadri, S.M.K.
Author_Institution :
Dept. of Comput. Sci., Univ. of Kashmir, Srinagar, India
fYear :
2013
fDate :
6-9 Oct. 2013
Firstpage :
7
Lastpage :
11
Abstract :
As a consequence of voluminous growth and proliferation of digital data, the file system size and count limitations have become problematic. The fact is that file systems use fixed length fields within their metadata structures to keep track of volume size, file size and file count, and hence need design (and source) modification to cope up with this growth. In this paper, we propose a Scalable User-space Virtual File System, namely suvfs, which when mounted on top of any file system extends its capability to store and process large files not natively supported by the file system. It works by exploiting the concept of virtual unification to present a large virtual file that spans over a number of legitimate sized physical files. It does so without modifying user applications, system libraries, system calls and even file systems. We implemented it using FUSE framework & evaluated it for performance overhead added by layering it over FAT32 file system. The results indicate that there is a very minimal performance hit encountered by FAT32 with suvfs mounted on top for sequential reading, while as for sequential writing & deletion the performance hit increases with file size but is largely due to FUSE framework & not by suvfs.
Keywords :
data structures; meta data; FAT32 file system; FUSE framework; design modification; digital data; file count; file size; large files; legitimate sized physical files; metadata structures; scalable user-space virtual file system; sequential reading; sequential writing; suvfs; system calls; system libraries; user applications; virtual unification; volume size; Benchmark testing; Fuses; Kernel; Libraries; Scalability; Sprites (computer); Writing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Big Data, 2013 IEEE International Conference on
Conference_Location :
Silicon Valley, CA
Type :
conf
DOI :
10.1109/BigData.2013.6691655
Filename :
6691655
Link To Document :
بازگشت