Abstract | ||
---|---|---|
We propose a novel cluster parallel file system: high-throughput & scalable parallel file system (HTSPFS). There are some new features in it such as automatic adaptive file striping policy based on file size, request arrival rate, concurrent of accessing files, storage servers' networking and disk performance; prefetching read-request and writing behind write-request to enable a higher throughput in HTSPFS. We give a detail discuss of Markov spatial predicting method for read request, experiment results show that Markov predicting technology has high prediction veracity. Overall, HTSPFS has some autonomies characteristics |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/DEXA.2006.14 | DEXA Workshops |
Keywords | Field | DocType |
parallel processing,file size,cluster parallel file system,prediction veracity,concurrency control,high-throughput file system,experiment result,automatic adaptive,novel cluster,file organisation,high prediction veracity,markov spatial,workstation clusters,parallel file system,scalable parallel file system,request arrival rate,markov spatial predicting method,markov predicting technology,accessing file,autonomics characteristic,markov processes,automatic adaptive file striping policy,disk performance,high throughput | File system,Stub file,Self-certifying File System,Computer science,File size,Versioning file system,Unix file types,File system fragmentation,Operating system,Database,Computer file | Conference |
ISSN | ISBN | Citations |
1529-4188 | 0-7695-2641-1 | 0 |
PageRank | References | Authors |
0.34 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wenguo Wei | 1 | 0 | 1.35 |
Shou-Bin Dong | 2 | 139 | 21.17 |
Ling Zhang | 3 | 143 | 14.77 |
Jialin Li | 4 | 247 | 18.58 |