Consistency Without Ordering
| dc.contributor.author | Arpaci-Dusseau, Remzi H. | |
| dc.contributor.author | Arpaci-Dusseau, Andrea C. | |
| dc.contributor.author | Sharma, Tushar | |
| dc.contributor.author | Chidambaram, Vijay | |
| dc.date.accessioned | 2012-04-16T19:59:56Z | |
| dc.date.available | 2012-04-16T19:59:56Z | |
| dc.date.issued | 2012-01 | |
| dc.description | This is an extended version of the paper published in the 10th Usenix conference on File and Storage Technologies (FAST 12). | en |
| dc.description.abstract | Modern file systems use ordering points to maintain consistency in the face of system crashes. However, such ordering leads to lower performance, higher complexity, and a strong and perhaps naive dependence on lower layers to correctly enforce the ordering of writes. In this paper, we introduce the No-Order File System (NoFS), a simple, lightweight file system that employs a novel technique called backpointer-based consistency to provide crash consistency without ordering writes as they go to disk. We utilize a formal model to prove that NoFS provides data consistency in the event of system crashes; we show through experiments that NoFS is robust to such crashes, and delivers excellent performance across a range of workloads. Backpointer-based consistency thus allows NoFS to provide crash consistency without resorting to the heavyweight machinery of traditional approaches. | en |
| dc.identifier.citation | TR1709 | en |
| dc.identifier.uri | http://digital.library.wisc.edu/1793/61251 | |
| dc.subject | file-system consistency | en |
| dc.subject | file-system design | en |
| dc.title | Consistency Without Ordering | en |
| dc.type | Technical Report | en |