| Mogul, Jeffrey C., "A Recovery Protocol for Spritely NFS," USENIX File System Workshop Proceedings, Ann Arbor, MI, USENIX Association, Berkeley, CA, May 1992. Second paper on Spritely NFS proposes a lease-based scheme for recovering state of consistency protocol. |
....system is that, as much as applications do not rely on the file system as a fully trusted partner in their recovery, distributed file systems do not rely on the clients ability to tolerate failures to improve their own reliability and performance. For instance, several distributed file systems [5, 28, 16, 17, 18, 24] rely on recovery protocols that use information provided by clients to restore the state of a faulty server s cache. These protocols for server recovery, however, are not designed for environments in which (1) clients cooperate in distributed applications and (2) clients attempt to recover to a ....
J.C. Mogul. A Recovery Protocol for Spritely NFS. In USENIX File Systems Workshop Proceedings, pages 93--109, May 1992.
....[Macklem91] are applicable to NFS Version 3. NFS Version 3 relaxes the 8KB limitation on the data portion of a READ or WRITE request, permitting more efficient use of TCP. Three efforts to revise the NFS protocol are related to this work. The first is Spritely NFS, described in [Srinivasan89] [Mogul92], and [Mogul93] Spritely NFS uses a stateful server that controls client caching behavior to ensure consistency. State recovery following a crash is server driven. The server keeps a nonvolatile list of old clients that are contacted during a grace period following reboot to initiate the ....
Mogul, Jeffrey C., "A Recovery Protocol for Spritely NFS," USENIX File System Workshop Proceedings, Ann Arbor, MI, USENIX Association, Berkeley, CA, May 1992. Second paper on Spritely NFS proposes a scheme for recovering state in a consistency protocol.
....clients which the clients have lost in crashes. Later when the server sends revoking calls to which the clients simply reply that they do not have it any more. A recovering server, however, has to recover the exact state it had before the crash. It appears that a server centric approach as done in [12] would work well. Under such a scheme, a recovering server directs its clients to help rebuild the lost server state. It has also been noted that such frequently updated and small amount of volatile state is a good candidate for inclusion in a stable memory that can survive machine crashes and the ....
J. Mogul. A Recovery Protocol for Spritely NFS. Proceedings of the USENIX Workshop on File Systems, May 1992.
....1 and so during the next few years, several people participated in a discussion of possible alternatives. In early 1992, I finally worked out a relatively pleasing recovery design, based in large part on more recent work done on Sprite recovery [1] this paper design was presented at a workshop [18]. That summer, an initial implementation of the recovery protocol was done by Bharat Shyam, an intern at my lab. Subsequently, I continued the implementation work to the point where the recovery protocol now works reliably and efficiently. 1 Mary Baker, Cary Gray, Rick Macklem, John Ousterhout, ....
....identically to NFS servers. In principle, we can establish rules that allow Spritely NFS hosts to detect when their peers change flavor (i.e. upgrade from NFS to Spritely NFS, or change from Spritely NFS back to NFS) Some speculations on how this might be done were presented in an earlier paper [18]. 3.6. Consistency between Spritely NFS and NFS clients A Spritely NFS server should provide consistency between NFS and Spritely NFS clients write sharing a file (as much as possible) The server does this by treating each NFS RPC referencing a Spritely NFS file as if it were bracketed by an ....
[Article contains additional citation context not shown here]
Jeffrey C. Mogul. A Recovery Protocol for Spritely NFS. In Proc. USENIX File System Workshop, pages 93-109. Ann Arbor, MI, May, 1992.
No context found.
Mogul, Jeffrey C., "A Recovery Protocol for Spritely NFS," USENIX File System Workshop Proceedings, Ann Arbor, MI, USENIX Association, Berkeley, CA, May 1992. Second paper on Spritely NFS proposes a lease-based scheme for recovering state of consistency protocol.
No context found.
Mogul, Jeffrey C., "A Recovery Protocol for Spritely NFS," USENIX File System Workshop Proceedings, Ann Arbor, MI, USENIX Association, Berkeley, CA, May 1992. Second paper on Spritely NFS proposes a lease-based scheme for recovering state of consistency protocol.
No context found.
Mogul, Jeffrey C., "A Recovery Protocol for Spritely NFS," USENIX File System Workshop Proceedings, Ann Arbor, MI, USENIX Association, Berkeley, CA, May 1992. Second paper on Spritely NFS proposes a lease-based scheme for recovering state of consistency protocol.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC