In a distributed file system built on network attached storage, client computers access data directly from shared storage, rather than submitting I/O requests through a server. Without a server marshaling access to data, if a computer fails or becomes isolated in a network partition while holding locks on cached data objects, those objects become inaccessible to other computers until a locking authority can guarantee that the lock holder will not again directly access these data. We describe a server that acts as the locking authority and implements a lease-based protocol for revoking access to data objects locked by an isolated or failed computer. When a lease expires, the server can be assured that the client no longer acts on locked data, and can safely redistribute locks to other clients. During normal operation, this protocol invokes no message overhead, and uses no memory and performs no computation at the locking authority.
|
1746
|
Time, clocks, and the ordering of events in a distributed system
– Lamport
- 1978
|
|
801
|
How to Make a Multiprocessor Computer that Correctly Executes Multiprocess Programs
– Lamport
- 1979
|
|
396
|
Coda: A highly available file system for a distributed workstation environment
– Satyanarayanan, Kistler, et al.
- 1990
|
|
366
|
Serverless network file systems
– Anderson, Dahlin, et al.
- 1996
|
|
219
|
Leases: An Efficient Fault-Tolerant Mechanism for Distributed File Cache Consistency
– Gray, Cheriton
- 1989
|
|
217
|
Frangipani: A scalable distributed file system
– Thekkath, Mann, et al.
- 1997
|
|
165
|
The LOCUS distributed operating system
– Walker, Popek, et al.
- 1983
|
|
142
|
Active disks: Programming model, algorithms and evaluation
– Acharya, Uysal, et al.
- 1998
|
|
123
|
A distributed per-sonal computing environment
– Morris
- 1986
|
|
112
|
File server scaling with network-attached secure disks
– Gibson, Nagle, et al.
- 1997
|
|
97
|
Active Storage for Large-Scale Data Mining and Multimedia Applications
– Riedel, Faloutsos, et al.
- 1998
|
|
92
|
Replication and fault-tolerance in the ISIS system
– Birman
- 1985
|
|
91
|
A case for intelligent disks (IDISKS
– Keeton, Patterson, et al.
- 1998
|
|
76
|
Relacs: a communications infrastructure for constructing reliable applications in large-scale distributed systems
– Babao˘glu, Davoli, et al.
- 1994
|
|
76
|
Swift: Using Distributed Disk Striping to Provide
– Cabrera, Long
- 1991
|
|
66
|
Deceit: A flexible distributed file system
– Siegel, Birman, et al.
- 1989
|
|
62
|
A case for network-attached secure disks
– Gibson, Nagle, et al.
- 1996
|
|
62
|
Processor Group Membership Protocols: Specification, Design and Implementation
– Jahanian, Fakhouri, et al.
- 1993
|
|
61
|
DEcorum file system architectural overview
– Kazar, Leverett, et al.
- 1990
|
|
57
|
Synchronization and caching issues in the Andrew file system
– KAZAR
- 1987
|
|
36
|
Fast Crash Recovery in Distributed File Systems
– Baker
- 1994
|
|
32
|
A high-performance multi-structured file system design
– Muller, Pasquale
- 1991
|
|
27
|
Overview of the Sun network file system
– WALSH, LYON, et al.
- 1985
|
|
24
|
A 64-bit, shared disk file system for Linux
– Preslan, Barry, et al.
- 1999
|
|
14
|
Implementation of the ficus replicated file system
– Page, Popek, et al.
- 1990
|
|
12
|
Recovery in the calypso file system
– Devarakonda, Kish, et al.
- 1996
|
|
4
|
The Zebra-Striped network file system
– Hartman, Ousterhout
- 1993
|
|
1
|
Collective consistency
– Dwork, Ho, et al.
- 1996
|
|
1
|
Nonblocking membership protocols with asymmetric safety
– Palmer, Strong, et al.
- 1997
|
|
1
|
Serverless network file
– Anderson, Neefe, et al.
- 1996
|
|
1
|
Crash Recovery in Distributed File Systems
– Fast
- 1994
|
|
