Granularity and semantic level of replication in the Echodistributed file system
Hisgen, A.; Birrell, A.; Jerian, C.; Mann, T.; Schroeder, M.; Swart, G.
Management of Replicated Data, 1990. Proceedings., Workshop on the
Volume , Issue , 8-9 Nov 1990 Page(s):2 - 4
Digital Object Identifier 10.1109/MRD.1990.138234
Summary:The choices for semantic level and granularity that have been made
in the Echo distributed file system are examined. The primary goals of
Echo are to explore issues of scaling, availability, and performance.
For scaling and uniformity of access, Echo provides a global,
hierarchical name space. Replication is used for availability.
Performance is achieved by distributed caching on clients and by using a
log on the file server to reduce disk seeks. The log also records
information about updates that are in progress, and this information is
used during crash recovery to bring all replicas into agreement. The
Echo hierarchical name space is structured as a collection of subtrees,
called echo volumes, that are glued together to form a single name
space. Each echo volume may be implemented by a different service, for
example, a name service or a file service. The file service component of
Echo is discussed
View citation and abstract |
Cart
