VICT
发表于 2025-4-1 05:21:26
https://doi.org/10.1057/9781137382559 of . in minority components, logical conflicts in different components . one-copy serializability. We present an algorithm based on these ideas which achieves higher availability than other pessimistic protocols. This leads us to define a new concept for control as opposed to the traditional adaptation/recovery paradigm for replica control.
热情的我
发表于 2025-4-1 06:31:34
http://reply.papertrans.cn/29/2818/281714/281714_62.png
显赫的人
发表于 2025-4-1 13:45:56
Weak consistency and pessimistic replica control, of . in minority components, logical conflicts in different components . one-copy serializability. We present an algorithm based on these ideas which achieves higher availability than other pessimistic protocols. This leads us to define a new concept for control as opposed to the traditional adaptation/recovery paradigm for replica control.
artifice
发表于 2025-4-1 16:06:32
Distributed data structures: A complexity-oriented view,nd efficient access protocols. Among the issues treated are centerless organizations of data structures, background maintenance of memory balancing, employing redundancy for increasing search efficiency and concurrent accesses to distributed structures.
钉牢
发表于 2025-4-1 20:25:31
Optimal computation of global sensitive functions in fast networks,bal sensitive" functions in the case that the computation time is some given P, and the communication time is some given C. (Roughly speaking, a global sensitive function is one that depends on each of its inputs.)
清洗
发表于 2025-4-2 01:38:58
http://reply.papertrans.cn/29/2818/281714/281714_66.png
Vulvodynia
发表于 2025-4-2 03:45:24
Stepwise development of a distributed load balancing algorithm,First an abstract algorithm is presented and its safety and liveness properties are proved. Then a concrete, distributed algorithm is shown to correctly implement the abstract one. Experimental results of the transputer implementation are also reported.
寒冷
发表于 2025-4-2 08:45:41
Weighted voting for operation dependent management of replicated data,r the cases of one or two operations. We introduce a technique for reducing the number of operations considered in the analysis. Using this technique we extend the above results to all cases of three operations.