A mechanism for synchronizing shared objects in a distributed system based on persistent, typed objects is presented. Synchronization constraints are expressed as separate control clauses and are factorized for a clas...
详细信息
A mechanism for synchronizing shared objects in a distributed system based on persistent, typed objects is presented. Synchronization constraints are expressed as separate control clauses and are factorized for a class of objects. the interference of this mechanism with inheritance and transactions is examined and solutions are proposed. Examples of synchronized objects are provided, and a semaphore-based implementation of the mechanism is described.< >
Synchronization algorithm is proposed which uses one of two probabilistic techniques to estimate remote clock values, and uses an interactive convergence algorithm on the resulting estimates to adjust the local clock....
详细信息
Synchronization algorithm is proposed which uses one of two probabilistic techniques to estimate remote clock values, and uses an interactive convergence algorithm on the resulting estimates to adjust the local clock. the algorithm does not require master/slave clocks and reduces the number of messages needed. As a result it is suitable for use in large distributed systems.< >
A language has been developed for queries which serves as an extension of the browsing model of hypertext systems. the query language and data model fit naturally into a distributed environment. A simple and efficient...
详细信息
A language has been developed for queries which serves as an extension of the browsing model of hypertext systems. the query language and data model fit naturally into a distributed environment. A simple and efficient method is discussed for processing distributed queries in this language. Results of experiments run on a distributed data server using this algorithm are presented.< >
this paper discusses the following: effective instrumentation as the key to effective monitoring; distributed monitoring systems as a basis for general purpose distributed multiprocessors; problems and prospects; perf...
详细信息
this paper discusses the following: effective instrumentation as the key to effective monitoring; distributed monitoring systems as a basis for general purpose distributed multiprocessors; problems and prospects; performance monitoring, fact and fancy; and software aspects.< >
A token-based mutual exclusion algorithm is presented which uses data structures similar to coteries, called quorum agreements. the performance of the algorithm depends on the quorum agreements used. When a good quoru...
详细信息
A token-based mutual exclusion algorithm is presented which uses data structures similar to coteries, called quorum agreements. the performance of the algorithm depends on the quorum agreements used. When a good quorum agreement is used, the overall performance of the algorithm compares favorably withthe performance of other mutual exclusion algorithms.< >
Concurrency in distributed systems is usually modeled by a non-deterministic choice, i.e., a concurrent execution that is a partial order on events is equated withthe set of total orders obtained from its interleavin...
详细信息
Concurrency in distributed systems is usually modeled by a non-deterministic choice, i.e., a concurrent execution that is a partial order on events is equated withthe set of total orders obtained from its interleavings. the validity of this interleaving (or global time) assumption is examined. A novel construction for atomic registers is presented; this construction is correct if the proof is based on partial orders, but is incorrect if all possible interleavings are confused with partial orders in the reasoning.< >
An interconnection topology that can be used to design communication architecture for distributed systems with an arbitrary number of computing nodes is proposed. the design is based on a novel generalization of the c...
详细信息
An interconnection topology that can be used to design communication architecture for distributed systems with an arbitrary number of computing nodes is proposed. the design is based on a novel generalization of the concept of star graphs. the proposed topology is shown to be incrementally extensible in steps of 1, optimally fault tolerant, and its diameter is sublogarithmic in the number of nodes.< >
A general framework is developed for reconfiguring applications dynamically, where developers may alter the application without loss of service. After presenting the overall framework within which reconfiguration is p...
详细信息
A general framework is developed for reconfiguring applications dynamically, where developers may alter the application without loss of service. After presenting the overall framework within which reconfiguration is possible, a description is given of the formal approach for programmers to capture the state of a process abstractly. An environment to support experimentation with dynamic reconfiguration is then described.< >
A token-based distributed mutual exclusion algorithm is presented. the algorithm assumes a fully connected, reliable physical network and a directed acyclic graph (DAG) structured logical network. the number of messag...
详细信息
A token-based distributed mutual exclusion algorithm is presented. the algorithm assumes a fully connected, reliable physical network and a directed acyclic graph (DAG) structured logical network. the number of messages required to provide mutual exclusion is dependent upon the logical topology imposed on the nodes. Using the best topology, the algorithm attains comparable performance to a centralized mutual exclusion algorithm; i.e., three messages per critical section entry. the algorithm achieves minimal heavy-load synchronization delay and imposes very little storage overhead.< >
Clouds LISP distributed environments (CLIDE) is a distributed, persistent object-based symbolic programming system being implemented on the Clouds distributed operating system. LISP environment instances are stored as...
详细信息
Clouds LISP distributed environments (CLIDE) is a distributed, persistent object-based symbolic programming system being implemented on the Clouds distributed operating system. LISP environment instances are stored as large-grained persistent objects, enabling users on many machines to share the contents of these environments through interenvironment evaluations. CLIDE provides a comprehensive research environment for distributed symbolic language, invocation and consistency semantics, and an implementation vehicle for the construction of the symbolic processing portions of complex megaprogrammed systems.< >
暂无评论