Showing papers on "Shared resource published in 1984"

Shared memory multiprocessing system & method

Abstract: When a first program executed on a first processor of a plurality of processors of a multiprocessing system intends to lock a given shared resource of a main memory in order to use same, if the desired resource is in use by a second program executed on a second processor, the first processor awaits an unlock signal which indicates that one of the shared resources is released for use. The first processor responds to the unlock signal and checks whether or not the desired resource is available. If not available, the first program again awaits the reception of the unlock signal, while if available, the first program accesses the desired resource to use same.

A Comparative Study of Distributed Resource Sharing on Multiprocessors

Abstract: In this paper we have studied the interconnection of resources to multiprocessors and the distributed scheduling of these resources. For a given interconnection network, the resource-mapping problem entails the search of one of the free resources which can be connected to each requesting processor. To prevent the bottleneck of sequential scheduling, a request without any destination address is given to the network, and the network is responsible for finding the necessary resource and connecting it to the processor. The addressing mechanism is thus distributed in the network. Three different classes of networks have been investigated: namely, single shared bus, multiple shared buses, and multistage dynamic networks. In each case, the scheduling algorithm is described, and the tradeoffs of different network configurations are studied. The resource-sharing networks are a generalization of conventional interconnection networks with routing tags in which all the resources are of different types.

Modeling file system organizations in a local area network environment

Abstract: This paper presents a modeling methodology for the design of file system organizations in a local area network environment. We first propose a characterization for the workload of typical business transaction systems, and then use this measurable characterization to derive input parameters for the file distribution graph models and the queuing network models that represent two completely different file system organizations, i.e., a file server-based file system and a distributed file system. Total system throughput and mean system response time are the indices used in comparing these two design approaches. An example of this comparison is given. It is shown that this methodology and these models are useful tools for the evaluation of certain design tradeoffs.

Selectors: High-Level Resource Schedulers

Abstract: Resource sharing problems can be described in three basically independent modular components. ? The constraints the resource places upon sharing because of physcal limitations and consistency requirements. ? The desired ordering of resource requests to achieve efficiency-either efficiency of resource utilization or efficiency of processes making the requests. ? Modifications to the ordering to prevent starvation of processes waiting for requests which might otherwise never receive service. A high-level nonprocedural language to specify these components of resource sharing problems is described. General deadlock and starvation properties of selectors are proven. Solutions to several classic resource sharing problems are shown to illustrate the expressiveness of this language. Proof techniques for this high-level language are introduced to show how to prove particular selectors are or are not deadlock and starvation free.

Time-constrained communication in multiple access networks (data communication, protocols)

Abstract: The characteristics of time-constrained communication applications, such as packetized voice, differ significantly from those of standard data communication applications. First, messages not received within a fixed amount of time after their generation at a sending station are considered lost. Secondly, a certain amount of message loss is tolerable. In this thesis we address the problem of supporting time-constrained communication applications in a multiple access network. The principal contributions of this thesis fall into two categories. The first contribution is the development and analysis of a new class of protocols for supporting multiaccess time-constrained communication. These protocols are based on a generalization of the time window mechanism and provide a family of network-wide message transmission scheduling disciplines based on message generation times. The problem of determining the optimal elements of the protocol's window selection policy is addressed. A semi-markov decision model is formulated for protocol operation and the optimal elements of the windowing policy are found to be both simple and intuitive. The extension of the protocol for transmitting both time-constrained and non-time-constrained messages is considered. In our scheme, time-constrained traffic, when transmitted, receives preemptive priority over other classes of traffic. Several novel analytic performance models are developed and validated through simulation. The protocol's time-constrained performance is found to critically depend on its imposed scheduling function and is significantly better under the optimal windowing policy elements than under other policy elements. For multiple classes of traffic, our results indicate that trading time-constrained message loss against the average delay of non-time-constrained traffic is not usually a viable option. The second major contribution of this thesis is the development of a systematic, formal approach towards distributed optimization via a fictitious resource sharing paradigm and a decentralized "microeconomic" solution to the resource sharing problem. This approach, which draws on previous work in mathematical economics, is successfully used to compute the optimum transmission probabilities for both the time window and Slotted Aloha protocols. Interestingly, several network mechanisms, such as flow control and priorities, are found to emerge naturally from this approach.

Assessing "Readiness for Resource Sharing" in an Academic Library

Abstract: In the last ten years, an abundance of writing has appeared on the need for cooperation, resource sharing, and networking. The terms themselves are not always well defined, although networking usually implies the use of computers and other telecommunication links. The consensus is that cooperation (resource sharing, networking) is an economic necessity. Resource sharing and cooperation are based on the assumption that academic libraries can no longer afford to be self‐sufficient—they cannot purchase all materials required to meet the needs of their curricula and related faculty research.

Development of resource sharing simulation system (rsss) : a computerized decision support system for library resource sharing networks

Abstract: Gives a historical perspective of libraries in industrially advanced countries developing complicated methods in order to meet the crisis, proliferation of publications, shrinking budgets and inflationary trends. Discusses the complex and turbulent management problems in operating a network. As the problems do not yield to algorithmic solutions, they are best handled heuristically. However a heuristic decision process is a result of "bounded rationality", introducing a break down of the manager's cognitive process when information demand of the management problem exceeds its information capacity. A computerised decision support system may improve heuristics. The paper describes a computerised decision support system developed by the School of Library and Information Science, University of Pittsburgh. This system works with modelling and simulation techniques to address the management problems associated with networking. Specific questions pertaining to economics of information transfer based on values, relating to the major relevant local vis-a-vis network parameters are also discussed.

On-Line Public Access Systems

Abstract: The advantages of the online public access catalog are discussed. A description is given of a typical search procedure used in consulting such catalogs, and suggestions appear concerning their use in networking and resource sharing. Finally, other forms of online public access, some yet to be realized, are mentioned.

The implementation of a GC/MS data system using DISNET: a Distributed Instrument System NETwork

Abstract: The primary goal of a computer network is to achieve resource sharing between several computers. Resource sharing is most easily performed at the application program level, with lower layers of software providing communications services. Application programs which make local data, peripherals, or processes available for shared use are defined as ’resource providers’. Application programs which require such res.ources from the network are defined as ’resource consumers’. This distinction helps the system designer identify the qualities of resource providers and consumers necessary to address data communication problems in a straightforward manner, while ensuring the effort invested will provide satisfactory solutions. We have developed this resource sharing protocol for the Distributed Instrument System NETwork (DISNET) to provide an environment suitable for the development and growth of a distributed system for real-time instrument control, data acquisition, and computation in a laboratory environment.

Impact of Automation on Acquisitions Functions

Abstract: Online order file arrangements are compared with manual arrangements and the advantages of the one over the other are indicated. The preparation of orders under the two arrangements is likewise considered, as are claiming and fund accounting, and further online possibilities such as agent performance monitoring and resource sharing are given attention.

DRAON : An Intelligent Local Area Network

Abstract: This paper discusses the design and fabrication of a local area network which keeps distributed systems off from system deadlocks in resource sharing with low overhead. We propose an Intelligent Network that exten由 the network concept in Its communication capability. This intelligent network provides the upper layer protocols, such a3 transport protocol and session protocol, which are normally carried out by host computers, and offers deadlock-free resource access method to its client, i.e., a distributed operating system. The design specification of DRAON, which is a kind of entirely di醜ributed controlled intelligent networks, i3 briefly introduced. DRAONア3 a network of intelligent nodes each of which performs communication procedures with high performance, and resource lock/unlock operations ln an inborn manner. Finally, an experimental resource sharing system using a prototype-DRAON is presented as an example of applications of loosely coupled distributed computing systems.

Resource controller tasks in ADA: Their structure and semantics

Abstract: The focus of this paper is on the processes that control access to shared resources in concurrent systems. Processes that access a shared resource send access requests to the controller of the shared resource which in turn services requests based on such criteria as the conditions enabling the requests, the fairness specified, etc. In this paper we examine the structure of resource controllers, in particular, we show how resource controllers manifest themselves in Ada. Our prime motivation for this work is to develop schemes by which controllers with complex resource control policies can be implemented using the tasking constructs of Ada. To enable the verification of Ada resource controllers, we provide a temporal semantics for the tasking constructs as well as for the resource controller components.

Combined resource-sharing algorithm

Abstract: The increasing use of multiprocessor systems in a variety of circumstances has highlighted a requirement for improved co-ordination algorithms for those systems where communication is via data structures in shared memory. In this paper, two classes of algorithm are described, and their principal characteristics are discussed. A hybrid algorithm having the advantages of both classes is then proposed. Finally, figures giving the performance of this algorithm on a four-processor shared-memory system are compared with those for alternative algorithms.

Intermittently Available Server, Priority Queues

Abstract: It is frequently the case in communications systems that transmission facilities are shared among a number of different sources. In Chapter 5, for example, time-division multiplexing is used to distribute transmission capacity among the sources sharing the same line. The allocation of resources in this case is fixed and is therefore unresponsive to the instantaneous needs of users. In this and in subsequent chapters we shall be examining techniques for sharing resources that respond to variations in instantaneous traffic levels. In this chapter sharing will be effected by granting priority to one class of users over another. As we shall see presently, this mechanism does not necessarily mean inequitable service.