Showing papers on "Shared resource published in 1994"

Systems and methods for sharing resources in a multi-user environment

Abstract: Multi-user system includes a server connected to one or more workstations or "clients" through a computer network. System provides concurrent access to shared resources (e.g., common data structures residing on the server), but without the disadvantage attendant with conventional mutual exclusive (mutex) primitives. Specifically, the system provides a "nested mutex" mechanism, so that user program code can acquire and release mutexes without concern for deadlocking and without special processing for testing a particular mutex condition or state. At the same time, the system prevents other threads or processes from accessing the shared resource in a manner which would violate concurrency.

System and method for multi-level token management for distributed file systems

Abstract: A system and method for controlling access to shared resources in a distributed computer system. Access to shared resources is controlled by a local authorization token manager. Only computer processes holding authorization tokens for the requested operation may perform that operation. Each requested operation checks for the proper token. If the token is not held by the process, it is requested. The local token manager resolves token conflicts before granting tokens. A token manager of a distributed file system export protocol also is able to request authorization tokens from the local token manager. The export protocol token manager controls authorization tokens for that particular distributed file system protocol. Multiple different export protocols may request tokens from the local token manager. The shared resources may therefore be shared by multiple different export protocols without conflict. Local processes and processes requesting shared resource operations through an export protocol that does not itself manage tokens are granted tokens through the operation token request mechanism. This mechanism enables local processes to use shared resources without the performance penalty of having to request through a local distributed client process.

System and method for allocating a shared resource among competing devices

Abstract: Apparatus and method for establishing "virtual connections" through a packet switched data communications network, the network including a plurality of end systems and switches connected by links. Each end system has a unique physical layer address and each switch has a connection database of valid connections between different ports on the switch and a switching mechanism for establishing temporary connections. Each switch is registered with a connection server such that, prior to transmission of a connectionsless datagram from a first end system to a second end system, a path of valid remains as a connectionless datagram. In other aspects, an improved method is provided for allocating bandwidth among competing devices requesting access to a bandwidth limited shared resource (e.g., the previously defined switch), and to a search method for making a best path determination through the network based on a number of constraints.

Method and system for providing a group of parallel resources as a proxy for a single shared resource

Abstract: A method and system for providing a group of parallel resources as a proxy for a single shared resource is provided. In a preferred embodiment, a resource grouping facility ("the facility") is incorporated in a "non-global" operating system. A non-global operating system is an operating system that is unable to respond correctly to a request to allocate a global resource of a particular type, such as a memory block, that can be accessed by every program executing in conjunction with the operating system. Instead, a non-global operating system allocates a putatively global resource that may not be accessed by every program executing in conjunction with the non-global operating system. When the facility detects that a transferor program is attempting to share a putatively global resource allocated by the operating system with a transferee program, the facility allocates a proxy resource that is accessible to the transferee. The facility may also allocate one or more intermediate resources accessible to other programs. The facility tracks the putatively global resource and all of the proxy resources as a proxy group. In a preferred embodiment, the facility also copies characteristics of the putatively global resource to the proxy resources. For example, where the putatively global resource and the proxy resources are a memory block, the facility preferably copies the contents of the putatively global memory block to the proxy memory blocks. When the facility detects that a program is attempting to deallocate a member of the proxy group, that is, a putatively global resource or one of its proxies, the facility preferably deallocates each member of the proxy group.

Efficient resource placement in hypercubes using multiple-adjacency codes

Abstract: While a certain resource in the hypercube may be shared by cube nodes to lower the cost, multiple copies of a shared resource often exist in the hypercube to reduce contention, and thus the potential delay, in fetching any shared copy It is desirable that one employs as few resource copies as possible to ensure that every node is able to reach the resource in a given number of hops, achieving efficient resource placement This placement method also keeps system performance degradation minimal after one resource copy becomes unavailable due to a fault First, we consider placing multiple copies of a certain resource in a way that every cube node without the resource is adjacent to a specified number of resource copies The use of our developed perfect and quasiperfect multiple-adjacency codes makes it possible to arrive at efficient solutions to this placement problem in a simple and systematic manner for an arbitrary hypercube We then deal with the generalized resource placement in the hypercube such that every node without the resource can reach no less than a specified number of resource copies in no more than a certain number of hops, using as few resource copies as possible Our placement results yield lowest potential access contention for a given number of resource copies (ie, cost), particularly useful for large-scale hypercubes >

Distributed file systems: focus on Andrew File System/Distributed File Service (AFS/DFS)

Abstract: Currently, there is a move away from huge, monolithic mainframe computers to smaller, individual workstations. This move requires that data and programs be shared between individual users on the same computer as well as across machines on a local area network (LAN) or even on a wide area network (WAN). A popular distributed file system is Transarc's Andrew File System (AFS), the precursor of the Open Software Foundation's (OSF) Distributed File Service (DFS), part of OSF's Distributed Computing Environment. This paper compares AFS and DFS with other successful distributed file systems, discussing clients and file servers, data cache (cache consistency and authentication), file system topology, access rights, privileged programs, critical data, and authentication in long-running batch jobs. >

Transfer labeling mechanism for multiple outstanding read requests on a split transaction bus

Abstract: A labelling method and system are disclosed for correlating multiple outstanding requests to utilize a shared resource issued by a particular master of a computer system. The labelling system includes a memory for storing an assigned indication corresponding to each label assigned by each master of a computer system. The memory is also for indicating a label available for assignment which is unique over each outstanding, unsatisfied request to utilize the shared resource issued by each master of the computers system. The labelling system also includes a first circuit which is responsive to the unique label indicated by the memory. The first circuit is provided for assigning the unique label indicated by the memory to a request to utilize the shared resource issued by the particular master in which the labelling system is located.

Resource sharing in distributed robotic systems based on a wireless medium access protocol (CSMA/CD-W)

Abstract: Resource sharing is crucial in any multi-agent systems, a distributed robotic system (DRS) is not an exception A new, general strategy of sharing multiple, discrete resources with predetermined capacities under the model of distributed robotic systems (DRS) is proposed It is based upon a media access protocol, CSMA/CD-W (Carrier Sense Multiple Access with Collision Detection for Wireless), which supports wireless inter-robot communication among multiple autonomous mobile robots without using any centralized mechanism This resource sharing strategy is derived based on the fact that with the single, time-multiplexed communication channel, asynchronous events for requesting and releasing resources are effectively serialized It is shown that the control protocol is effective, efficient, reliable and robust >

Comparison of virtual path bandwidth assignment and routing methods

Abstract: The virtual path (VP) can simplifyAtm network management by minimizing connection routing and admission costs, and by facilitating the layered control of resources. However, fully exploiting these advantages may lead to a large number of relatively low capacity virtual paths travelling on each physical link. If each VP is treated as a separate unit, as is commonly assumed, low path capacities will lead to low network utilisation. This paper carefully examines the trade-off between simplification through traffic separation and improved efficiency due to traffic consolidation. We review existing vp bandwidth assignment and control techniques, and propose a new vp tagging control method. A comparison shows that by permitting resource sharing between paths it is possible to influence significantly the trade-off between simplified network management and multiplexing gain from traffic consolidation.

RHODOS — A Microkernel based Distributed Operating System: An Overview of the 1993 Version *

Abstract: The current direction of computer systems is increasingly moving away from centralised system and moving towards distributed sets of workstations and personal computers connected by a network, known as distributed systems. This has led to the development of specialised operating systems to take full advantage of the resource sharing potential that a distributed system provides. The specialised operating systems being developed for these situations are known as Distributed Operating Systems. Research into this area is still at the primary stage with little firm evidence indicating what components of Distributed Operating systems are more important than others. RHODOS is a microkernel based distributed operating system that has been designed and detailed from the study of a number of existing Distributed Operating Systems. The primary object of RHODOS is to enable the study and testing of all components that combine to form a distributed operating system and not just a limited few. This paper introduces the architecture of RHODOS, highlighting the benefits envisaged by our design and the extra research areas we consider important that are not being investigated by other builders of distributed operating systems.

Failure recovery for a distributed processing shared resource control.

Abstract: Communicating the failure of a master process controlling one or more shared resources to all processes sharing the resources. A shared resource control file is established that contains the identities of all sharing processes. Master process failure triggers a race to establish exclusive access over the shared control file. The new master reads shadow address data from the old shared control file, marks it as invalid and establishes a new control file based on renewed registrations from processes. The master process maintains the sharing process list as process begin and end sharing.

Session management for distributed multimedia applications

Abstract: The Touring Machine system is a software infrastructure that supports the development and deployment of distributed multimedia applications in a public network environment. This paper describes the design of the session management service in the Touring Machine system (Arango, 1993). A session is a temporary confederation of one or more parties for the negotiated and cooperative sharing of resources. The session management service is useful for a large class of distributed multimedia applications (such as desktop conferencing, shared editing, and distance education) to create and manage multiple concurrent multi-party, multimedia communication sessions using a common set of protocols and mechanisms. Although the communication models implemented by these applications are very different from each other, the mechanics of adding and deleting session members, and of setting up the transport topology have much in common. Rather than re-inventing and re-implementing the same mechanism for each application, it is desirable for the underlying infrastructure to provide a session management service that can be customized to be used by all applications to manage multi-party, multimedia communication sessions.

Shared resource control in a distributed processing system.

Abstract: A system and method for determining a master process for control of a shared system resource. The improved system requires the master process to hold exclusive access on a shared resource control file only intermittently. The master process periodically updates the shared resource control file with a new timestamp. Processes seeking resource access read the shared control file and determine whether another process has been designated master. If the interval since the latest timestamp is greater than a preset staleness interval, the shared control file is discarded and a new one created by the accessing process.

Models for performance evaluation of a local area network with a file server

Abstract: We consider a system of single user workstations connected to a file server over a local network. Users arrive at random intervals and occupy a workstation if one is available otherwise leave the system. Upon arrival, the user issues a request for file transfer from the server to the workstation local memory. Subsequent requests for additional transfers are issued in a random manner as needed. We consider two priority schemes for scheduling the two types of requests at the file server. Assuming that all relevant intervals are exponentially distributed, we propose two queueing models for the two scheduling schemes and develop computational procedures to analyze the performance of the system. Illustrative examples are presented to study the system behavior under various load conditions and to compare the performance of the two scheduling disciplines.

The adaptive cycle cell insertion MAC protocol for high throughput and fair multiaccess networks

Abstract: This paper deals with a MAC protocol suitable for data traffic in a twin bus high speed LAN/MAN. Its main features are the possibility of distributed buffering of the information units propagating along the busses and a decentralized traffic-adaptive access-cycle mode of operation. These features ensure both high throughput-delay performance and fair resource sharing. A complete description of the ACCI protocol is given, with and without prioritized traffic handling. The performance evaluation is obtained by simulation. It mainly focuses on a LAN interconnection scenario, representing a bursty traffic environment, where the backbone network adopts the ACCI protocol. The results suggest that, to reach a performance close to the theoretical limits, LAN frames should be transmitted by individual cells rather than by contiguous cells. Moreover, considerable insight is gained in the network buffers dimensioning.

Alpha: A Non-Proprietary Realtime Distributed Operating System For Mission Management Applications

Abstract: Alpha is a non-proprietary experimental operating system kernel which extends the real-time domain to encompass distributed applications, such as for telecommunications, factory automation, and defense. Distributed real-time systems are inherently asynchronous, dynamic, and non-deterministic, and yet are nonetheless mission-critical. The increasing complexity and pace of these systems precludes the historical reliance solely on human operators for assuring system dependability under uncertainty. Traditional real-time OS technology is based on attempting to assert or impose determinism of not just the ends but also the means, for centralized low-level sampled-data monitoring and control, with an insufficiency of hardware resources. Conventional distributed OS technology is primarily based on two-party client/server hierarchies for explicit resource sharing in networks of autonomous users. These two technological paradigms are special cases which cannot be combined and scaled up cost-effectively to accommodate distributed real-time systems. Alpha’s new paradigm for real-time distributed computing is founded on best-effort management of all resources directly with computation completion time constraints which are expressed as benefit functions; and multiparty, peer-structured, trans-node computations for cooperative mission management.

Method and system for sizing a packet switched network

Abstract: Method and system for sizing of an entity, such as a communications network. In the preferred embodiment, the system is a PC-based (10) data-driven interactive computational tool for the sizing of packet switched networks. The method includes the step of defining an input screens text file, a calculation processing text file, and a report format text file, each of which are user-modifiable. The method also includes the steps of entering (42), by a user, network sizing data to the computer in response to predefined input queries (62) related to network requirements contained in the input screens file, and calculating (44) the number of network components according to the process calculation file utilizing the entered network sizing data so as to determine the size of the network. The method also includes generating a network sizing report (46) of the number of network components according to the report format file and configuring the network based on the network sizing report.

Method and equipment for arbitrating access to shared resource and communicating method and equipment and micro-computer device

Abstract: PURPOSE: To arbitrate the access of a multiprocessor to a shared resource applicable to multiprocessor communication CONSTITUTION: Each shared resource is provided with an access request and access permission register which stores an access request and access permission semaphore The access request and access permission semaphore is provided with several access request and access permission bits assigned to a processor Moreover, each access request register is provided with a circuit which sets/ clears each access request bit, and simultaneously reads all the access request bits of the stored access request semaphore Moreover, the processor is provided with a cooperative request and permission mask reflecting the relative access priority order of the processor for judging whether or not the shared resource is permitted to a processor whose priority order is low, or whether or not the shared resource is requested by a processor whose priority order is high

Shared resource control system

Abstract: PURPOSE:To enable efficient control over shared resources by dynamically determining and changing control systems during the operation of a system. CONSTITUTION:The shared resources 1 are decentralized to plural computers. A resource control part 2 accesses to the shared resources 1 at a request from a program (process) which operates on each computer, performs some process, and sends the result back to the program. Further, the resource control part 2 sends access characteristics such as the frequency and locality of the access to a history managing part 3 and dynamically changes the control system of the shared resources 1 by an instruction from a system determination part 5. The history managing part 3 gathers and holds characteristics of the access to the shared resources by respective resource control parts 2. A prediction part 4 predicts future access characteristics basing on the history that the history control part 3 has. The system determination part 5 determines an optimum shared resource control system according to the prediction result of the prediction part 4 and sends instructions to the resource control parts 2.

Benefits and Problems of Networking Participation: A Case Study of Central Road Research Institute, New Delhi

Abstract: Time seems to be right for Indian libraries and information centres to join networks in greater numbers to overcome the issues such as budget constraints, information explosion, increase in cost of publications, and to utilize information available in machine-readable form worldwide. Telematics, the newly developed information technology - a combination of computers with telecmmunications - has been considered to be very promising technology for computer networking. Applications of Telematics in computer networking and its components have been discussed. Benefits of computer networking in terms of resource sharing, speed of information retrieval, retrenching the limit of the distance, etc. have been highlighted. Further experiences of Central Road Research Institute (CRRI), New Delhi, a premier R&D organisation engaged in a wide variety of research programmes on highway engineering and related subjects, using its own Local Area Network and other two networks, viz., DELNET and SIRNET have been discussed in terms of hardware, communication softwares, LAN components and utilities (e.g. peer to peer communication and E-mail). The use of LAN with client server architecture, its potential benefits in library automation such as inter-library loan, quick reference, catalogue search facility through E-mail, file transfer and correspondence with member libraries, and problems, namely, non-availability of databases at member libraries, standardization of information, security, limited staff and cost of hardware and software have been discussed in particular for library and information applications.

Recovery system in loose coupling electronic computer system

Abstract: PURPOSE:To prevent a shared resource from being simultaneously used by plural electronic computers at the time of fault occurance in a loose coupling electronic computer system allowing plural electronic computers to share the shared resource in accordance with the control of a shared resource exclusive control device. CONSTITUTION:An electronic computer 20 outputs normal use information to the shared resource exclusive control device 10 at each time within a fixed time. When the detection of the normal use information is disabled, the device 10 judges the generation of a fault in the computer 20 or a connection pass 41 and outputs fault information to an electronic computer 30. Thereby the computer 30 requests the disconnection of the device 10 and the shared resource 15 to the computer 20. In response to the request, the computer 20 forcedly sets up the connection passes 41, 43 to an unusable state and then outputs disconnection completion information to the computer 30. Upon receiving the disconnection completion information, the computer 30 requests the device 10 to release the resource occupied by the computer 20.

Shared Resource Assistive Systems

Abstract: Conventional assistive technology uses a dedicated device for each consumer, with specialized input, processing, and output components built into a single unit. This article describes a new way of providing assistive technology to people with disabilities, built on shared use of remote technical resources, based on the rapid evolution of telecommunications networks. The approach may have functional, clinical, and economic advantages in some situations.