Showing papers on "Shared resource published in 1983"

Shared resource matrix methodology: an approach to identifying storage and timing channels

Abstract: Recognizing and dealing with storage and timing channels when performing the security analysis of a computer system is an elusive task. Methods for discovering and dealing with these channels have mostly been informal, and formal methods have been restricted to a particular specification language. A methodology for discovering storage and timing channels that can be used through all phases of the software life cycle to increase confidence that all channels have been identified is presented. The methodology is presented and applied to an example system having three different descriptions: English, formal specification, and high-order language implementation.

Shared resource locking apparatus

Abstract: Disclosed is a hardware lock unit for limiting concurrent use of shared resources, such as segments of a memory, by a plurality of devices, such as processors, in a program controlled system. In such a system, devices wishing to use a shared resource make a use request to the lock unit by means of a memory READ command accompanied by an address that is associated in the lock unit with that resource, which each requesting device sends to the lock unit. The requesting devices then wait for an answer, as from a slow memory. The hardware lock unit determines whether the resource is free for access by a device, or whether the resource is busy being accessed by a device. When the resource is busy, the requesting devices are caused to wait. When the resource becomes free, the lock unit hardware selects one of the requesting devices and responds to its request to grant it exclusive use of the resource. When it is finished using the resource, the device notifies the lock unit to free the resource, by means of a memory WRITE command accompanied by the address that is associated in the lock unit with that resource, which the device sends to the lock unit. Additionally, the lock unit may include hardware for preventing a lockable resource from being accessed by a device that is not its current owner, and hardware for preventing the current owner from accessing the resource more than a predetermined number of times.

System intercommunication processor used in distributed data processing system

Abstract: A distributed data processing system including a general, communications network, and a plurality of local systems which each include a central processing unit, associated memory, and at least one peripheral device. The control of the intercommunication is effected by respective systems intercommunication processors, each attaching one local system to the network. Each SIP has a programmed processor, a local and a network interface, and a bidirectional buffer. The system intercommunications processor will provide for address and code parameter translation, resource requesting and allocating access granting and protecting of the local resources and information objects, while sharing resources among plural requesters. Also failure management and control panel simulation is effected by the systems intercommunications processor.

File Allocation in a Distributed Computer Communication Network

Abstract: An algorithm is presented to determine locations for the storage of copies of files in store-and-forward computer communications networks. The algorithm determines storage locations which minimize the sum of network file storage costs and message transmission costs. Networks that use adaptive routing techniques are the primary focus. Feasible file locations must satisfy network performance requirements for file availability and delay by message class. An effective method of evaluating delay constraints for networks using adaptive routing techniques is introduced. The algorithm uses the solution to a p-median problem to identify initial candidate file placements. Interaction between a set of file movement rules and a network simulator is employed to modify initial placements to fmd near-optimal locations which satisfy the network performance constraints.

MIKE: A Network Operating System for the Distributed Double-Loop Computer Network

Abstract: This paper presents the framework and model of a network operating system (NOS) called MIKE for use in distributed systems in general and for use in the Distributed Double-Loop Computer Network (DDLCN) in particular. MIKE, which stands for Multicomputer Integrator KErnel, provides system-transparent operation for users and maintains cooperative autonomy among local hosts.

Inference machine: From sequential to parallel

Abstract: In this paper, the research and development plan for computer architecture in the fifth generation computer system project ( FGCS Project) is described, focusing on the research on the inference machine.

Some Practical Simulations of Impractical Parallel Computers

Abstract: Many popular theoretical models of parallel computers suffer the drawback of being highly impractical. The aim of this paper is to examine simulations of two impractical parallel machine models (shared memory machines and networks of sequential processors) by two more practical models (uniform circuits and feasible networks). We give a single basic simulation theorem which epitomizes a number of related results in this area.

Issues of network transparency and file replication in the distributed filesystem component of locus (system)

Abstract: The advent of distributed systems has brought with it the opportunities for greater resource sharing and availability via resource replication and the problem of building distributed software. This dissertation addresses these issues in the light of new local area network hardware which has improved bandwidth, delay and error characteristics. Software principles are proposed for designing local area network operating systems. One of the major architectural approaches to ease software development in a distributed environment is network transparency, by which we mean both a global naming scheme for all resources in the network and a common interface for local and non-local resources so the collection of machines appears to users and applications as a single machine. Network transparency also facilitates data sharing. The principle of resource location transparency is analogous to and may be as significant as the principles of data independence in database design and virtual memory in operating system design. Automatic and yet selective resource replication can, when coupled with transparency, address the increasing need for higher availability. If one copy of a resource is unavailable, another may be used without the need for programs or users to be aware of the substitution. Two internal architectural principles are particularly significant. First is the idea of hiding the network interface deep within the operating system, transparent even to upper levels of the operating system code. Second is the idea of request/response protocols tailored for specific problems. To best demonstrate the viability and significance of these principles, an extensive case study was constructed and is presented. LOCUS, a highly transparent, efficient, general purpose distributed timesharing system, including replication of storage, was developed. It was based on Unix, is upward compatible with it, has been operational for two years and is the base for much of the distributed computing research at UCLA.

STORK: An Experimental Migrating File System for Computer Networks

Abstract: STORK is an experimental file system designed for local and long-haul networks. It ensures that each user has a single view of his flIes, independent of the network node where he works, and independent of the location of the files. STORK files have no fixed location; instead they migrate to the network node where they are needed. File consistency is ensured by permitting only one current copy of each file to exist in the net at any given time. A. .lock mechanism is provided for controlling concurrent access. The performance of the system depends on the locality of the references to a given file and not on the host where the file was created. An analytical model is presented that compares file migration with remote file access. STORK h~s been implemented on a network of UNIX systems running on VAXes and PDP-II's, using primitives of the Berkeley Network software. It can also be quickly installed on any network of UNIX systems allowing remote execution of commands.

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. Three different classes of interconnection networks have been investigated; namely, single shared bus, multiple shared buses, and networks with logarithmic delays such as the cube and Omega networks. For a given network, the resource mapping problem entails the search of one (or more) of the free resources which can be connected to each requesting processor. To prevent the bottleneck of sequential scheduling, the type(s) and number(s) of resources desired by a processor are given to the network and it is the responsibility of the network to find the necessary resources and connect them to the processor. The addressing mechanism is, thus, distributed in the network. This is a generalization of conventional interconnection networks with routing tags in which all the resources are of different types.

RM: A resource-sharing system for personal computers

Abstract: With the recent advances in personal computer technology, time-sharing of a processor is no longer a necessity; each user can have his own machine It is valuable, however, to share resources among the individual machines This paper discusses a system structure for interactive computing in which personal computers are connected by a local-area network for the purpose of resource sharing, and describes an experimental prototype that is being implemented using the IBM Personal Computer

An Interactive Simulation Facility for the Evaluation of Shared-Resource Architectures (Parallel ARchitecture SIMulator - PARSIM)

Abstract: A general-purpose, interactive simulation facility for modeling computational systems is described. The simulation facility is especially suited for evaluating the performance of parallel computational structures on workloads exhibiting arbitrary degrees of parallelism. Two different simulators are provided, one that operates at the processor level only, ignoring explicit system connectivity; and one that allows a detailed specification of system architecture and connectivity. Supplementing the simulators are: (a) a workload generator for synthesizing workloads exhibiting any desired degree of parallelism, and (b) a resource specification system that allows easy description of the capabilities and parameters of various resources in a system. Several graphical utility programs are provided to aid in interpretation of simulation results. The system has been implemented in the programming language 'C' on a Data General MV/8000 computer operating under the Data General Advanced Operating System; the system should port easily to other virtual architecture machines with a 'C' compiler.

Multiprocessor throughput with shared resource interference

Abstract: A stochastic model of throughput with interference for a system of n processors and m shared resources is developed which provides both individual processor and overall system throughputs. In addition, the model considers the influence of local processor resources, the bandwidth of shared resources, the priorities of processors, and the processor utilizations of each shared resource. To validate the model, experimental data collected on a three-processor, one shared-resource (memory) computer is compared to model predictions. Accuracy decreases as shared resource utilization and the number of processors increases. For utilization of 60-70percent, the error is less than 3percent, and at saturation (100percent) it increases to 10percent. Finally, a two-processor, three-shared-resource computer illustrates the shift in throughput as various model parameters change. 8 references.

Computer terminal memory performance in a resource sharing distributed supercomputing environment

Abstract: Computer terminal memory performance in a resource sharing distributed supercomputing environment is analysed with Erlang arrivals, synchronous transmission and single server random interruptions through a Bernoulli sequence of independent random variables. A new method to derive a closed expression for data arrivals with Erlangly distributed interarrival times is presented. A simple and easy approach to derive the steady state probability expressions of the terminal memory content process is presented. The memory performance is studied in terms of overflow probability and average queueing delay. The results portrayed on graphs will provide an insight about system response time and performance to the system designers.