Showing papers on "Shared resource published in 1997"

File server scaling with network-attached secure disks

Abstract: By providing direct data transfer between storage and client, network-attached storage devices have the potential to improve scalability for existing distributed file systems (by removing the server as a bottleneck) and bandwidth for new parallel and distributed file systems (through network striping and more efficient data paths). Together, these advantages influence a large enough fraction of the storage market to make commodity network-attached storage feasible. Realizing the technology's full potential requires careful consideration across a wide range of file system, networking and security issues. This paper contrasts two network-attached storage architectures---(1) Networked SCSI disks (NetSCSI) are network-attached storage devices with minimal changes from the familiar SCSI interface, while (2) Network-Attached Secure Disks (NASD) are drives that support independent client access to drive object services. To estimate the potential performance benefits of these architectures, we develop an analytic model and perform trace-driven replay experiments based on AFS and NFS traces. Our results suggest that NetSCSI can reduce file server load during a burst of NFS or AFS activity by about 30%. With the NASD architecture, server load (during burst activity) can be reduced by a factor of up to five for AFS and up to ten for NFS.

Method for electronic distribution and redemption of coupons on the world wide web

Abstract: A method and system for electronic distribution and redemption of coupons on a computer network. The method includes the steps of: providing an electronic coupon in the form of a machine readable computer file; permitting a user of a client machine to receive the computer file via the computer network when the user accesses a selected coupon distribution web site; storing the computer file on the client machine; and authorizing a benefit when the computer file is received by a selected coupon redemption web site via the computer network. The method can further include the steps of transmitting the computer file from the coupon redemption web site to the centralized computer facility; and verifying the authenticity of the computer file prior to authorizing the benefit.

Method and apparatus for resource allocation with guarantees

Abstract: A method and apparatus are provided for resource allocation with guarantees. A resource allocator is coupled to a controller. The resource allocator allocates resources between a plurality of arrival processes. A dedicated resource pool and a shared resource pool are provided. When an arrival process is identified, the resource allocator obtains a predefined characterizing value for the identified arrival process. Responsive to the obtained predefined characterizing value, resource from one of the dedicated resource pool or the shared resource pool is allocated to the arrival process. The controller is utilized for tracking resource use and for providing the predefined characterizing value for each of the plurality of arrival processes. The dedicated resource pool has a predetermined capacity greater than or equal to the total of all the low threshold values for each of the arrival processes. The dedicated resource pool provides the guarantees with the shared pool providing statistical multiplexed resource use. The controller increments a usage charge for the arrival process when a resource is allocated and decrements the usage charge at the end of use of the allocated resource. The controller evaluates use for the identified arrival process and updates the predefined characterizing value.

System for managing the configuration of multiple computer devices

Abstract: A system for managing the configuration of multiple computer devices over a network is provided in which each of the computer devices has memory for storing local configuration information and is configurable in accordance with its stored local configuration information. A file server in the system is connectable to each of the computer devices via the network. The file server has memory storing master configuration information for each of the computer devices. Each of the computer devices periodically connects via the network to the file server to provide a connected computer device. The connected computer device compares data characterizing its master configuration information at the file server with data characterizing its local configuration information to determine if its master and local configuration information are different. When one or more components of the master configuration information are determined different, such components are transferred from the file server to the connected computer device. The connected computer device revises its configuration in accordance with the transferred master configuration information. The computer devices may be part of a network system where such computer devices inter-operate with each other. This network system is properly configured for inter-operation when the local configuration information at each of the computer devices corresponds to their respective master configuration information at the file server. Local configuration information may be changed at the computer device, such changes are sent to the file server for review to determine whether to revise the master configuration in accordance with such changes.

Sharing the “cost” of multicast trees: an axiomatic analysis

Abstract: Given the need to provide users with reasonable feedback about the "costs" their network usage incurs and the increasingly commercial nature of the Internet, we believe that the allocation of cost among users will play an important role in future networks. This paper discusses cost allocation in the context of multicast flows. The question we discuss is this. When a single data flow is shared among many receivers, how does one split the cost of that flow among the receivers? Multicast routing increases network efficiency by using a single shared delivery tree. We address the issue of how these savings are allocated among the various members of the multicast group. We first consider an axiomatic approach to the problem, analyzing the implications of different distributive notions on the resulting allocations. We then consider a "one-pass" mechanism to implement such allocation schemes and investigate the family of allocation schemes such mechanisms can support.

Resource sharing between real-time and general purpose programs

Abstract: The present invention provides a method, system, and program product for sharing resources between real-time and non-real-time (or general purpose) programs in a computer system which utilizes Slotted Priority Architecture. Non-pre-emptable, internally triggered resources are shared using the method of the present invention. The real-time scheduler anticipates upcoming realtime minor cycles and, using knowledge of which resources are to be used by the next scheduled real-time task and of the latency times of the resources to be used, signals the device drivers for the resources to be used to stop accepting requests from general purpose tasks far enough in advance to the beginning of the real-time minor cycles that will utilize them to ensure that the resources will be idle and available for the real-time tasks to use without delay.

Exploiting locality for data management in systems of limited bandwidth

Abstract: This paper deals with data management in computer systems in which the computing nodes are connected by a relatively sparse network. We consider the problem of placing and accessing a set of shared objects that are read and written from the nodes in the network. These objects are, e.g., global variables in a parallel program, pages or cache lines in a virtual shared memory system, shared files in a distributed file system, or pages in the World Wide Web. A data management strategy consists of a placement strategy that maps the objects (possibly dynamically and with redundancy) to the nodes, and an access strategy that describes how reads and writes are handled by the system (including the routing). We investigate static and dynamic data management strategies.

Electronic document delivery system

Abstract: A document, preferably in a portable format, is forwarded to a remote server ( e.g. using HTTP to push the document to the server). The server sends a generic notification of the document to an intended recipient, and the recipient can download the document from the server using local protocols. A method and system is also provided that sends documents from a desktop computer inside an intranet through a series of firewalls and/or proxy servers to a server residing on the Internet. A computer in an intranet system protected by a firewall or proxy server uses a software application to access the Internet. The software also encodes binary data to be sent as text. This binary data may be subdivided into smaller text packets. The text packets are sent, using HTTP, to a server outside the firewall, which has been configured to accept such text packets. The server converts the text packets back to the original binary data representation. The binary data, once resident on the internet server, can then be forwarded directly to other internet servers, internet desktop computers, printers, or fax machines. A document delivery server is also provided that dynamically customizes the format of a document to be delivered, based on the capabilities of the recipient and the type of document to be delivered. The server attempts to maintain the information contained in the document in a high level representation and deters the decision of when to convert to a lower level representation, thereby maximizing the potential set of options and function at each step in the delivery process.

Method and system for locking resources in a computer system

Abstract: Methods and systems are provided for providing locking in a system. The resource objects of the system can be persistent, and thus provide finer granularity locking by allowing shared resource objects to be dynamically allocated and de-allocated. The persistent nature of the resource objects allows for the dynamic allocation and de-allocation of the resource objects, while guarding against the abnormal release of resource locks that result in the possibility of inconsistent data. If abnormal release occurs, the affected resource object(s) are marked to indicate that they are in a "dubious" state. The dubious resource objects are not dynamically de-allocated, but are instead allowed to persist until corrective or validation actions are taken. If the locks are validly released, then the resource objects can be safely de-allocated. In this manner, fine granularity locks can be created to cover minute portions of the shared system resources for some duration, without excessively incurring system overhead and memory.

Adaptation in distributed multimedia systems

Abstract: The real-time requirements of continuous media call for careful resource management in distributed multimedia systems. In complex and mobile systems, however, effective resource reservation becomes almost impossible. Recent research suggests adaptive applications as a complementary solution. This article reviews heterogeneous networks and the rationale behind adaptation, gives implementation examples, and discusses some outstanding research issues.

An Architectural Overview Of The Alpha Real-Time Distributed Kernel

Abstract: Alpha is a non-proprietary experimental operating system kernel which extends the realtime 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-criticalThe 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

Shared memory arbitration apparatus and method

Abstract: An apparatus and method for arbitrating requests for access to a shared resource. A buffer, on command from control logic, can selectively couple or decouple two buses. The control logic uses signals from two logic devices, one of which may be a microprocessor, and one of which may be a communications interface, to determine which of the devices is granted access to the shared resource. The control logic can generate an inhibit signal to the microprocessor to stall it while the second logic device is accessing the shared resource. Handshaking is used to control access by the second device to the shared resource.

Atomic resource sharing in noncooperative networks

Abstract: In noncooperative networks, resources are shared among selfish users, which optimize their individual performance measure. We consider the generic and practically important case of atomic resource sharing, in which traffic bifurcation is not implemented, hence each user allocates its whole traffic to one of the network resources. We analyze topologies of parallel resources within a game-theoretic framework and establish several fundamental properties. We prove the existence of and convergence to a Nash equilibrium. For a broad class of residual capacity performance functions, an upper bound on the number of iterations till convergence is derived. An algorithm is presented for testing the uniqueness of the equilibrium. Sufficient conditions for achieving a feasible equilibrium are obtained. We consider extensions to general network topologies. In particular, we show that, for a class of throughput-oriented cost functions, existence of and convergence to a Nash equilibrium is guaranteed in all topologies. With these structural results at hand, we establish the foundations of a design and management methodology, that enables one to operate such networks efficiently, in spite of the lack of cooperation among users and the restrictions imposed by atomic resource sharing.

Resource sharing facility functions as a controller for secondary storage device and is accessible to all computers via inter system links

Abstract: A method and architecture for sharing data items using a resource sharing facility with a medium level cache accessible to all of the computers which are to share and connected to the computers by fast intersystem links. The resource sharing facility also acts as an ordinary secondary storage controller and in the resource sharing facility the control information and logic is provided which is needed for the mapping of cache data to the secondary storage and vice versa.

System and method for enabling a target computer to use storage resources of a host computer

Abstract: A system and method for a target computer to use a storage device of its host computer and in particular for bootstrapping an operating system from the storage device onto the target computer. The computer system comprises a host computer coupled to a target computer via an I/O bus. In one embodiment the target computer is an embedded system comprising an intelligent data acquisition device. The host computer includes a disk drive with a file system and a file which serves as a virtual disk drive for the target computer, i.e., the file is essentially an image of a disk drive which would otherwise be coupled to the target computer. The target computer may be a BIOS level IBM-compatible personal computer. The target computer includes an option ROM with an int13H handler which hooks the disk service routine software interrupt vector of the target computer and forwards INT 13H requests to a device driver executing on the host computer via a shared memory on the target computer. The device driver converts the sector address specified in the INT 13H request input parameters into an offset into the virtual disk file and reads the data from the file to the shared memory. The int13H handler copies the data from the shared memory to its local memory, in the case of a read request, or from its local memory to the shared memory, in the case of a write request. The operating system booted onto the target computer may be different from the operating system executing on the host computer.

Sharing Resources through Advance Reservation Agents

Abstract: We propose an architecture where clients can make advance reservations through agents responsible for advance admission control The agents allocate resources in the routers just before they are needed for packet forwarding In this paper we show that network resources can be shared between immediate and advance reservations without being pre-partitioned The admission control schemes for immediate and advance reservations still operate with little interaction

Efficient spare-resource allocation for fast restoration of real-time channels from network component failures

Abstract: Since real-time applications usually require not only timeliness but also fault-tolerance, it is essential to incorporate fault-tolerance into real-time communication services that are indispensable to distributed real-time applications. The techniques for failure recovery in datagram communication are not adequate for real-time communication, because they cannot provide recovery-delay guarantees. To ensure fast recovery of a real-time channel from network component failures, we need to reserve network resources (spare resources) along a backup route before failures actually occur. The focus of this paper is on minimizing the amount of spare resources while meeting the fault-tolerance requirement. Specifically, we present resource sharing mechanisms and backup-route selection algorithms, and evaluate their efficiency with extensive simulations.

Fast restoration of real-time communication service from component failures in multi-hop networks

Abstract: For many applications it is important to provide communication services with guaranteed timeliness and fault-tolerance at an acceptable level of overhead. In this paper, we present a scheme for restoring real-time channels, each with guaranteed timeliness, from component failures in multi-hop networks. To ensure fast/guaranteed recovery, backup channels are set up a priori in addition to each primary channel. That is, a dependable real-time connection consists of a primary channel and one or more backup channels. If a primary channel fails, one of its backup channels is activated to become a new primary channel. We describe a protocol which provides an integrated solution to the failure-recovery problem (i.e., channel switching, resource re-allocation, ...). We also present a resource sharing method that significantly reduces the overhead of backup channels. The simulation results show that good coverage (in recovering from failures) can be achieved with about 30% degradation in network utilization under a reasonable failure condition. Moreover, the fault-tolerance level of each dependable connection can be controlled, independently of other connections, to reflect its criticality.

Generalized resource sharing

Abstract: Resource sharing is one of the main tasks in high-level synthesis, and although many algorithms have addressed the problem there are still several limitations which restrict the generality and applicability of current algorithms. Most clique-partitioning-based algorithms use local and inaccurate cost-functions which result in inefficient results. This paper presents algorithms for the resource sharing problem on registers and functional units, and shows how they overcome the limitations of existing algorithms. The main characteristics of this work are: interleaved register and functional unit merging in a global clique partitioning based framework, accurate merging cost estimation, accurate interconnect cost estimation, relative control cost taken into account and efficient false loop elimination. The results obtained show significant improvements in the delay of designs, while also minimizing area, specially for large designs with many sharing possibilities.

Networked file operations for computer numerical controls

Abstract: A networked system combines multiple workstations, storage devices and file handlers with multiple computer numerical controls. Typically, each workstation comprises a personal computer with a Windows-based operating system utilizing a standard process-to-process communication protocol, such as Dynamic Data Exchange (DDE). This type of system allows a wide variety of M-to-N topologies in CNC environments. Further, the use of a file management system, according to the present invention, allows the activation and execution of part program operations at a computer numerical control on files accessed through standard open networks.

Methods, systems and computer program products for preemptive avoidance of constraints for shared resources

Abstract: Methods, systems (apparatus) and computer program products are provided which control access to a shared resource in a data processing system by predicting utilization of the shared resource based upon historical utilization of the shared resource. Users of the shared resource are then notified of a potential shortage of the shared resource if the prediction predicts that the shared resource will be over-utilized. The prediction may utilize a linear extrapolation to predict future utilization of the share resource. Furthermore, the interval between predictions of the future utilization may be based on time, number of utilization events or a combination of the two.

System and method for synchronizing disparate processing modes and for controlling access to shared resources

Abstract: A system and method for synchronizing disparate processing modes and for providing mutually exclusive access to shared system resources. A processing unit operates in disparate first and second processing modes. In the first processing mode, the computer is under the control of an operating system. In the other processing mode, the computer is under the control of a system management mode interrupt handling routine. To synchronize the two processing modes and allow mutually exclusive access to shared hardware resources, the computer system includes shared memory, which contains an intermodal lock, and a mechanism for allowing each processing mode to signal the other. Before either processing mode can access the shared resource, the processing mode must attempt to acquire the intermodal lock. If the lock is acquired, the processing mode accesses the shared resource. If the lock cannot be acquired, the processing mode sets a pending bit and resumes other tasks until it receives a lock release signal from the other processing mode. When a processing mode has finished accessing the shared resource, it releases the lock and checks to see if the pending bit was set. If so, the processing mode sends a lock release signal to the other mode.

System and method for networking a computer numerical control with a workstation

Abstract: A system combines an open control interface workstation, e.g., a properly configured personal computer, with a networked computer numerical control. The personal computer and CNC are preferably linked to a local area network such as an Ethernet network. The open control interface is configured to utilize Windows DDE, or other protocol, to accomplish process-to-process communications with other DDE-compliant Windows applications. Additionally, the open control interface is designed to allow DDE-compliant Windows applications to communicate with one or more networked computer numerical controls while minimizing data flow over the network.

Method for controlling a computer system including a plurality of computers and a network processed as a user resource

Abstract: In a computer system including a plurality of computers interconnected through a network, a specific computer A in the computer system manages the computer resource information and the operating condition information such as for a CPU, a file and a memory and the user resource information such as file data and a program of each computer of the computer system. When a user issues a request from a computer C to log in to the computer system, the request is reported to the computer A, and the information related to the user is returned to the computer C with reference to the user resource information held by the computer A. Then, the computer C acquires the file and the usable program held by the user in the computer system and executes a process, whereby the whole system can be used as resources of each user.

Building the Infrastructure of Resource Sharing: Union Catalogs, Distributed Search, and Cross-Database Linkage.

Abstract: Effective resource sharing presupposes an infrastructure which permits users to locate materials of interest in both print and electonic formats. Two approaches for providing this are union catalogs and Z39.50-based distributed search systems. The advantages and limitations of each approach are considered, paying particular attention to a realistic assessment of Z39.50 implementations. This article argues that the two approaches should be considered complementary rather than competitive. Technologies to create linkage between the bibliographic apparatus of catalogs and abstracting and indexing databases and primary content in electronic form; such as the new Serial Item and Contribution Identifier (SICI) standard are also discussed as key elements in the infrastructure to support resource sharing.

Using an index and count mechanism to coordinate access to a shared resource by interactive devices

Abstract: Th present invention coordinates access to a shared resource, comprised of a plurality of segments, between a first device and a second device using an index and count mechanism The present invention includes a respective descriptor, for each of the plurality of segments Entries to the respective descriptors of the segments are maintained by the first device to inform the second device of activity between the first device and the shared resource The present invention also includes a descriptor queue register, coupled to the first device and the second device The first device writes an index into the descriptor queue register for indicating a starting descriptor of a corresponding segment that is available to the second device for access The first device also writes a count into the descriptor queue register for indicating a subsequent number of descriptors, from the starting descriptor, of any corresponding segments that are available to the second device for access By thus using this index and count mechanism, the second device does not poll the descriptors to determine any available segments within the shared resource thereby substantially eliminating bandwidth, delay, and data processing overhead associated with the polling process of the prior art The present invention can be used to particular advantage when the first device is a CPU of a computer host system having a shared memory which is the shared resource and when the second device is a computer network peripheral device that couples the computer host system to a network of computers

Method and apparatus for modification of network link histories

Abstract: A method and implementing system 101, are provided in which a computer system is arranged for connection 210 to a network system such as the Internet. A user of the computer system may selectively display 401 a listing of network data path and site history files from previous network sessions, and select one or more items from the list for modification 407, 409, 411. The user may then modify the current history file by creating 411, 701 a new current history file. A new current history file may also be modified by exchanging 407, 501 or appending 409, 601 the selected and modified selected items with the current history file to create a new current history file. The newly created history file then includes data paths and/or portions thereof, which were successfully used in previous network sessions.

Method and apparatus for implementing bandwidth allocation with a reserve feature

Abstract: A method for accessing a shared resource is provided. An assigned usage rate is received from a resource coordinator and a desired usage rate is determined. When it is determined that the desired usage rate is higher than the assigned usage rate, a shared resource may be accessed at an enhanced usage rate if a usage reserve has been accumulated. When a shared resource is accessed at an enhanced usage rate, the usage reserve is decremented by an amount based on a difference between the enhanced usage rate and the assigned rate. When there is no usage reserve accumulated, access to the shared resource is limited to the assigned usage rate. When the desired usage rate is not higher than the assigned usage rate, a shared resource is accessed at the desired usage rate. When the desired usage rate is less then the assigned usage rate, the usage reserve is accumulated up to a reserve maximum. The reserve maximum may be based on configuration data.

Resource Sharing in a Changing Ohio Environment

Abstract: Starting from the assumption that significantly expanded resource sharing will be a dominant feature of all twenty-first century libraries, this article identifies five milestones or landmarks which can be used to identify key tasks and chart progress. Joining a consortium, integrating intellectual access, providing for both physical and electronic delivery of materials, and integrating the collection development process are steps illustrated with primary reference to the OhioLINK (OL) experience. This article focuses on clearly identifying major issues in resource sharing and illustrating possible solutions with actual examples. The intent, however, is to educate and facilitate ongoing discussion rather than propose final answers.

Accessing a Data File in a Data Communication Network

Abstract: A mobile user terminal for accessing a data file stored in a server computer system in a data communications network comprises a reader for reading a network address identifying the data file from a machine readable label. A transmitter in the user terminal requests, via a wireless communication link, access to the data file on receipt of the network address from the label. The user terminal further comprises a receiver for receiving the data file from the server via the wireless communication link and output means for outputting the data file to a user.