Showing papers on "Shared resource published in 2002"

Economic models for resource management and scheduling in Grid computing

Abstract: The accelerated development in peer-to-peer and Grid computing has positioned them as promising next-generation computing platforms. They enable the creation of virtual enterprises for sharing resources distributed across the world. However, resource management, application development and usage models in these environments is a complex undertaking. This is due to the geographic distribution of resources that are owned by different organizations or peers. The resource owners of each of these resources have different usage or access policies and cost models, and varying loads and availability. In order to address complex resource management issues, we have proposed a computational economy framework for resource allocation and for regulating supply and demand in Grid computing environments. This framework provides mechanisms for optimizing resource provider and consumer objective functions through trading and brokering services. In a real world market, there exist various economic models for setting the price of services based on supply-and-demand and their value to the user. They include commodity market, posted price, tender and auction models. In this paper, we discuss the use of these models for interaction between Grid components to decide resource service value, and the necessary infrastructure to realize each model. In addition to usual services offered by Grid computing systems, we need an infrastructure to support interaction protocols, allocation mechanisms, currency, secure banking and enforcement services. We briefly discuss existing technologies that provide some of these services and show their usage in developing the Nimrod-G grid resource broker. Furthermore, we demonstrate the effectiveness of some of the economic models in resource trading and scheduling using the Nimrod/G resource broker, with deadline and cost constrained scheduling for two different optimization strategies, on the World-Wide Grid testbed that has resources distributed across five continents.

Open platform architecture for shared resource access management

Abstract: An open platform architecture and methods for shared resource access management are provided. A redirection module in kernel space receives requests for access to resources from applications in user space. The redirection module routes signals representative of the received requests to a device driver interface in user space. Components of the device driver interface include resource management modules and device drivers that correspond to available resources. The resource management modules generate queries to the device drivers regarding availability of the requested resources. Upon receipt of resource status information from the device drivers, components of the device driver interface generate schedules for granting access to the requested resources. Further, the device driver interface components control access to the resources in accordance with the generated schedules including issuing responses to the requesting applications and the device drivers of the requested resources.

A model of hierarchical real-time virtual resources

Abstract: A real-time virtual resource is an abstraction for resource sharing where application task groups must meet timing constraints and knowledge of all the timing requirements may not be available for a global schedulability analysis, such as is the case in the open system environment. In a 2001 paper, we introduced the notion of a real-time virtual resource which operates at a fraction of the rate of the shared physical resource and whose rate of service provision varies with time but is bounded. The shared resource is partitioned into real-time virtual resources by a resource-level scheduler such that each real-time virtual resource is accessible only by an individual application task group; tasks within the same task group are scheduled by an application-task-level scheduler that is specialized to the real-time requirements of the tasks in the group. In this paper we propose a hierarchical real-time virtual resource model that permits resource partitioning to be extended to multiple levels. Through this model, partitions on each level are scheduled as if they had access to a dedicated resource and there is minimal interference between neighboring partition levels. We also investigate the partitioning of real-time virtual resources subject to scheduling quantum requirements.

Document service appliance

Abstract: A method and system for accessing a network-based document server application from a client An access point is defined within a local file system of the client A local file navigation interface allows a user of the client to interface to the access point such that the network-based document management system is accessed via the local file system of the client

Decentralized peer-to-peer advertisement

Abstract: Embodiments of a shared resource distributed index mechanism that peers in a peer-to-peer network may utilize to distribute index entries corresponding to resources to indexes of shared resources among one or more other peers. These indexes may be used to direct queries to peers where the queries are most likely to be answered. When a query is received by a rendezvous peer including one or more indexes, contents of the query may be “looked up” in the index to find matches. The results of the lookup may include information on one or peer(s) that may hold advertisement(s) to the resource requested by the query. The query may then be forwarded to one or more peers that may hold the advertisement for the resource. Embodiments may provide “loosely-coupled” distribution of index entries for use in querying for resources in the peer-to-peer network.

Building secure file systems out of byzantine storage

Abstract: This paper shows how to implement a trusted network file system on an untrusted server. While cryptographic storage techniques exist that allow users to keep data secret from untrusted servers, this work concentrates on the detection of tampering attacks and stale data. Ideally, users of an untrusted storage server would immediately and unconditionally notice any misbehavior on the part of the server. This ideal is unfortunately not achievable. However, we define a notion of data integrity called fork consistency in which, if the server delays just one user from seeing even a single change by another, the two users will never again see one another's changes---a failure easily detectable with on-line communication. We give a practical protocol for a multi-user network file system called SUNDR, and prove that SUNDR offers fork consistency whether or not the server obeys the protocol.

Storage management integrated system and storage control method for storage management integrated system

Abstract: It is intended to achieve an arrangement wherein, when file information of shared disks which are distributed in a plurality of computers connected to a network are used, operating conditions at the time of accessing shared disks can be defined, thus enabling users to easily share files without being bothered by setting-up, or operations of computers located on the other side when they are to perform file sharing. In order to achieve the above-stated arrangement, a storage management integrated server 100 is provided in a network, and respective computers register conditions, an accessibility states and use types pertaining to shared volume to be offered to the server. Thereafter, when a certain computer is to make a file accessing to a shared volume, the computer makes an inquiry to the storage management integrated server for an adequate access destination, determines, on the basis of a response from the server, computers which are suitable to the access source, and makes direct accesses to such computers.

Centrally enhanced peer-to-peer resource sharing method and apparatus

Abstract: A peer-to-peer network has a server that maintains a list of addresses of clients connected to the peer-to-peer network. The server generates seed lists for each of the clients connected to the network from the server maintained list. The clients conduct peer-to-peer searches using the seed list provided by the server. The seed lists may be either randomly generated or generated to facilitate network objectives. The clients may periodically request seed list refreshing. The peer-to-peer network may further include authentication and authorization search security checks.

Method and apparatus to allow remotely located computer programs and/or data to be accessed on a local computer in a secure, time-limited manner, with persistent caching

Abstract: A file system driver program executes on a local computer. One or more agent procedures is configured to execute on the local computer to access file resources on behalf of a target process. A security process regulates the access of file resources by the agent procedures. The regulation of the agent procedure by the security procedure is based on a property that is unique to the target process.

Large-Scale Newscast Computing on the Internet

Abstract: This paper introduces the newscast model of computation for large-scale computing on the Internet. The engine realizing this model is a lazy fully distributed information propagation protocol among the participants which is responsible for membership management and communication. It maintains a constantly changing communication graph over the participants. This graph has useful emergent properties like small diameter and sufficiently random structure without deploying special purpose protocols to achieve these properties. For adding a new participant only the address of an arbitrary member is needed and for removal no action is necessary. We provide theoretical and empirical evidence that—besides being simple and lightweight—our newscast computing engine is extremely scalable and robust. We also suggest some interesting application areas including information dissemination, monitoring of large systems, resource sharing and efficient multicasting.

Method to enable cooperative processing and resource sharing between set-top boxes, personal computers, and local devices

Abstract: A system and method for resource sharing are provided. The method includes storing an electronic programming guide (EPG) application and an EPG, determining when local memory of a local video device lacks capacity to download additional time of the EPG, and communicating with another device to transmit a resource request to the other device to download the additional time of the EPG to storage in the other device. The method also includes processing for display monitoring data that indicates remaining storage space in the storage of the other device, querying the other device to determine what programming is being viewed, and processing controls included in the EPG application that enable access to the storage of the other device to interact with the EPG stored on the other device through the local video device to schedule a programming event at the local video device.

Programming the Grid: Distributed Software Components, P2P and Grid Web Services for Scientific Applications

Abstract: Computational Grids [17,25] have become an important asset in large-scale scientific and engineering research. By providing a set of services that allow a widely distributed collection of resources to be tied together into a relatively seamless computing framework, teams of researchers can collaborate to solve problems that they could not have attempted before. Unfortunately the task of building Grid applications remains extremely difficult because there are few tools available to support developers. To build reliable and re-usable Grid applications, programmers must be equipped with a programming framework that hides the details of most Grid services and allows the developer a consistent, non-complex model in which applications can be composed from well tested, reliable sub-units. This paper describes experiences with using a software component framework for building Grid applications. The framework, which is based on the DOE Common Component Architecture (CCA) [1,2,3,8], allows individual components to export function/service interfaces that can be remotely invoked by other components. The framework also provides a simple messaging/event system for asynchronous notification between application components. The paper also describes how the emerging Web-services [52] model fits with a component-oriented application design philosophy. To illustrate the connection between Web services and Grid application programming we describe a simple design pattern for application factory services which can be used to simplify the task of building reliable Grid programs. Finally we address several issues of Grid programming that better understood from the perspective of Peer-to-Peer (P2P) systems. In particular we describe how models for collaboration and resource sharing fit well with many Grid application scenarios.

Network-based photosharing architecture for search and delivery of private images and metadata

Abstract: A method for executing searches for resources that span more than one private resource repository in a restricted-access resource sharing system is disclosed. The system includes at least one server node (12) and multiple peer nodes (16a-16d) connected to a network. Resources, such as data digital images, may be retrieved from the nodes based by issuing queries containing terms matching the metadata associated with the resources. The method includes maintaining storage of resources and associated metadata on respective peer nodes, wherein the associated metadata is based on at least one metadata vocabulary. Each of the peer nodes is allowed to indicate to the server that the metadata vocabularies associated with the resources are designated as private, thereby becoming a restricted access peer node. If a first restricted access peer node specifies to the server which metadata vocabularies the first restricted access peer node supports, a first level of privacy is provided whereby search queries received by the server that use the specified metadata vocabularies are passed to the first respective restricted access peer nodes for processing, while searches that do not use the specified vocabularies are processed by the server. If the first restricted access peer node does not specify to the server which metadata vocabularies the first restricted access peer node supports, a second level of privacy is provided whereby search queries received by the server are passed to the first respective restricted access peer nodes for processing.

Application-aware admission control and scheduling in Web servers

Abstract: This paper presents an architecture and algorithms for optimizing the performance of Web services. For a given service, session-based admission control is combined with stage-wise request queuing, where the stages represent sub-tasks within sessions. The scheduling of requests is governed by generalized processor sharing. We present a performance model, relying on online estimation of parameters describing client-server interaction. A reward function corresponding to the service provider's objective is maximized using techniques for nonlinear optimization. In a case study, we model and optimize the resource sharing at a Web server hosting an electronic store. The performance advantages of our approach are quantified numerically, and the robustness to parameter estimation errors is assessed by sensitivity analysis.

System and method for providing secure resource management

Abstract: System and method for providing secure resource management. The system includes a first device that creates a secure, shared resource space and a corresponding root certificate for the shared space. The first device associates one or more resources that it can access with the shared space. The first device invites one or more other devices to join as members of the space, and establishes secure communication channels with the devices that accept this invitation. The first device generates a member certificate for each accepting device, and sends the root certificate and the generated member certificate to the device through the secure channel. These devices may then access resources associated with the shared space by presenting their member certificates. Further, members of the shared space may invite other device to join the space, and may create member certificates in the same manner as the first device.

Secured and access controlled peer-to-peer resource sharing method and apparatus

Abstract: A peer-to-peer network propagates searches from client to client. Resources within each client are selectively searched in response to authentication and authorization processes. Authentication information may be included in a search request or may be performed by an authentication process external to the client. Authorization is performed by a process external to the client. Only after authentication or authorization may resources of any particular client be accessed. The system allows for secure propagated searches and resource access in a peer-to-peer network environment. The network may further include a server for maintaining a list of clients connected to the peer-to-peer network in order to more efficiently facilitate peer-to-peer communications.

A prediction-based real-time scheduling advisor

Abstract: The real-time scheduling advisor (RTSA) is an entirely user-level system that an application running on a typical shared, unreserved distributed computing environment can turn to for advice on how to schedule its compute-bound soft real-time tasks. Given a list of hosts, a description of the CPU demands of the task, the deadline, and a confidence level, the RTSA will recommend one of the hosts and predict, as a confidence interval, the running time of the task on that host. The RTSA is based on a scalable and extensible shared resource prediction system based on statistical time series analysis. The author first describes how the RTSA builds on this underlying system to provide its service, and then he evaluates its performance using a randomized methodology based on real background workloads, determining the effect of different factors. He also compares it with a random approach and a measurement-based approach.

Mirroring network data to establish virtual storage area network

Abstract: Mirroring data to provide a virtual storage area network (340) using policing protocols (311, 321) and mirror engines (317, 327) without a physical shared storage node. The mirror engines (317, 327) are found at each server computer (310, 320) in the network (301) in order to mirror the data between mass storage devices (319, 329) of the servers (310, 320) as the servers receive and execute write operations, which results in each mass storage device containing the same stored data. The policing protocols (311, 321) prevent data corruption by not allowing more than one server (310, 320) at a time write to a file of data. If one server (310, 320) experiences failure and is incapable of providing access to network data, the other server or servers can service all read requests, since all network data is accessible by all servers. Unlike conventional storage area networks, there is no physical shared storage node and, accordingly, the costs of obtaining and operating the virtual storage area network (340) are relatively small.

A Framework for Classifying Peer-to-Peer Technologies

Abstract: Popularized by Napster and Gnutella file sharing solutions, peer-to-peer (P2P) computing has suddenly emerged at the forefront of Internet computing. The basic notion of cooperative computing and resource sharing has been around for quite some time, although these new applications have opened up possibilities of very flexible web-based information sharing. This article provides a frame-work for classifying current and future P2P technologies. The main motivation for the classification is to identify basic characteristics of P2P applications so that the infrastructure to support P2P computing can concentrate on these basic characteristics.

Reliability analysis of grid computing systems

Abstract: Grid computing system is different from conventional distributed computing systems by its focus on large-scale resource sharing, where processors and communication have significant influence on grid computing reliability. Most previous research on conventional small-scale distributed systems ignored the communication time and processing time when studying the distributed program reliability, which is not practical in the analysis of grid computing systems. This paper describes the property of the grid computing systems and presents algorithms to analyze the grid program and system reliability.

Meta content distribution network

Abstract: A method for responding to a request for a file, comprising receiving a request for a file at a selection server for the selection server to select one of a plurality of content distribution networks based upon predetermined selection criteria, the request by a client system to a file server, the selection server, file server client system, and content distribution networks all connected to an Internet; and responding to the request by providing the file from the selected content distribution network to the client system.

A Web-Based Learning and Assessment System To Support Flexible Education.

Abstract: At a time where increased costs and resource constraints are experienced by many tertiary institutions globally, the pressure to find alternative methods to deliver teaching and assessment increases. Whilst the individual learning experience is paramount, the need to manage the numbers, resources and assessment provide an administrative overhead and headache to all teaching staff. With this predicament in mind a computer-supported learning system (CECIL) was developed. It is a web-based teaching and learning resource and administration system. This paper describes the CECIL structure and discusses the potential benefits that a university-wide resource management system may have in terms of the educational flexibility and resource sharing.

Concurrent process planning and scheduling in distributed virtual manufacturing

Abstract: With the fast development of the world economy, distributed virtual manufacturing is becoming increasingly important since it can respond rapidly to market changes and make resource sharing more efficient among manufacturing partners. In this environment, partners may be located at different geographical locations, and co-operation among partners is a vital task and thus concurrent planning and scheduling has become a challenging research topic. This paper presents a computerized model that can integrate these manufacturing functions and resolve some of the critical problems in distributed virtual manufacturing, such as virtual co-operation, optimal partner selection, etc. This integration model is realized through a multi-agent approach that provides a practical approach for software integration in a distributed environment. A cost function is proposed and adopted for optimal partner selection in a virtual enterprise, which not only considers a partner's manufacturing capability and process requirements, but also the processing time, partner's location and product due date. Through establishing a virtual manufacturing model in a simulated environment, the proposal was validated with a case study. It shows that the proposed methodology can satisfy the distribution and agility requirements. This approach is able to contribute to the reduction of product cost, improving product quality and shortening lead time, compared to the sequential approach in the normal engineering and production practice.

Exactly once cache framework

Abstract: A system for managing objects in a clustered network includes a file system containing at least one copy of a data object. The system can include several clustered servers in communication with the file system. A distributed consensus algorithm is used to select a host server. The selected host server can contain a copy of the data object, such as in local cache, providing access to the local copy to any other server in the cluster. Any change made to an item hosted by the host server can also be updated in the file system. If the host server becomes unable to host the object, a new host can be chosen using the distributed consensus algorithm. The other servers are then notified of the new host by multicast messaging.

System and method for wireless network admission control based on quality of service

Abstract: Admission to one or more shared resources in a wireless network is based on whether such admission would unduly comprise the network's ability to meet one or more Quality-of-Sevice (QoS) constraints associated with users of the shared resources. Therefore, use of a resource, such as the shared use of a high-speed packet data channel, may be scheduled for current and newly admitted users in consideration of the QoS constraints associated with those users. By evaluating the QoS penalty that would be incurred with the admission of a prospective new user, an admission controller determines whether such admission would unduly comprise an associated resource scheduler's ability to meet the QoS constraints associated with user's of the shared resource. Thus, new users are admitted or blocked based on the penalty incurred. Users may be preferentially admitted by tolerating higher penalties for some users, such as those in a preferred user class.

Method, system, program, and data structure for implementing a locking mechanism for a shared resource

Abstract: Provided are a method, system, program, and data structure for implementing a locking mechanism to control access to a shared resource A request is received to access the shared resource A determination is made of whether a first file has a first name The first file is renamed to a second name if the first file has the first name A second file is updated to indicate the received request in a queue of requests to the shared resource if the first file is renamed to the second name An ordering of the requests in the queue is used to determine whether access to the shared resource is granted to the request The first file is renamed to the first name after the second file is updated

Group-based management of distributed file caches

Abstract: We describe a way to manage distributed file system caches based upon groups of files that are accessed together. We use file access patterns to automatically construct dynamic groupings of files and then manage our cache by fetching groups, rather than single files. We present experimental results, based on trace-driven workloads, demonstrating that grouping improves cache performance. At the file system client, grouping can reduce LRU demand fetches by 50 to 60%. At the server cache hit rate improvements are much more pronounced, but vary widely (20 to over 1200%) depending upon the capacity of intervening caches. Our treatment includes information theoretic results that justify our approach to file grouping.

Grid Resource Discovery Based on a Routing-Transferring Model

Abstract: The Grid technology emerges with the need of resource sharing and cooperation in wide area Compared with the traditional single computer system, effective resource locating in Grid is difficult because of huge amount and wide-area distribution of dynamical resources In this paper, we propose a Routing-Transferring resource discovery model, which includes three basic roles: the resource requester, the resource router and the resource provider The provider sends its resource information to a router, which maintains this information in routing tables When a router receives a resource request from a requester, it checks routing tables to choose a route for it and transfer it to another router or provider We give the formalization of this model and analyze the complexity of the SD-RT (Shortest Distance Routing-Transferring) algorithm The analysis shows that the resource discovery time depends on topology (the longest path in the graph) and distribution of resources When topology and distribution are definite, the SD-RT algorithm can finda resource in the shortest time Our experiments also show that when topology is definite, the performance is determined by resource distribution, which includes two important factors: resource frequency andresource location The testing result shows that high frequency and even location of resources can reduce the resource discovery time significantly

Method, system, and program for managing locks enabling access to a shared resource

Abstract: Provided are a method, system, and program for managing locks enabling access to a shared resource. A first server receives a lock request from a client for the shared resource. A determination is made as to whether a second server owns the client locks. The first server issues a request to the second server to transfer ownership of the client locks to the first server, wherein the client lock requests are handled by the server owning the client locks.

Inter Java virtual machine (JVM) resource locking mechanism

Abstract: A system and method of sharing a resource includes receiving a request for a shared resource in a locking repository. The request is from a requestor and the requestor is one of several applications. Each of the applications is running on one of several Java virtual machines (JVMs). The shared resource is locked to the requester, if the shared resource is identified as available in the master locking repository.