By Topic

Management of Replicated Data, 1990. Proceedings., Workshop on the

Date 8-9 Nov. 1990

Filter Results

Displaying Results 1 - 25 of 30
  • Proceedings. Workshop on the Management of Replicated Data (Cat. No.90TH0329-3)

    Publication Year: 1990
    Request permission for commercial reuse | PDF file iconPDF (582 KB)
    Freely Available from IEEE
  • Communication substrate for maintaining replicated data

    Publication Year: 1990, Page(s):125 - 127
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (168 KB)

    A fault-tolerant system is proposed for maintaining replicated data that is implemented from a set of fundamental building blocks. At the heart of the modular design is the PSYNC communication protocol. PSYNC is an interprocess communication protocol that explicitly preserves the partial order of messages exchanged among a set of processes in the presence of host and network failures. Fundamentall... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Analysis of replication control protocols

    Publication Year: 1990, Page(s):117 - 121
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (272 KB)

    In recent years, many replication control protocols have been proposed, but too often these protocols are presented with insufficient evidence to demonstrate superiority over existing protocols. Some simple analytical tools that allow replication control protocols to be compared are presented. Markov analysis is used to estimate both availability and reliability performance measures. A dynamic vot... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Maintaining availability of replicated data in partition-prone networks

    Publication Year: 1990, Page(s):108 - 112
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (380 KB)

    The results of investigations into the design of replica control protocols for maintaining availability of replicated data are discussed. Protocols that tolerate not only site failures, but also network partitions were studied. Only pessimistic protocols that maintain availability without sacrificing one-copy serializability have been considered. Pessimistic schemes can be classified as being stat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Consistency control of replicated data in federated databases

    Publication Year: 1990, Page(s):130 - 132
    Cited by:  Papers (4)  |  Patents (17)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (184 KB)

    The effective use of distributed databases requires a proper balance between autonomy and coordination. A critical decision influencing the autonomy of local sites concerns the method for update propagation to replicated data. An identity connection model is designed to specify replication, permissible delay in the consistency of copies, and data derivation rules. This model allows the nature of t... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Highly redundant management of distributed data

    Publication Year: 1990, Page(s):91 - 95
    Cited by:  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (308 KB)

    An algorithm for redundant management of distributed data using a minimal amount of data replication is described and analyzed. The main results on storage space utilization, I/O (input/output) performance, and reliability are outlined. The recently introduced RAID (redundant array of inexpensive disks) concept is extended to a distributed computing system. The resulting distributed storage archit... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Deceit: a flexible distributed file system

    Publication Year: 1990, Page(s):15 - 17
    Cited by:  Papers (26)  |  Patents (18)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (152 KB)

    Deceit, a distributed file system that provides flexibility in the fault-tolerance and availability of files, is described. Deceit provides many capabilities to the user: file replication with concurrent reads and writes, a range of update propagation strategies, automatic disk load balancing and the ability to have multiple versions of a file. Deceit provides Sun Network File Server (NFS) protoco... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Some (naive?) questions about replica control

    Publication Year: 1990, Page(s):113 - 116
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (252 KB)

    Some questions about replica control in database systems are posed. They are concerned with the definition of availability, statistics for replica control algorithm comparison, pessimistic and optimistic algorithms, and the one-copy serializability as a correctness measure View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Replication in Ficus distributed file systems

    Publication Year: 1990, Page(s):5 - 10
    Cited by:  Papers (18)  |  Patents (35)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (376 KB)

    Ficus is a replicated general filing environment for Unix intended to scale to very large (nationwide) networks. The system uses an optimistic one copy availability model in which conflicting updates to the file system's directory information are automatically reconciled, while conflicting file updates are reliably detected and reported. The system architecture is based on a stackable layers metho... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Management of interdependent data: specifying dependency and consistency requirements

    Publication Year: 1990, Page(s):133 - 136
    Cited by:  Papers (15)  |  Patents (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (232 KB)

    Multiple databases that serve the needs of various application systems are considered. One of the significant problems in managing these databases is to maintain the related data items consistent to the required degree. This problem is frequently referred to as `redundant data management'. Since the term `redundancy' tends to imply that the data is unwanted or superfluous, the authors use the more... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Replicated data management in the Gamma database machine

    Publication Year: 1990, Page(s):79 - 84
    Cited by:  Papers (2)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (448 KB)

    To help ensure availability of the system in the event of processor and/or disk failures, the Gamma database uses an availability technique termed chained declustering. Like Tandem's mirrored disk (MD) mechanism and Teradata's interleaved declustering mechanism, chained declustering uses both a primary and backup copy of each relation. All three systems can sustain the failure of a single processo... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Coping with conflicts in an optimistically replicated file system

    Publication Year: 1990, Page(s):60 - 64
    Cited by:  Papers (4)  |  Patents (11)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (292 KB)

    Coda is a scalable distributed Unix file system that provides high availability through the use of two distinct but complementary mechanisms. One mechanism, server replication, stores copies of a file at multiple servers. The other mechanism, disconnected operation, is a mode of execution in which a caching site temporarily assumes the role of a replication site. Disconnected operation is particul... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Managing replicated copies in very large distributed systems

    Publication Year: 1990, Page(s):39 - 42
    Cited by:  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (248 KB)

    Data management in very large distributed systems (VLDS) is considered. A replication strategy that can offer a tradeoff between cost and quality of service is discussed. Imperfect replicated data, called quasi-copies, are considered in conjunction with the notion of file stashing. Stashing a file means placing copies of that file in several nodes of a computer network to augment the availability ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Reliability of replicated files in partitioned networks

    Publication Year: 1990, Page(s):98 - 101
    Cited by:  Papers (3)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (236 KB)

    Before replication can become a practical way to improve the reliability of general-purpose file systems, robust low-cost methods must be available. The reliability provided by a novel consistency control algorithm, suitable for networks which may become partitioned, is compared to that provided by other schemes. The extent to which the reliability of replicated files is affected by the communicat... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • New asynchronous atomic broadcast protocols

    Publication Year: 1990
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (56 KB)

    Presents three protocols for atomically broadcasting updates to the global state of a highly available service implemented by a team of replicated processes. The protocols are designed for asynchronous systems where no upper bounds exist on message transmission and process scheduling delays. The authors let correct team members that have achieved timely communication in the recent past form dynami... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A replicated Unix file system

    Publication Year: 1990, Page(s):11 - 14
    Cited by:  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (312 KB)

    An implementation of a replicated Unix file system for use via the NFS protocol is reported. The replication method is intended to support the following goals: when used via NFS, the system should provide the same semantics as an unreplicated NFS server, and it should be usable with whatever NFS client code exists at the client machine; the system should not depend on proprietary information; the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Replicated K-resilient objects in Arjuna

    Publication Year: 1990, Page(s):53 - 58
    Cited by:  Papers (14)  |  Patents (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (720 KB)

    The design of an object replication scheme for the Arjuna distributed system is described. The design supports K-resiliency, where, in the absence of network partitions, K out of a total of K+1 replica failures can be tolerated before an object becomes unavailable. The scheme chosen uses active replication, in which each and every functioning replica of an object carries... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Lazy replication: exploiting the semantics of distributed services

    Publication Year: 1990, Page(s):31 - 34
    Cited by:  Papers (20)  |  Patents (4)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (288 KB)

    The need for high availability in distributed services requires that the data managed by the service be replicated. A major challenge in managing replicated data is ensuring consistency among the copies of the data. One way to guarantee consistency is to force operations to take effect in the same order at all sites. This approach, however, is often expensive. A novel method is designed for constr... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Valued redundancy

    Publication Year: 1990, Page(s):76 - 78
    Cited by:  Papers (1)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (220 KB)

    The idea of valued redundancy for the complex memory hierarchies of the gigabit networks of tomorrow is introduced. The goal of valued redundancy is to replicate only the most valuable objects in the system, i.e. those that contribute the most to system performance and availability. The objects value explicitly represents its cost/performance ratio for the redundancy management system. In this way... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The case for controlled inconsistency in replicated data

    Publication Year: 1990, Page(s):35 - 38
    Cited by:  Papers (9)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (304 KB)

    Although replication is widely accepted as a good technique for increasing reliability and availability of data, it is also known as an expensive proposition, especially when the number of replicas increases. Protocols that keep the copies consistent, such as two-phase commit, require one or more rounds of messages and have a high overhead in the overall performance. There are some applications th... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An analysis of replication strategies for X.500-like distributed directories

    Publication Year: 1990, Page(s):137 - 142
    Cited by:  Patents (15)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (472 KB)

    The X.500 standard for distributed directories is now in its second cycle of definition and is close to completion. There is, however, much work remaining regarding issues of replication. The success of the standard is predicated on a workable replication strategy. The authors look at replication algorithms in the context of X.500-like distributed directories, report on the performance of some, an... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Type-specific replication algorithms for multiprocessors

    Publication Year: 1990, Page(s):70 - 74
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (348 KB)

    The use of replication for enhancement of the availability of data in multiprocessor systems is discussed. The author explores theoretical aspects of the extent to which it is possible to exploit the semantics of data to make replication more effective. Some of the literature is surveyed, and some opinions about appropriate models and interesting open questions are presented. In particular, linear... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Efficient techniques for replicated data management

    Publication Year: 1990, Page(s):48 - 52
    Cited by:  Papers (2)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (336 KB)

    Data replication in distributed systems is considered. Two approaches are developed to partially mitigate the costs associated with replicated data management. The first approach, termed the views protocol, is developed to address the concern of practitioners who reject the quorum protocol since it requires that a read operation be executed on more that one copy. The second approach organizes the ... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Implicit replication in a network file server

    Publication Year: 1990, Page(s):85 - 90
    Cited by:  Papers (7)  |  Patents (8)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (320 KB)

    The design and implementation of a highly available network file server (HA-NFS) is reported. It is implemented on a network of workstations from the IBM RISC System/6000 family. HA-NFS servers preserve the semantics of the NFS protocol and can be used by existing NFS clients without modification. Therefore, existing application programs can benefit from highly availability without alteration. HA-... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Increasing file system availability through second-class replication

    Publication Year: 1990, Page(s):65 - 69
    Cited by:  Papers (1)  |  Patents (30)
    Request permission for commercial reuse | Click to expandAbstract | PDF file iconPDF (340 KB)

    High availability in the Coda file system is achieved through two types of data replication: first-class replication, in which entire servers are replicated, and second-class replication, otherwise known as client caching. The two are complementary: server replication increases the availability of the entire file store, whereas caching permits operation in the event of total disconnection. A parti... View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.