Active Transaction - Explore the Science & Experts | ideXlab

Scan Science and Technology

Contact Leading Edge Experts & Companies

Active Transaction

The Experts below are selected from a list of 72 Experts worldwide ranked by ideXlab platform

Active Transaction – Free Register to Access Experts & Abstracts

Christopher R. Lumb – One of the best experts on this subject based on the ideXlab platform.

  • Towards higher disk head utilization : extracting “free” bandwidth from busy disk drives
    , 2018
    Co-Authors: Christopher R. Lumb
    Abstract:

    Abstract: “Freeblock scheduling is a new approach to utilizing more of disks’ potential media bandwidths. By filling rotational latency periods with useful media transfers, 20[50% [sic] of a never-idle disk’s bandwidth can often be provided to background applications with no effect on foreground response times. This paper describes freeblock scheduling and demonstrates its value with two concrete applications: free segment cleaning and free data mining. Free segment cleaning often allows an LFS file system to maintain its ideal write performance when cleaning overheads would otherwise cause up to factor of 3 performance decreases. Free data mining can achieve 45 – 70 full disk scans per day on an Active Transaction processing system, with no effect on Transaction performance.

  • towards higher disk head utilization extracting free bandwidth from busy disk drives
    Operating Systems Design and Implementation, 2000
    Co-Authors: Christopher R. Lumb, Jiri Schindler, Gregory R. Ganger, David F Nagle, Erik Riedel
    Abstract:

    Freeblock scheduling is a new approach to utilizing more of a disk’s potential media bandwidth. By filling rotational latency periods with useful media transfers, 20-50% of a never-idle disk’s bandwidth can often be provided to background applications with no effect on foreground response times. This paper describes freeblock scheduling and demonstrates its value with simulation studies of two concrete applications: segment cleaning and data mining. Free segment cleaning often allows an LFS file system to maintain its ideal write performance when cleaning overheads would otherwise reduce performance by up to a factor of three. Free data mining can achieve over 47 full disk scans per day on an Active Transaction processing system, with no effect on its disk performance.

  • OSDI – Towards higher disk head utilization: extracting free bandwidth from busy disk drives
    , 2000
    Co-Authors: Christopher R. Lumb, Jiri Schindler, Gregory R. Ganger, David F Nagle, Erik Riedel
    Abstract:

    Freeblock scheduling is a new approach to utilizing more of a disk’s potential media bandwidth. By filling rotational latency periods with useful media transfers, 20-50% of a never-idle disk’s bandwidth can often be provided to background applications with no effect on foreground response times. This paper describes freeblock scheduling and demonstrates its value with simulation studies of two concrete applications: segment cleaning and data mining. Free segment cleaning often allows an LFS file system to maintain its ideal write performance when cleaning overheads would otherwise reduce performance by up to a factor of three. Free data mining can achieve over 47 full disk scans per day on an Active Transaction processing system, with no effect on its disk performance.

Erik Riedel – One of the best experts on this subject based on the ideXlab platform.

  • towards higher disk head utilization extracting free bandwidth from busy disk drives
    Operating Systems Design and Implementation, 2000
    Co-Authors: Christopher R. Lumb, Jiri Schindler, Gregory R. Ganger, David F Nagle, Erik Riedel
    Abstract:

    Freeblock scheduling is a new approach to utilizing more of a disk’s potential media bandwidth. By filling rotational latency periods with useful media transfers, 20-50% of a never-idle disk’s bandwidth can often be provided to background applications with no effect on foreground response times. This paper describes freeblock scheduling and demonstrates its value with simulation studies of two concrete applications: segment cleaning and data mining. Free segment cleaning often allows an LFS file system to maintain its ideal write performance when cleaning overheads would otherwise reduce performance by up to a factor of three. Free data mining can achieve over 47 full disk scans per day on an Active Transaction processing system, with no effect on its disk performance.

  • OSDI – Towards higher disk head utilization: extracting free bandwidth from busy disk drives
    , 2000
    Co-Authors: Christopher R. Lumb, Jiri Schindler, Gregory R. Ganger, David F Nagle, Erik Riedel
    Abstract:

    Freeblock scheduling is a new approach to utilizing more of a disk’s potential media bandwidth. By filling rotational latency periods with useful media transfers, 20-50% of a never-idle disk’s bandwidth can often be provided to background applications with no effect on foreground response times. This paper describes freeblock scheduling and demonstrates its value with simulation studies of two concrete applications: segment cleaning and data mining. Free segment cleaning often allows an LFS file system to maintain its ideal write performance when cleaning overheads would otherwise reduce performance by up to a factor of three. Free data mining can achieve over 47 full disk scans per day on an Active Transaction processing system, with no effect on its disk performance.

  • towards higher disk head utilization extracting free bandwidth from busy disk drives cmu cs 00 130
    , 2000
    Co-Authors: Christopher R. Lumb, Jiri Schindler, Gregory R. Ganger, David F Nagle, Erik Riedel
    Abstract:

    Freeblock scheduling is a new approach to utilizing more of a disk’s potential media bandwidth. By lling rotational latency periods with useful media transfers, 20{50% of a never-idle disk’s bandwidth can often be provided to background applications with no e ect on foreground response times. This paper describes freeblock scheduling and demonstrates its value with simulation studies of two concrete applications: segment cleaning and data mining. Free segment cleaning often allows an LFS le system to maintain its ideal write performance when cleaning overheads would otherwise reduce performance by up to a factor of three. Free data mining can achieve over 47 full disk scans per day on an Active Transaction processing system, with no e ect on its disk performance.

Alexander Thomasian – One of the best experts on this subject based on the ideXlab platform.

  • Performance analysis of two-phase locking
    IEEE Transactions on Software Engineering, 1991
    Co-Authors: Alexander Thomasian, I.k. Ryu
    Abstract:

    A straightforward analytic solution method is developed which takes into account the variability of Transaction size (the number of lock requests). The authors first obtain analytic expressions for the probability of lock conflict, probability of deadlock, and the waiting time per lock conflict. They then develop a family of noniterative analytic solutions to evaluate the overall system performance by considering the expansion in Transaction response time due to Transaction blocking. The accuracy of these solutions is verified by validation against simulation results. Also introduced is a new measure for the degree of lock contention, which is a product of the mean number of lock conflicts per Transaction and the mean waiting time per lock conflict (when blocked by an Active Transaction). It is shown that the variability in Transaction size results in an increase in both measures as compared to fixed-size Transactions of comparable size. The authors also provide a solution method for the case when the processing times of Transaction steps are different. >

  • ICDE – Performance limits of two-phase locking
    [1991] Proceedings. Seventh International Conference on Data Engineering, 1
    Co-Authors: Alexander Thomasian
    Abstract:

    A novel mean-value analysis method for two-phase locking (2PL) is presented which extends previous work to the important case of variable size Transactions. The system performance expressed as the fraction of blocked Transactions ( beta ) is determined by solving a cubic equation in beta whose coefficients are functions of a single parameter ( alpha ), which determines the degree of lock contention in the system. In fact, alpha is proportional to the mean number of lock requests per Transaction ( eta /sub c/) and additionally the mean waiting time (W/sub 1/) for a lock held by an Active Transaction. For alpha >

Xiaodong Yang – One of the best experts on this subject based on the ideXlab platform.

  • HPCC – Software Assisted Transact Cache to Support Efficient Unbounded Transactional Memory
    2008 10th IEEE International Conference on High Performance Computing and Communications, 2008
    Co-Authors: Shaogang Wang, Zhengbin Pang, Xiaodong Yang
    Abstract:

    Transactional memory (TM) provides efficient, easy, deadlock-free parallel programming model for today’s multicore-ubiquitous hardware platform. Implementation of TM needs to guarantee that the Transaction is executed atomically and in isolation. Our paper proposes an efficient and unbounded hybrid-mode TM system with strong isolation guarantee, called HybridTCache. HybridTCache optimizes the common case by executing small Transactions completely by hardware, and triggers operating system (OS) support with low overhead for the uncommon case when Transaction size exceeds the hardware capacity. HybridTCache adds a new L1 cache, named TCache, to buffer Transactional data for the Active Transaction executed by the processor. Compared with traditional log based approach, TCache provides fast bookkeeping which eliminates software logging overhead for the un-overflowed blocks, thus making both Transaction commit and abort fast. A key design point of hardware TM is to support unbounded Transactions. HybridTCache achieves this by introducing TCache overflow exceptions and resorting to OS to handle the overflowed blocks.

  • ICYCS – Lowering the Overhead of Hybrid Transactional Memory with Transact Cache
    2008 The 9th International Conference for Young Computer Scientists, 2008
    Co-Authors: Shaogang Wang, Zhengbin Pang, Wensheng Tang, Xiaodong Yang
    Abstract:

    Recent years, it has been a hot research topic on providing efficient and unbounded Transactional memory support through hybrid hardware and software approach. Yet, current proposed systems which buffer Transactional data in traditional data cache have high overhead and design complexity. In this paper, we propose a new design approach to build hybrid Transactional memory system. Our approach adds a new L1 cache, named TCache, to buffer Transactional data for the Active Transaction executed on the processor. The obvious benefit of TCache is that software logging for un-overflowed blocks are no longer needed. To handle Transactional overflow, we propose two alternative schemes: the “buffer” approach which writes new value in software, and the “log” approach which writes new value to memory but logs old value in software. TCache introduces exception based hardware and software co-operation approach which is more smoothly and easy to implement. We also propose a scheme which further optimizes our baseline system by saving the shadow copy of Transactional blocks in TCache, which accelerates the re-open process if Transaction is re-executed.

Jan Peciva – One of the best experts on this subject based on the ideXlab platform.

  • Active Transaction approach for collaborative virtual environments
    International Conference on Virtual Reality, 2006
    Co-Authors: Jan Peciva
    Abstract:

    Active Transactions is a novel approach for Collaborative Virtual Environments (CVE). It is based on the Transaction concept from database systems, however it was adapted to fit better the requirements of CVE.The Transactions brings new benefits for CVE. They guarantee atomic execution of their updates. They provide advanced consistency guarantees that may result in simpler application design, and the speculative Transaction execution enables to exploit prediction algorithms to provide an user with high responsiveness.The Transaction concept is combined with Active replication of the scene data. Active replication enables some performance optimizations of the Transaction concept. Therefore, we call it Active Transaction approach.

  • VRCIA – Active Transaction approach for collaborative virtual environments
    Proceedings of the 2006 ACM international conference on Virtual reality continuum and its applications – VRCIA '06, 2006
    Co-Authors: Jan Peciva
    Abstract:

    Active Transactions is a novel approach for Collaborative Virtual Environments (CVE). It is based on the Transaction concept from database systems, however it was adapted to fit better the requirements of CVE.The Transactions brings new benefits for CVE. They guarantee atomic execution of their updates. They provide advanced consistency guarantees that may result in simpler application design, and the speculative Transaction execution enables to exploit prediction algorithms to provide an user with high responsiveness.The Transaction concept is combined with Active replication of the scene data. Active replication enables some performance optimizations of the Transaction concept. Therefore, we call it Active Transaction approach.