A non-blocking locking method and performance evaluation on network of workstations

被引:0
|
作者
Ge Yu
Guoren Wang
Huaiyuan Zheng
Taiyong Jin
Kunihiko Kaneko
Akifumi Makinouchi
机构
[1] Northeastern University,Department of Computer Science
[2] Kyushu University,Department of Intelligent Systems
关键词
distributed and parallel database; concurrency control; transaction management; locking mechanism; NOW (network of workstation);
D O I
暂无
中图分类号
学科分类号
摘要
A network of workstation (NOW) can act as a single and scalable powerful computer by building a parallel and distributed computing platform on top of it. WAKASHI is such a platform system that supports persistent object management and makes full use of resources of NOW for high performance transaction processing. One of the main difficulties to overcome is the bottleneck caused by concurrency control mechanism. Therefore, a non-blocking locking method is designed, by adopting several novel techniques to make it outperform the other typical locking methods such as 2PL: 1) an SDG (Semantic Dependency Graph) based non-blocking locking protocol for fast transaction scheduling: 2) a massively virtual memory based backup-page undo algorithm for fast restart; and 3) a multi-processor and multi-thread based transaction manager for fast execution. The new mechanisms have been implemented in WAKASHI and the performance comparison experiments with 2PL and DWDL have been done. The results show that the new method can outperform 2PL and DWDL under certain conditions. This is meaningful for choosing effective concurrency control mechanisms for improving transaction-processing performance in NOW environments.
引用
收藏
页码:25 / 38
页数:13
相关论文
共 50 条
  • [41] Architecture and performance of non-blocking ATM switches with shared internal queueing
    Bianchi, G
    Pattavina, A
    COMPUTER NETWORKS AND ISDN SYSTEMS, 1996, 28 (06): : 835 - 853
  • [42] Leveraging Non-Blocking Collective Communication in High-Performance Applications
    Hoefler, Torsten
    Gottschling, Peter
    Lumsdain, Andrew
    SPAA'08: PROCEEDINGS OF THE TWENTIETH ANNUAL SYMPOSIUM ON PARALLELISM IN ALGORITHMS AND ARCHITECTURES, 2008, : 113 - 115
  • [43] Practical Non-blocking Unordered Lists
    Zhang, Kunlong
    Zhao, Yujiao
    Yang, Yajun
    Liu, Yujie
    Spear, Michael
    DISTRIBUTED COMPUTING, 2013, 8205 : 239 - 253
  • [44] Efficient Non-blocking Radix Trees
    Velamuri, Varun
    EURO-PAR 2017: PARALLEL PROCESSING, 2017, 10417 : 565 - 579
  • [45] Efficient and non-blocking agreement protocols
    Gupta, Suyash
    Sadoghi, Mohammad
    DISTRIBUTED AND PARALLEL DATABASES, 2020, 38 (02) : 287 - 333
  • [46] Non-blocking Binary Search Trees
    Ellen, Faith
    Fatourou, Panagiota
    Ruppert, Eric
    van Breugel, Franck
    PODC 2010: PROCEEDINGS OF THE 2010 ACM SYMPOSIUM ON PRINCIPLES OF DISTRIBUTED COMPUTING, 2010, : 131 - 140
  • [47] REARRANGEABLE AND NON-BLOCKING SWITCHING NETWORKS
    PIPPENGER, N
    JOURNAL OF COMPUTER AND SYSTEM SCIENCES, 1978, 17 (02) : 145 - 162
  • [48] A STUDY OF NON-BLOCKING SWITCHING NETWORKS
    CLOS, C
    BELL SYSTEM TECHNICAL JOURNAL, 1953, 32 (02): : 406 - 424
  • [49] Modular Verification of a Non-Blocking Stack
    Parkinson, Matthew
    Bornat, Richard
    O'Heam, Peter
    CONFERENCE RECORD OF POPL 2007: THE 34TH ACM SIGPLAN SIGACT SYMPOSIUM ON PRINCIPLES OF PROGAMMING LANGUAGES, 2007, : 297 - 302
  • [50] Non-Blocking Conditions for EGS Networks
    Busi, Italo
    Pattavina, Achille
    IEEE COMMUNICATIONS LETTERS, 2010, 14 (06) : 572 - 574