A high availability mechanism for parallel file system

被引:0
|
作者
Zhang, H [1 ]
Wu, WG
Dong, XS
Qian, DP
机构
[1] Xian Jiaotong Univ, Dept Comp Sci, Xian 710049, Shaanxi, Peoples R China
[2] Beihang Univ, Sch Comp Sci, Beijing 100083, Peoples R China
关键词
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Parallel file systems achieve a high I/O throughput by dividing a file into multiple blocks and storing them on multiple I/O nodes. However, the reliability and availability of the parallel file systems are sacrificed for the stripping of file data over multi I/O nodes. A new mechanism named Logic Mirror Ring (LMR), has been developed to improve the reliability and availability of the parallel file systems in this study. A logic mirror ring is built over all I/O nodes to indicate the mirror relationship among the nodes, i.e., each node maintains not only its own data but also the mirror data of other nodes. The fault tolerant capability of the system is improved because the node maintaining the mirror data of the failed node will takeover the requests to the failed node. The mirror depth can be adjusted to different levels based on the requirements of the reliability and availability. A model is developed to evaluate the reliability and availability of the paxallel file systems. The effects of LMR on the reliability and availability of the parallel file system is studied. The results show that LMR can be used to improve the reliability and availability of the parallel file systems effectively.
引用
收藏
页码:194 / 203
页数:10
相关论文
共 50 条
  • [1] Distributed checkpointing mechanism for a parallel file system
    Távora, VN
    Silva, LM
    Silva, JG
    RECENT ADVANCES IN PARALLEL VIRTUAL MACHINE AND MESSAGE PASSING INTERFACE, PROCEEDINGS, 2000, 1908 : 137 - 144
  • [2] Symmetric active/active metadata service for high availability parallel file systems
    He, Xubin
    Ou, Li
    Engelmann, Christian
    Chen, Xin
    Scott, Stephen L.
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2009, 69 (12) : 961 - 973
  • [3] A mechanism of building a reliable parallel file system with unreliable nodes
    Huang, Heqing
    Cao, Yuanda
    Song, Xiaohua
    2006 IMACS: MULTICONFERENCE ON COMPUTATIONAL ENGINEERING IN SYSTEMS APPLICATIONS, VOLS 1 AND 2, 2006, : 1395 - +
  • [4] Design and evaluation of a high performance parallel file system
    Ou, L
    He, XB
    Scott, SL
    Xu, ZY
    Fang, YC
    LCN 2005: 30TH CONFERENCE ON LOCAL COMPUTER NETWORKS, PROCEEDINGS, 2005, : 100 - 107
  • [5] Adaptive file prefetching in parallel file system
    Hwang-Bo, JH
    Lim, JD
    Seo, DW
    PDPTA'2001: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, 2001, : 1919 - 1924
  • [6] Rotational lease: Providing high availability in a shared storage file system
    Tak, BC
    Chung, YD
    Kim, SJ
    Kim, MH
    HIGH PERFORMANCE COMPUTING AND COMMUNICATIONS, PROCEEDINGS, 2005, 3726 : 190 - 195
  • [7] Comparative analysis of selected high availability solutions for ZFS file system
    Korecki, Michal
    Bun, Roscislaw
    Rostanski, Maciej
    Maczka, Krystian
    PROCEEDINGS OF THE 11TH SCIENTIFIC CONFERENCE INTERNET IN THE INFORMATION SOCIETY 2016, 2016, : 285 - 301
  • [8] High scalable storage management in redbud parallel file system
    Yi, Le-Tian
    Shu, Ji-Wu
    Zheng, Wei-Min
    Jisuanji Xuebao/Chinese Journal of Computers, 2015, 38 (05): : 961 - 972
  • [9] The Vesta parallel file system
    Corbett, PF
    Feitelson, DG
    ACM TRANSACTIONS ON COMPUTER SYSTEMS, 1996, 14 (03): : 225 - 264
  • [10] The Galley parallel file system
    Nieuwejaar, N
    Kotz, D
    PARALLEL COMPUTING, 1997, 23 (4-5) : 447 - 476