N Fault-tolerant Sender-based Message Logging for Group Communication-based Message Passing Systems

被引:2
|
作者
Ahn, Jinho [1 ]
机构
[1] Kyonggi Univ, Dept Comp Sci, Suwon Gyeonggi, South Korea
关键词
message passing systems; n fault-tolerance; group communication; rollback recovery; message logging; RECOVERY;
D O I
10.1109/CSE.2014.248
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
All the existing SBML protocols have the limitations that they cannot tolerate concurrent failures in common. In this paper, we identify the exact reasons why they unavoidably have their incapability with the assumption of reliable FIFO unicast-only networks and present an effective SBML protocol to overcome this shortcoming without any abandonment of SBML's strength by using the inherent positive feature of group-based communication networks assumed generally in this literature. This protocol satisfies the requirement by replicating the log information of a message sent to a group, separately assigned by each process, into volatile storages of other processes executing the same distributed application together. Therefore, even if only one process in a group survives at a time, our protocol can progress the execution of the entire system without stopping and restarting it.
引用
收藏
页码:1296 / 1301
页数:6
相关论文
共 50 条
  • [21] Design, implementation and performance of fault-tolerant message passing interface (MPI)
    Selvakumar, AD
    Sobha, PM
    Ravindra, GC
    Pitchiah, R
    PARALLEL AND DISTRIBUTED COMPUTING SYSTEMS, 2004, : 145 - 150
  • [22] Recent Results on Fault-Tolerant Consensus in Message-Passing Networks
    Tseng, Lewis
    STRUCTURAL INFORMATION AND COMMUNICATION COMPLEXITY, SIROCCO 2016, 2016, 9988 : 92 - 108
  • [23] Design, implementation and performance of Fault-Tolerant message passing interface (MPI)
    Selvakumar, AD
    Sobha, PM
    Ravindra, GC
    Pitchiah, R
    SEVENTH INTERNATIONAL CONFERENCE ON HIGH PERFORMANCE COMPUTING AND GRID IN ASIA PACIFIC REGION, PROCEEDINGS, 2004, : 120 - 129
  • [24] Fault-tolerant message switching based on wormhole switching and backtracking
    Sueishi, M
    Kitakami, M
    Ito, H
    10TH IEEE PACIFIC RIM INTERNATIONAL SYMPOSIUM ON DEPENDABLE COMPUTING, PROCEEDINGS, 2004, : 183 - 190
  • [25] CMDE: A Channel Memory based Dynamic Environment for fault-tolerant message passing based on MPICH-V architecture
    Selikhov, A
    Germain, C
    PARALLEL COMPUTING TECHNOLOGIES, PROCEEDINGS, 2003, 2763 : 528 - 537
  • [26] The optimal data interval for message passing to update checkpointed states in fault-tolerant distributed systems
    Shin, SY
    Shim, CYS
    Gantenbein, RE
    INTERNATIONAL SOCIETY FOR COMPUTERS AND THEIR APPLICATIONS 13TH INTERNATIONAL CONFERENCE ON COMPUTERS AND THEIR APPLICATIONS, 1998, : 376 - 379
  • [27] FAULT-TOLERANT DISTRIBUTED SYSTEMS BASED ON BROADCAST COMMUNICATION
    MELLIARSMITH, PM
    MOSER, LE
    9TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, 1989, : 129 - 134
  • [28] Fault-tolerant protocol for hybrid task-parallel message-passing applications
    Martsinkevich, Tatiana
    Subasi, Omer
    Unsal, Osman
    Labarta, Jesus
    Cappello, Franck
    2015 IEEE INTERNATIONAL CONFERENCE ON CLUSTER COMPUTING - CLUSTER 2015, 2015, : 563 - 570
  • [29] Broadcast Network-Based Sender Based Message Logging for Overcoming Multiple Failures
    Ahn, Jinho
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 2017, E100D (01): : 206 - 210
  • [30] Communication Mechanism and Its Implementation for MSVL Based on Message Passing
    Wang X.-B.
    Guo W.-X.
    Duan Z.-H.
    Duan, Zhen-Hua (zhhduan@mail.xidian.edu.cn), 1607, Chinese Academy of Sciences (29): : 1607 - 1621