Roll-forward and rollback recovery: Performance-reliability trade-off

被引:17
|
作者
Pradhan, DK
Vaidya, NH
机构
[1] Department of Computer Science, Texas A and M University, College Station
关键词
checkpointing; duplex systems; performance; reliability; roll-forward;
D O I
10.1109/12.580435
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Performance and reliability trade-offs depend on the recovery scheme used in any fault-tolerant system. Gain in performance, using comparable resources, typically requires sacrifice in reliability, and vice-versa. Roll-forward schemes for duplex systems achieve better performance than rollback schemes, without a significant increase in hardware resource requirements. This paper compares two roll-forward schemes with two roll-back schemes. It is shown that the roll-forward schemes improve performance with only a small loss in reliability as compared to rollback schemes.
引用
收藏
页码:372 / 378
页数:7
相关论文
共 50 条
  • [1] Speculative Instruction Validation for Performance-Reliability Trade-off
    Kumar, Sumeet
    Aggarwal, Aneesh
    [J]. 2008 IEEE 14TH INTERNATIONAL SYMPOSIUM ON HIGH PEFORMANCE COMPUTER ARCHITECTURE, 2008, : 375 - 384
  • [2] Time-redundant recovery policy of TMR failures using rollback and roll-forward methods
    Yoon, J
    Kim, H
    [J]. IEE PROCEEDINGS-COMPUTERS AND DIGITAL TECHNIQUES, 2000, 147 (02): : 124 - 132
  • [3] Rollback and roll-forward of architecturally fixed and non-fixed states
    Fechner, Bernhard
    [J]. RELIABILITY, RISK AND SAFETY: THEORY AND APPLICATIONS VOLS 1-3, 2010, : 2007 - 2012
  • [4] A hybrid roll-forward recovery scheme for distributed systems
    Gupta, B
    Mogharreban, N
    Banerjee, SK
    [J]. PDPTA'2001: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, 2001, : 48 - 54
  • [5] Design of new roll-forward recovery approach for distributed systems
    Gupta, B
    Banerjee, SK
    Liu, B
    [J]. IEE PROCEEDINGS-COMPUTERS AND DIGITAL TECHNIQUES, 2002, 149 (03): : 105 - 112
  • [6] A New Roll-Forward Checkpointing / Recovery Mechanism for Cluster Federation
    Gupta, B.
    Rahimi, S.
    Ahmad, R.
    [J]. INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND NETWORK SECURITY, 2006, 6 (11): : 292 - 298
  • [7] Adaptive control in roll-forward recovery for extreme scale multigrid
    Huber, Markus
    Ruede, Ulrich
    Wohlmuth, Barbara
    [J]. INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS, 2019, 33 (05): : 817 - 837
  • [8] Roll-forward error recovery in embedded real-time systems
    Xu, J
    Randell, B
    [J]. 1996 INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, PROCEEDINGS, 1996, : 414 - 421
  • [9] A quasi-synchronous approach for roll-forward recovery in distributed systems
    Liu, H
    Shen, L
    Gu, M
    Gupta, B
    [J]. PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, 2000, : 2117 - 2122
  • [10] Reliability and Performance Trade-off Study of Heterogeneous Memories
    Gupta, Manish
    Roberts, David
    Meswani, Mitesh
    Sridharan, Vilas
    Tullsen, Dean
    Gupta, Rajesh
    [J]. MEMSYS 2016: PROCEEDINGS OF THE INTERNATIONAL SYMPOSIUM ON MEMORY SYSTEMS, 2016, : 395 - 401