期刊文献+

容错实时系统的内存管理优化方案及实现

An Optimal Scheme for Memory Management in Fault-tolerant Real-time System
在线阅读 下载PDF
导出
摘要 探讨如何把抢占门限应用于具有优先级提升和内存受限的实时系统,并进一步研究了互不抢占组内,linux平台上基于增量检测点的内存备份/恢复的方法及原型系统的实现。原型系统采用了可扩展的链接方式作为检测点文件格式,使得数据更加紧凑有序;在内存的备份操作上,提出了“影子脏位”算法来识别两检测点之间有无被改变的部分。原型实验验证了所提出方法的有效性。 After analyzing how to apply preemption - threshold - scheduling into real - time systems among which the recoveries of safety tasks may be executed at higher priority levels and the sizes of memories are limited, we research realization methods about memory backup/recovery on the Linux platform based on increment checkpoints for no-pre- emption task groups. At last, taking the microcomputer interlocking simulation system as an example, prototype experiment of memory backup/recovery has been done on the Linux platform in the lab. Our prototype experiment takes an ex- tendable checkpoint file layout to make data in a file compact. And with regard of memory backup operation, by using a“ showdown of dirty-bit” algorithm to identify the difference between two checkpoints, it implements an increment check- point to improve system performance. This experiment has proved the validity of proposed methods.
出处 《航空计算技术》 2007年第3期63-65,82,共4页 Aeronautical Computing Technique
基金 广东省自然科学基金(06029667)
关键词 抢占门限 内存管理 EtoC 增量检测点 preemption threshold memory management execute to completion increment checkpoint
  • 相关文献

参考文献6

二级参考文献32

  • 1[1] A.Ziv and J.Bruck.Performance optimization of checkpointing schemes with task duplication.IEEE Trans.Computers,Dec.1997,46(12):1381~1386
  • 2[2] A.Ziv and J.Bruck.Analysis of checkpointing schemes with task duplication.IEEE Trans.Computers,Feb.1998,37(2):222~227
  • 3[3] D.P.Siewiorek and R.S.Swarz.The theory and practice of reliable system design.Digital Press,1982
  • 4[4] P.Agrawal.Fault tolerance in multiprocessor systems without dedicated redundency.IEEE Trans.Computers,Mar.1988,37(3):358~362
  • 5[5] A.Duda.The effects of checkpointing on program execution time.Information Processing Letters,June 1983,16:221~229
  • 6[6] D.K.Pradhan,and N.H.Vaidya.Roll-Forward and Rollback Recovery:Performance-Reliability Trade-off.Proc.24th IEEE Int′l Symp.Fault-Tolerant Computing,June 1994:186~195
  • 7[7] J.Long,W.K.Fuchs,and J.A.Abraham.Forward recovery using checkpointing in parallel systems.Proc.19th Int′l Conf.Parallel Processing,Aug.1990:272~275
  • 8[8] E.N.Elnozahy,D.B.Johnson and W.Zwaenepoel.The performance of consistent checkpinting.The 11th Symposium on Reliable Distributed Systems,1992:39~47
  • 9[9] J.S.Plank,M.Beck and G.Kingsley.Libckpt:Transparent Checkpointing under Unix.1995 USENIX Technical Conference,1995:213~223
  • 10[1]Tannenbaum, T., Litzkow, M. The condor distributed processing system. Dr. Dobb's Journal, 1995,(2):40~48.

共引文献5

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部