Characterizing the Storage Process and Its Effect on the Update of Main Memory by Write Through

The problem of multiple, nonidentical copies of the same data in computer systems with both local cache and shared main memory has led some manufacturers to use "write-through" updating for main memory despite some known efficiency advantages favoring "swap" updating We propose that write throughs to main memory be buffered, thus reducing the probability that the CPU will have to walt for a mare memory write operation to take place Statistics on the nonstatmnary point process of stores to memory lead to a model in which the sequence of stores is considered to be described by a Poisson process which proceeds at rate ~, for a fraction of the Ume 13, This type of process has been described as a regime process Values for X, and /3, are obtained by (least squares) fitting the distrnbutlon function for the number of stores per 100 memory cycles This model is a model for the effect of the storage process on write-through updating, but is not a model of the storage process itself The model is then used to estimate the frequency of blocking in a computer system using a finite queue to buffer write-through operations The predicted frequency of blocking is found to agree well with the actual frequency of blocking as determined by trace driven simulation Comparisons are made with swap updating.

[1]  Carol Webb.  PRACTICAL USE OF THE FAST FOURIER TRANSFORM (FFT) ALGORITHM IN TIME-SERIES ANALYSIS. , 1970 .

[2]  Alan Jay Smith,et al.  On the effectiveness of set associative page mapping and its application to main memory management , 1976, ICSE '76.

[3]  Alan Jay Smith.  A Modified Working Set Paging Algorithm , 1976, IEEE Transactions on Computers.

[4]  Peter A. W. Lewis,et al.  Statistical Analysis of Non-Stationary Series of Events in a Data Base System , 1976, IBM J. Res. Dev..

[5]  R. K. Adenstedt.  Weather regimes in stochastic meteorological models , 1970 .

[6]  A. L. Truslove.  Queue length for the E k/G/1 queue by finite waiting room , 1975 .

[7]  E. Çinlar.  Markov renewal theory , 1969, Advances in Applied Probability.

[8]  Maurice V. Wilkes,et al.  Slave Memories and Dynamic Storage Allocation , 1965, IEEE Trans. Electron. Comput..

[9]  Michael D. Schroeder,et al.  Performance of the GE-645 associative memory while Multics is in operation , 1971, SIGOPS Workshop on System Performance Evaluation.

[10]  Ulf Grenander,et al.  Patterns in Program References , 1975, IBM J. Res. Dev..

[11]  Forest Baskett,et al.  The A0 inversion model of program paging behavior , 1976 .

[12]  Robert O. Winder,et al.  Cache-based Computer Systems , 1973, Computer.

[13]  A.V. Pohm,et al.  The cost and performance tradeoffs of buffered memories , 1975, Proceedings of the IEEE.

[14]  Journal of the Association for Computing Machinery , 1961, Nature.

[15]  John S. Liptay,et al.  Structural Aspects of the System/360 Model 85 II: The Cache , 1968, IBM Syst. J..

[16]  A. Pohm,et al.  An efficient flexible buffered memory system , 1973 .

[17]  Francis F. Lee,et al.  Study of "Look-Aside" Memory , 1969, IEEE Transactions on Computers.

[18]  J. ContiC.,et al.  Structural aspects of the system/360 model 85 , 1968 .

[19]  Alan G. Konheim,et al.  A Queueing Model with Finite Waiting Room and Blocking , 1976, JACM.

[20]  P. Moran.  Testing for serial correlation with exponentially distributed variates. , 1967, Biometrika.

[21]  R. Mattson.  Evaluation of multilevel memories , 1971 .

[22]  James D. Riley,et al.  Stability Properties of Adams-Moulton Type Methods , 1965 .

[23]  Maurice V. Wilkes,et al.  Slave Memories and Segmentation , 1971, IEEE Transactions on Computers.

[24]  Hisashi Kobayashi,et al.  The Effects of Service Time Distributions on System Performance , 1974, IFIP Congress.