Name
Abstract | ||
|---|---|---|
One of the challenging issues in performance evaluation of parallel storage systems through synthetic-trace-driven simulation is to accurately characterize the I/O demands of data-intensive scientific applications. This paper analyzes several I/O traces collected from different distributed systems and concludes that correlations in parallel I/O inter-arrival times are inconsistent, either with little correlation or with evident and abundant correlations. Thus conventional Poisson or Markov arrival processes are inappropriate to model I/O arrivals in some applications. Instead, a new and generic model based on the alpha-stable process is proposed and validated in this paper to accurately model parallel I/O burstiness in both workloads with little and strong correlations. This model can be used to generate reliable synthetic I/O sequences in simulation studies. Experimental results presented in this paper show that this model can capture the complex I/O behaviors of real storage systems more accurately and faithfully than conventional models, particularly for the burstiness characteristics in the parallel I/O workloads. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1109/CLUSTR.2008.4663778 | CLUSTER |
Keywords | Field | DocType |
i/o demand,parallel processing,parallel i/o workload,parallel storage system,distributed memory systems,data-intensive scientific application,synthetic-trace-driven simulation,parallel i/o burstiness,distributed system,physics,stochastic processes,stable process,storage system,benchmark testing,computational modeling,correlation,predictive models,mathematical model | Computer science,Parallel computing,Markov chain,Parallel processing,Stochastic process,Real-time computing,Burstiness,Poisson distribution,Parallel I/O,Distributed memory systems,Benchmark (computing) | Conference |
ISSN | ISBN | Citations |
1552-5244 E-ISBN : 978-1-4244-2640-9 | 978-1-4244-2640-9 | 8 |
PageRank | References | Authors |
0.49 | 16 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dan Feng | 1 | 1845 | 188.16 |
| Qiang Zou | 2 | 50 | 7.71 |
| Hong Jiang | 3 | 2137 | 157.96 |
| Yifeng Zhu | 4 | 513 | 35.33 |