Mining for statistical models of availability in large-scale distributed systems: An empirical study of SETI@home
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
In the age of cloud, Grid, P2P, and volunteer distributed computing, large-scale systems with tens of thousands of unreliable hosts are increasingly common. Invariably, these systems are composed of heterogeneous hosts whose individual availability often exhibit different statistical properties (for example stationary versus non-stationary behavior) and fit different models (for example Exponential, Weibull, or Pareto probability distributions). In this paper, we describe an effective method for discovering subsets of hosts whose availability have similar statistical properties and can be modelled with similar probability distributions. We apply this method with about 230,000 host availability traces obtained from a real large-scale Internet-distributed system, namely SETI@home. We find that about 34% of hosts exhibit availability that is a truly random process, and that these hosts can often be modelled accurately with a few distinct distributions from different families. We believe that this characterization is fundamental in the design of stochastic scheduling algorithms across large-scale systems where host availability is uncertain.Keywords
This publication has 16 references indexed in Scilit:
- Modeling Job Lifespan Delays in Volunteer Computing ProjectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2009
- On correlated availability in Internet-distributed systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Nonparametric test for checking lack of fit of the quantité regression model under random censoringThe Canadian Journal of Statistics / La Revue Canadienne de Statistique, 2008
- Probabilistic allocation of tasks on desktop grids2008 IEEE International Symposium on Parallel and Distributed Processing, 2008
- Understanding churn in peer-to-peer networksPublished by Association for Computing Machinery (ACM) ,2006
- The Computational and Storage Potential of Volunteer ComputingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Reputation-Based Scheduling on Unreliable Distributed InfrastructuresPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Characterizing and evaluating desktop grids: an empirical studyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Is remote host availability governed by a universal law?ACM SIGMETRICS Performance Evaluation Review, 2003
- The available capacity of a privately owned workstation environmentPerformance Evaluation, 1991