Charles Sutton and Michael Jordan

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2009-21

February 2, 2009

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-21.pdf

Probabilistic models of the performance of computer systems have long been used to predict future performance. What has not been as widely recognized, however, is that performance models can also be used to diagnose past performance problems. In this paper, we analyze queueing networks from the probabilistic modeling perspective, applying inference methods from graphical models that allow answering diagnostic questions from incomplete data. In particular, we present a slice sampler for networks of G/G/K queues. As an application of this technique, we localize performance problems in distributed systems from incomplete system trace data. On both synthetic networks and a benchmark distributed Web application, we identify bottlenecks with 25% of the overhead of full instrumentation.

---

BibTeX citation:

@techreport{Sutton:EECS-2009-21,
    Author= {Sutton, Charles and Jordan, Michael},
    Title= {A Graphical Modeling Viewpoint on Queueing Networks},
    Year= {2009},
    Month= {Feb},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-21.html},
    Number= {UCB/EECS-2009-21},
    Abstract= {Probabilistic models of the performance of computer systems
have long been used to predict future performance.
What has not been as widely recognized, however, is that performance models 
can also be used to diagnose past performance problems.
 In this paper, we analyze queueing networks from the probabilistic
  modeling perspective, applying inference methods from
  graphical models that allow answering diagnostic questions from incomplete data.
  In particular, we present a slice sampler for networks of G/G/K queues.  As an
  application of this technique, we localize performance problems in
  distributed systems from incomplete system trace data.  On both
  synthetic networks and a benchmark distributed Web application, 
we identify bottlenecks with 25% of the overhead of full instrumentation.},
}

EndNote citation:

%0 Report
%A Sutton, Charles 
%A Jordan, Michael 
%T A Graphical Modeling Viewpoint on Queueing Networks
%I EECS Department, University of California, Berkeley
%D 2009
%8 February 2
%@ UCB/EECS-2009-21
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-21.html
%F Sutton:EECS-2009-21