Failure Analysis of Internet Services

Archana S. Ganapathi

EECS Department, University of California, Berkeley

Technical Report No. UCB/CSD-03-1255

2003

This publication is archived. It is kept only for reference purposes, so it is no longer being updated and may not meet accessibility standards. If you need this content in a different format, please email webteam@eecs.berkeley.edu.

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2003/Archive/CSD-03-1255.pdf

We present operational characteristics and failure data of several large-scale Internet services. Case studies and data are used to broaden the range of metrics used in this analysis. We found that operator-induced errors are most impacting and also the hardest failure to mask. Failure-mitigation techniques, such as configuration checking, online testing as well as fault/load injection, improve Internet service availability.

BibTeX citation:

@techreport{Ganapathi:CSD-03-1255,
    Author= {Ganapathi, Archana S.},
    Title= {Failure Analysis of Internet Services},
    Year= {2003},
    Month= {Jul},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2003/5456.html},
    Number= {UCB/CSD-03-1255},
    Abstract= {We present operational characteristics and failure data of several large-scale Internet services. Case studies and data are used to broaden the range of metrics used in this analysis. We found that operator-induced errors are most impacting and also the hardest failure to mask. Failure-mitigation techniques, such as configuration checking, online testing as well as fault/load injection, improve Internet service availability.},
}

EndNote citation:

%0 Report
%A Ganapathi, Archana S. 
%T Failure Analysis of Internet Services
%I EECS Department, University of California, Berkeley
%D 2003
%@ UCB/CSD-03-1255
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2003/5456.html
%F Ganapathi:CSD-03-1255