Physical domain error isolation and recovery in a multi-domain system

作者: Brian J. McGee , Jurgen M. Schulz , Vishak Chandrasekhar , Wayne F. Seltzer

DOI:

关键词:

摘要: The disclosed embodiments disclose techniques for performing physical domain error isolation and recovery in a multi-domain system, where the system includes two or more processor chips one switch that provide connectivity cache-coherency support chips, are divided into distinct domains. During operation, of determines fault system. chip an originating is associated with fault, then signals identifier to its internal units, some which perform clearing operations clear out all traffic without affecting other domains

参考文章(7)
Colin N. B. Cook, Pete A. Hawkins, Switched platform management architecture and related methods ,(2002)
Yousef A. Khalidi, Jose Bernabeu-Auban, Expressing fault correlation constraints ,(2008)
Srinivas Madhur, Julia D. Harper, David M. Brean, Bjørn Dag Johnsen, Fault zones for interconnect fabrics ,(2005)
Patricia Shanahan, Andrew E. Phelps, Guy David Frick, Shared resource domains ,(2003)
Barry Stanley Ibm United Kingdom Ltd. Barnett, Douglas Craig Ibm United Kingdom Ltd. Bossen, Method and system for end-to-end problem determination and fault isolation for storage area networks ,(2000)
Steven F. Weiss, Patricia Shanahan, Eric Eugene Graf, Daniel P. Drogichen, Andrew E. Phelps, Douglas B. Meyer, Don Kane, Cage for dynamic attach testing of I/O boards ,(1999)