Method and system for fault isolation methodology for I/O unrecoverable, uncorrectable error

摘要

A method and system for managing uncorrectable data error conditions from an I/O subsystem as the UE passes through a plurality of devices in a central electronic complex (CEC) is disclosed. The method and system comprises detecting a I/O UE by at least one device in the CEC; and providing an SUE-RE (Special Uncorrectable Data Error-Recoverable Error) attention signal by at least one device to a diagnostic system that indicates the I/O UE condition. The method and system further includes analyzing the SUE-RE attention signal by the diagnostic system to produce an error log with a list of failing parts and a record of the log. A method and system in accordance with the present invention provides a new fault isolation methodology and algorithm, which extends the current capability of a service processor runtime diagnostic code (PRD). The method allows for the accurate determination of an error source and provides appropriate service action if and when the system fails to recover from the UE condition. This new methodology allows a more focused determination of error source and appropriate service action if and when the system fails to recover from an I/O UE.