SELECTING I/O INTERRUPT TARGET FOR MULTI-CORE SERVER SYSTEMS

摘要

Implementations of the present disclosure involve a system and/or method for handling errors in a multi-node commercial computing system running a number of guest applications simultaneously. In particular, the system and/or method provides the ability to program on a per-error basis the destination within the system for an interrupt based on an I/O error, the ability to provision for multiple/redundant error reporting paths for a class of more severe errors and/or distributed set of error status and log registers to aid software in narrowing down the source of an error that triggered the interrupt. In addition, the system provides for dynamically altering the destination of the error handling in response to one or more operating conditions of the system. Such flexibility in the system provides for a more robust error handling without impacting the performance of the multi-node computing system.

主权项

1. A multi-node computing device comprising:
a plurality of processing nodes, each processing node comprising a plurality of processing cores; a service processor in communication with at least one of the plurality of processing nodes; and an input/output (I/O) hub electrically connected to the at least one of the plurality of processing nodes and the service processor and configured to connect to at least one external component of the I/O hub, the I/O hub comprising:
a status register configured to store a plurality of error status messages, wherein each of the plurality of error status messages corresponds to one of a plurality of components of the I/O hub; andan interrupt steering register configured to store a plurality of indicators of a destination component for transmission of an interrupt signal, each of the plurality of indicators corresponds to one of the error status messages stored in the status register, wherein each of the plurality of indicators of a destination component indicates the service processor or the at least one of the plurality of processing nodes based at least on the corresponding one of the error status messages of the status register.