Detecting and handling an expansion card fault during system initialization

Abstract

A method includes running a system mainline initialization process on a compute node that includes an expansion card with read-only memory storing expansion card initialization code. The method obtains and executes the expansion card initialization code from the read-only memory to perform initialization of the expansion card. The method further includes updating a current operational progress state of the expansion card initialization stored in non-volatile memory of the node as the expansion card initialization moves through a plurality of operational progress states, detecting a fault, such as a hung condition, during the expansion card initialization in response to exceeding a predetermined time period in the current operational progress state, and storing a fault indication in the non-volatile memory, wherein the fault indication identifies the card experiencing the fault. Optionally, the method may reset the node and bypass initializing the card associated with the fault indication.