CONTAP-771205: ONTAP cluster node reboots unexpectedly
Issue
- ONTAP cluster node reboots unexpectedly:
Uncorrectable Machine Check Error at CPU8. SPR_UBOX Error: STATUS<0xba00000000000e0b>(VALID,UC,EN,MISCV,PCC,CESI(0),CERR_CNT(0),OTHER_INFO(0),MSCOD(0),MCACOD(0xe0b))MISC<0x000000009a280000>(BUS_LOG(0x9a),DEVICE_LOG(0x5),FUNCTION_LOG(0),SEGMENT_LOG(0)) IIO Machine Check from devices(s): .
- A PCIe adapter, or the PCIe link to it, reported an uncorrectable hardware error.
- The system responds with a controller disruption to protect data integrity; in an HA pair, the partner takes over so that client I/O continues.
- In some cases the message does not list the failing device after "IIO Machine Check from devices(s):", so the hardware component that needs to be replaced cannot be identified from the message alone.
