Intel C2550 FH8065401488912 Scheda Tecnica
Codici prodotto
FH8065401488912
Intel
®
Atom™ Processor C2000 Product Family for Microserver
September 2014
Datasheet, Vol. 2 of 3
Order Number: 330061-002US
69
Volume 2—System Agent and Root Complex—C2000 Product Family
Error Classification
4.6.1
Correctable Errors
Hardware correctable errors include those error conditions where the system recovers
without any loss of information. The hardware corrects these errors, and no software
intervention is required. For example, a link CRC error which is corrected by the data
link level retry is considered a correctable error.
• An error is corrected by the hardware without software intervention. System
operation is degraded, but its functionality is not compromised.
• A correctable error is logged and reported in a implementation specific manner:
— Upon the immediate detection of the correctable error, or
— Upon the accumulation of errors reaching to a threshold.
— Upon the accumulation of errors reaching to a threshold.
4.6.2
Fatal Errors
Fatal errors are uncorrectable error conditions which render the SoC hardware
unreliable. For a fatal error, inband reporting to the CPU occurs. A reset is required to
return to reliable operation.
• System integrity is compromised and continued operation is not feasible.
• System interface is compromised.
• Inband reporting is feasible, for example, an uncorrectable tag error in cache or a
• System interface is compromised.
• Inband reporting is feasible, for example, an uncorrectable tag error in cache or a
permanent PCIe* link failure.
• This error requires immediate logging and reporting of the error to the CPU.
4.6.3
Non-Fatal Errors
Non-fatal errors are software correctable or software/hardware uncorrectable errors
which cause a particular transaction to be unreliable, but the system hardware is
otherwise fully functional. Isolating non-fatal from fatal errors provides system
management software the opportunity to recover from the error without reset and
disturbing other transactions in progress. Devices not associated with the transaction in
error are not impacted by the error. An example of recoverable error is an ECC
uncorrectable error that affects only the data portion of a transaction.
• The error is not corrected by the hardware and requires software intervention for
correction.
• Or the error is not corrected. Data integrity is compromised, but system operation
is not compromised.
• This error requires immediate logging and reporting of the error to the CPU.
The OS/firmware takes the action to contain the error.
4.6.3.1
Software Correctable Errors
Software correctable errors are considered as a recoverable error. These errors include
those error conditions where the system recovers without any loss of information.
Software intervention is required to correct these errors.
• This error requires immediate logging and reporting of the error to the CPU.
• The firmware or other system software layers take corrective actions.
• The firmware or other system software layers take corrective actions.
Data integrity is not compromised with such errors.