PCI / PCIe Error Recovery Product Note, September 2010

Tunable Kernel Parameters
There are two PCI Error Recovery tunables that you can configure:
• pci_eh_enable
This tunable is used to enable or disable the PCI Error Recovery feature. On HP-UX 11i v3,
PCI Error Recovery is enabled by default.
pci_eh_enable is not a dynamic tunable. A reboot will be required for changes to take
effect.
For more information about kernel tunable parameters, see the pci_eh_enable(5) manpage.
• pci_error_tolerance_time
This tunable determines whether an automatic PCI error recovery will occur on an I/O slot
based on the time interval between two PCI errors. If two PCI errors occur on a PCI slot
within the time interval specified by the pci_error_tolerance_time tunable, the card
in the I/O slot will be suspended and a manual PCI error recovery operation is required to
restore the card.
For more information about kernel tunable parameters, see the pci_error_tolerance_time(5)
man page.
Error Messages for PCI Error Recovery
All drivers that support PCI Error Recovery generate error messages for specific PCI Error
Recovery events.
Mass storage drivers post error messages to the diaglog. If a mass storage driver generates
verbose error messages, they can be accessed in the Support Tools Manager (STM) diagnostic
logs.
NOTE: Support Tools Manager (STM) is supported only on legacy platform.
Networking drivers post error messages to the console and to the syslog. If a networking driver
generates verbose error messages, they will be posted to nettl.
• When a PCI error is detected
• After a successful PCI error recovery
• When PCI error recovery fails
These messages are posted to the console and to the syslog.
PCI errors supported by the product are mapped to specific events.Table 1-3 “Events Generated
on Legacy Platforms due to PCI / PCIe Errors” and Table 1-4 “Events Generated on HP Superdome
2 Platform due to PCIe Errors” lists the events generated due to PCI / PCIe errors supported on
all platforms.
To view the list of critical events generated on the system, use the following command:
evweb eventviewer -L
To obtain detailed information about an event generated on the system, use the following
command:
evweb eventviewer -E -n <EvArchNo>
Table 1-3 Events Generated on Legacy Platforms due to PCI / PCIe Errors
SummaryEvent ID
An Uncorrectable Error was reported by PCI express bus for which recovery is in progress.100107
A corrected platform error was reported by PCI bus100104
10 PCI / PCIe Error Recovery Product Note