olrad.1m (2012 03)

o
olrad(1M) olrad(1M)
Remove time displays the approximate time required to delete the driver instance.
The value displayed accounts for worst case scenarios, and the time taken would nor-
mally be less than this. This field will be valid only if the target operating environ-
ment supports OnLine Deletion.
Error time field is for future enhancements.
During the On-Line Replace operation of a card at a slot,
olrad runs pref_replace and
prep_replace driver scripts during the pre-replace of the card (
olrad -r slot_id) and
post_replace driver script in the post-OLR phase (
olrad -R slot_id).
During the On-Line Addition operation of a card at the slot,
olrad runs the post_add driver script in
the post add phase. Note that there are no
preface and prepare driver scripts for OLA (olrad -A
slot_id).
During the On-Line Delete operation of a card at the slot,
olrad runs prep_delete and the
post_delete driver scripts associated with the card at the slot.
For a given OL* operation on a slot,
pref_replace driver scripts will always be run for all the affected
slots (meaning, slots sharing the same power domain)
An audit trail is logged onto
NetTL
log file whenever an OLA/OLR/OLD operation is initiated (see
nettl (1M)). This information is also written to standard output.
PCI Error Handling
Some systems have the capability to handle certain PCI hardware errors during the operation of PCI I/O
cards. When such errors occur, the operating system will automatically try and recover from the error.
However, on certain occasions the system cannot recover from the error automatically. In this scenario,
the software states of the components in error will be marked ERROR in
ioscan output. If this occurs,
the following sequence can be tried from the olrad command to attempt a manual recovery at the slot:
1. If the slot is not already suspended, suspend it using:
olrad -r slot_id
2. Try a post replace operation at the slot using:
olrad -R slot_id
If the card/slot is recovered from the error and the post replace operation succeeds, software states of
the components recovered from the error will be restored to CLAIMED in
ioscan output. If the post
replace operation fails and the error persists, one of the reasons could be that the card has gone bad.
The card in error can be replaced with another card of the same type, and a post replace operation can
be tried with the replaced card.
A complete description on PCI Error Handling is not covered here. For more details refer to documents
on PCI Error Handling available under the High Availability section at the
http://www.hp.com/go/hpux-core-docs
website. Note that the sequence mentioned here for
PCI Error Handling is generic. This is subject to changes depending on different platforms and operating
system releases.
Logging
olrad uses the NetTL subsystem to log errors and audit trail for all OLA/R/D operations performed on
slots. See nettl (1M).
olrad makes use of the sysadmin subsystem formatter to format the log messages.
The following details are not logged:
• CRA report when performing OLA/R/D,
• CRA report when using the
-C option,
• Output of view information options such as -v, -c, -g, -h, -q, -L, and -n.
RETURN VALUE
olrad returns the cra-return values when invoked with -C (cra-only) option. The valid values are as
follows:
0 CRA_SUCCESS
1 CRA_WARNING
2 CRA_DATA_CRITICAL
HP-UX 11i Version 3: March 2012 − 7 − Hewlett-Packard Company 7