Three 2 node clusters on IBM Blades.




All installed the same way, same day, except PO2 and PO3 was installed before firmware updates were done to the Blades.
Those 2 were installed before the firmware upgrades, but were upgraded as well.
APPS was reinstalled yesterday, still reboots.

PO2, PO3, PO4 stable and do not reboot
PO5 and APPS reboot several times a day
HDR does reboot, but not often

Clusters fail over fine.

There are 4 other blades, with Linux and Windows, not clustered, that do not seem to be rebooting.

We can not find anything in any logs, or the messages on the servers telling us what called for the reboot.

The techs installing the Blade Center/SAN keep saying it is the Cluster, or the OS, or the network. We did find the switch on the blade center
was dropping packets, bit I can not see how a switch would cause a reboot.

Any ideas on how we can figure out what is causing it, would be appreciated..

I get this from the IBM Blade center Manager:

Alert Text: System boot initiated

Type of Alert: System Information
Severity: 4
Application ID: ServProc
Application Alert Type: 182
Event ID:0x00000081
Log Source:Blade_05
Date(m/d/y): 01/21/09

Time(h:m:s): 15:14:30

Contact: Les Hooe
Location: Bay County Schools

Blade Blade Name: bayapps3

Blade Serial Number: YK125088E18G

Blade UUID: 80E78F43D573B601A09A00215E20A9F4

Blade Machine Type/Module:

BladeCenter MM Name: BCH01AMM

BladeCenter Serial Number: 99C4360

BladeCenter UUID: C7A034AC96F011DD939C00145EE1B74A

BladeCenter Machine Type/Module: 88524YU

Call Home Flag: N

AMM IP Address: