Greetings,
I have a PowerEdge T710 with the following:
Perc6 RAID
5 146Gb SAS Drives, RAID 5, one virtual drive
One 2.4Ghz Xeon (currently, I had same issue with 2)
6 1Gb DIMMS (currently, I had same issue with 4 2Gb dimms with 2 processors)
Redungant 1100W Power Supplies, both working, redundancy tested ok
Windows Server 2008R2 Enterprise, fully patched
I have been through the ringer on this thing. It will simply shut down, and the fans rev up to what I believe is their highest RPM. It will then act like it going to restart, but I get no video. If you watch it, it looks like it is addressing the hard drives in the array, then gets to a certain point, and the process starts all over again. I spent most of the day yesterday going through each and every firmware update, starting with the Life Cycle Controller, and then using the Unified Server Configurator. As near as I can tell, I have this thing as up to date as possible. I ran diagnostics yesterday as well, and I did have an error on one of the drives in the array. I had a spare, so I removed the bad one, put in the spare, allowed it to rebuild, then ran diagnostics again with no errors. This server started as a dual processor. I thought I might have an intermittent error on one of the processors, so I removed number 2, still had the issue, swapped them, and still had the issue. It does not appear to be load or heat related. I wrote a simple little batch program that just keeps multiplying files that would eventually fill up the drive. It works the drives and the processor pretty well. Anyway, it ran fine. To get the server to boot again, I have found I can disconnect power cords, press and hold in the power button for 5 seconds, plug the cords back in and it will boot right up. I don't think it's a software issue, because the first time it happened there was not much loaded. I also had it go down on me once when I was in the BIOS settings. I talked to one person that mentioned the power distribution board, but I thought I would try a post here first. Any direction or advice is greatly appreciated, as I have roughly 16 hours into troubleshooting and updating this thing.