Dell T710 lock ups

Kenazo

Lifer
Sep 15, 2000
10,429
1
81
Well so far I must say my first experience with Dell servers hasn't been that exciting. We recently picked up the following computer to run as a Windows 2008 R2 remote desktop server:

Dell T710
2 x Xeon X5550's
48gb 1066mhz DDR3 (12x4gb)
8x146gig 15,000 rpm Seagate Cheetah SAS drives (2 in a RAID 1 the OS&apps are installed on and 5 in a RAID 6 array for our user data and one global hotspare)

It's a freaking awesome machine, but every so often (maybe once a week on average) the entire thing crashes, but does not reboot. There is no video @ the console, the computer appears to not be running (hitting numlock won't change the numlock light on or off), but all the fans and system lights are still on. I can't access the iDrac remotely either. To get the system back I have to hold in the power button until the system completely powers down, then I can hit the power button again and it starts up as if nothing happened (except for Windows telling me that it had an unexpected shut down).

Dell has already sent a new motherboard which has been installed. We had the same crash about 3 days after replacing the motherboard, so I guess that wasn't the problem. I've ran all of Dell's diagnostic tools but they all come up blank on it being a hardware problem. Windows Logs don't seem to show anything useful either. I'm stuck! Any ideas?

Dell doesn't think it's a hardware problem but I've never seen a software problem that will crash all hardware including the video, but not cause it to reboot.
 
Last edited:

ch33zw1z

Lifer
Nov 4, 2004
39,471
20,154
146
Has Dell support verified your are the correct firmware and driver versions? Do you have a stable power setup for this server?
 

Kenazo

Lifer
Sep 15, 2000
10,429
1
81
Bios is 1.3.6, the most recent one for the T710. I've sent all of the DSET logs to Dell and they haven't raised any issue with anything driver related.

Stable power - being a small accounting office our "server room" is just a back corner of the office. This computer is running into the same UPS as our Exchange server... I suppose I could try moving it to a different location so I know it's running on its own circuit. Perhaps I'm just over loading that leg.
 

Kenazo

Lifer
Sep 15, 2000
10,429
1
81
I've now got it running on a seperate breaker from all our other computers and on its own UPS.
 

ch33zw1z

Lifer
Nov 4, 2004
39,471
20,154
146
Yep: https://plone4.fnal.gov/P1/Main/runii/sysadmin/global_docs/dset.txt

Is this a production machine you can't live without?

Can the services you need be run under Linux? If not, consider running it and see if it still locks up.


Dell doesn't think it's a hardware problem but I've never seen a software problem that will crash all hardware including the video, but not cause it to reboot.

I've had the unfortunate experience of just that when I had a failing PSU. Ubuntu would either lock up or reboot, Windows was BSoD with random errors or locking up. I've also seen this from drivers/firmware problems, non-related to my home PC's.
 

Kenazo

Lifer
Sep 15, 2000
10,429
1
81
As an update to this, turns out NOD32 was the culprit. We replaced it with McAfee 8.7i and it's been running like a charm ever since.