db1082.eqiad.wmnet crashed yesterday and we had to power cycle it from the ILO.
So far we haven't been able to figure out why, apparently it had a kernel panic.
The RAID looks healthy at this point, but as @MoritzMuehlenhoff suggests - @Cmjohnson could you perform a hardware check to make sure the RAID controller and/or RAM is healthy?
This server is non pooled so it would be safe to power it off if needed. Just ping me if you need me for something.