This true customer story is related to a physical move of a storage subsystem. A need for a data center move could arise because of a wide variety of reasons. In this case the customer was moving all the IT assets from one building to another as part of a cost savings (large facilities to smaller facilities).
The annual revenues of this customer were around 250 Million a year, with several groups within their IT Business organization.
The customer were moving all IT data center assets from Building 1 to Building 2. Typically during these moves, the vendors of the IT Assets are brought in to verify power shut down procedures, label all the cables, moves, recertification of assets, connect cables, power up, data consistency checks, etc. This customer decided to make a move without involving all the necessary vendors. This move was scheduled in various phases, where all the primary servers and storage assets were being moved in phase 1. Project plans were put in place, resources scheduled, etc, etc. Things were moving along fine with phase 1 move, until it came to moving one of the storage subsystems, it was too heavy to push it across the raised floor since some storage assets need reinforced raised floor and typically that is not the case throughout the entire datacenter. Someone associated with the move decided to remove every drive that was installed in the storage subsystem, pack it in boxes and move it to Building 2. Though they didn’t label the drives as to where they came from. The storage subsystem move to Building 2 finished without any issues.
The customer quickly realized this very big mistake once it was time to power the system back online. No one had an idea of where the disk drives would be inserted based on slot addresses.
At this crucial point, the vendor was contacted and asked for help. This storage subsystem consists of all the data used for their CRM and APPs development teams. Because this storage subsystem was moved without the prior knowledge of the vendor, now they had to come in and certify the system before they could start working on the issue. The vendor knew it was a daunting task ahead.. The onsite CE asked for all the logs prior to the system shut down, which the customer were able to provide, based on slot numbers and serial numbers of disk drives, they inserted one in at a time. Most of the drive serial numbers went in fine, there were some that had been recently replaced, where there was no way to match the slot id’s to disk drive serial numbers since they were not found in the logs. The vendor took an extra step to go back to their own records to find every drive that had been replaced at this customer site and what slot id’s they had been replaced based on their service ticketing system.
12 hours of tedious work of matching serial numbers to slot id’s and finally the system was back up and running with some failed drives. Escalations, Vendor meetings, customer meetings and a 24 hour downtime could have been averted.
Data Center moves should be taken very seriously, 99% of times plug and play is not an option.
Label every cable that was pulled out of the storage subsystem before the move.
Every IT Asset vendor should be involved in the process.
Systems should be powered off correctly based on manufacturer specifications and by the manufacturer itself, especially all storage subsystems.
Every system should be certified prior to the move and re-certified after the move, these services are typically provided for free by all the major vendors.
Vendors recommend using movers that move storage subsystems on a daily basis and it may be a good idea to involve them during this process, as they can provide extra precaution for the move.
Backup data on the storage subsystem before the move.
Run data consistency checks after the move on the storage subsystem and from the associated host system for data integrity.