The center is about to undergo major changes in the next few months due to the upcoming move of all of the NYU HPC (which houses our equipment) facilities to a new location in New Jersey. As part of this move, we are turning off much of our old equipment, storage , servers and networking equipment. This will increase our capacity, provide more reliable service, faster storage and networking, but entail some periods of downtime.
New VMWARE Hosts
We will have two new vmware servers, replacing 4 older servers. These two servers will have 792GB of ram and 8 GPus. One server, Tiffany, was purchased by the Marketing Department, and the other, Einstein was purchased for Deep Learning research in the TOpS Department supervised by Joao Sedoc. These servers will complement the recent purchase of Hawking alos being upgraded to 792GB. Hawking has 1 V100 GPU.
2 of our oldest servers will be decommissioned, and 1 other will be converted to a file server.
New Backup Facilities
Backup facilities will now be provided by the new Rubrik cluster of the university, which keeps 3 days of backups on-line, and up to 90 days in the cloud at AWS. This allows us to retire much of our old storage as well as tape drives.
Space on a new, very fast Netapps storage device from Stern IT will be used to house machines and files that need fast access.
Upgraded Network Speeds
Network access to the rest of the world will be using 10gb network connections instead of the current 1gb connect.ions in the current data center.
Unfortunately, these major changes will entail several periods of downtime both before during and after the move. We are working to keep these to a minimum, and will provide a schedule as we get closer to the move, which will be in late June, or mid-August