(please note, we just started with this section and much information is still missing!)
It is installed in a 450 m2 basement on the campus of the Leibniz University Hannover, featuring about 1MW of power and cooling capacity and about 4200 rack units of space to mount servers. The external 2x10Gbit/s network connectivity is provided by LUIS, internally, we use a large core switch switch with 768 10Gbit/s ethernet ports connecting all machines.
Atlas consists mostly of 1000s of compute nodes along with about 10 log-in or head nodes. Data storage is currently handled by about 100 dedicated machines for different purposes.
Typical metrics for our high-throughput computing cluster currently are
- more than 2700 servers
- more then 40000 (virtual) compute cores
- more than 10 PByte HDD storage
- more than 15 PByte tape storage
Most recent, irregularly published, news items
subscribe via RSS