WD/HGST just released details on a PMR (aka “real”, non-archive class) hard disk. You can read the specs here.
We will be offering these in Unison HPC storage systems, to provide up to 600TB/4U unit, or up to 6PB per rack of 10 unison chassis. Coupled with our 100Gb fabric, we expect to be able to drive about 8-9 GB/s per chassis. And thats before we leverage the distributed journaling/metadata NVMe’s rear mounted on the units.
Unison supports parallel file systems, and leverages BeeGFS by default, with options for Lustre, GPFS, and others by request. With CephFS solidfying, the range of options has increased markedly, and we can now provide very high performance file systems, along with very highly reliable scale out NAS and object/reliable block stores (native client, NFS, and CIFS support).
6PB per rack at under 15kW/rack, and enough computational power to run erasure coding at line rate, while pushing bits over multiple 100Gb networks.