November 27, 2017

SuperComputing 17 was a good conference

Super Computing 2017 is always a very interesting conference and you see very often technologies that will arrive in more classic IT a few years later.

I invite you to read the long summary I wrote for StorageNewsletter available here. And in a nutshell a few points below.

Topics were about GPU, of course, burst buffers and fast I/O, file systems/storage, NVMe and composable infrastructure.

The organization also unveiled the new Top500 ranking and introduced the new IO500.

A lot of Lustre-and Spectrum Scale-based file storage solution of course, Quantum with StorNext of course, but also Rook, a multi-protocol SDS - file, block and object - product for massive volume of data, based on Ceph. We saw Panasas as well, the company has announced the 7.0 major PanFS release and a disaggregated model. Vexata demonstrated a file-based solution running Spectrum Scale and of course companies such DDN, NetApp, HPE, Cray, IBM, Dell...

Among the new file storage vendors or vendors with a innovative distributed file system, we noticed the presence of Avere Systems, Elastifile, Panasas and Qumulo but Rozo Systems and Weka IO didn't have a booth.

On the object storage side, it was limited as pure players were pretty much absent like Cloudian, except Caringo.

It confirms two things again: object storage is a capacity tier and file access is king.

Next year the event will take place in Dallas, TX, from 12 to 15 of November, 2018.


0 commentaires: