Data Centre


SPEC SFS 2014 benchmark smashed by storage newbie

NVMe over Fabrics shows its razor sharp performance teeth

By Chris Mellor


NVMe-over-Fabrics fanboy startup E8 has whupped other suppliers' behinds with a SPEC SFS2014 filer benchmark.

It is the software build section of the benchmark, which measures the number of software builds and the overall response time.

The previous record holder was NetApp, with 520 builds and a 1.04 second overall response time (ORT).

E8 used its D24 storage array with with 24 x HGST SN200 1.6TB dual-port NVMe SSDs, 24TB total capacity, and 16 Spectrum Scale client nodes to achieve 600 builds and an 0.69 secs ORT.

SPEC SFS 2014 software builds results

If we chart the results ordered by ORT then we get this:

Sixteen Spectrum Scale parallel file system client nodes generated the load for the E8 D24 appliance, with communications using a 100GbitE Mellanox 32-port switch and 100GbitE adapters in each Spectrum Scale node, and RDMA data transfer.

WekaIO started the jump from the 150-250 build level, with its 500-build result in July last year. NetApp beat that in October and now E8 has gone one better.

We understand E8 will put out a press release once contributing supplier quotes have been finalised but, meanwhile, the SPEC SFS 2014 result is live and available for all to see.

Get the detailed E8 SPEC SFS 2014 software build benchmark data here. ®

Sign up to our NewsletterGet IT in your inbox daily


More from The Register

E8 prises software away from its arrays to run on Dell, HPE, Lenovo kit

Flash flinger does a Kaminario

Lazy parent Intel dumps Lustre assets on HPC storage bods DDN

Chipzilla offloads devs, support teams and contracts

Liquidators appointed for Tintri UK as DDN bids to become reseller

Unpaid former staff will get something... eventually

WOS going on? DDN ejected from IDC object storage marketscape

Cue raised eyebrows – Cohesity and SUSE enter

Tintri rescued by DDN just hours after filing for Chapter 11

Exclusive Customer support to be saved, roadmap assurances delivered

Flash array startup E8 whips out benchmarks, everyone will complain

NVMe over Fabrics box bashes Dell EMC, Pure and Infinidat

Artificial intelligence? yawns DDN. That's just the new HPC, isn't it?

We already do bigger, faster arrays – now we're scaling up

AI, AI, Pure: Nvidia cooks deep learning GPU server chips with NetApp

Pure Storage's AIRI reference architecture probably a bit jelly

HPE gets carried array with HPC: Partners up with DDN

+Comment High-performance servers get data-pumping storage arrays

Starting small with burst buffers? DDN says it's got an 'entry-level' one

How much? No word yet