SPC says up yours to DataCore

One of three SPC-1 benchmark results withdrawn

12 Reg comments Got Tips?

The 1,510,090.52 IOPS DataCore Parallel Server single node result in March this year was the fourth highest SPC-1 reading, and has now been withdrawn.

After someone, possibly a competitor, went over the results with a microscope they noticed there was no UPS. While its presence or absence wouldn't affect the IOPS result, it does affect the system's price and $/IOPS calculation.

So, DataCore chairman Ziya Aral tells us, the test run will be repeated and results resubmitted with a UPS included and the system price and $/IOPS numbers adjusted upwards.

Say a UPS costs $1,000, this changes the system price from $136,759 to $137,759, which will change the price/performance from $0.09/IOPS to, wait for it, $0.09/IOPS. What foolishness.

It has been suggested that a change in administration at the SPC (Storage Performance Council) and pressure from big array vendors, upset at being upstaged by a piece of storage software running on a server, is resulting in a feeling that hyper-converged systems are in some way invalid and inappropriate competition for big iron storage arrays.

Certainly the earthquake of a $137K system outperforming $1 million-plus systems (Hitachi VSP all-flash, Huawei OceanStor 6800 v3, NetApp FAS8080 EX all-flash), $2 million-plus (Huawei OceanStor 18800), and $3 million-plus (IBM Power 780 Server with SSDs), combined with DataCore's $506K DataCore Parallel Server 2-node's record-breaking 5,120,098.98 IOPS result, is causing after-shocks.

But the big array SPC-1 emperor has been shown to be wearing no clothes. It's no use forcing a fig leaf on DataCore to hide its big balls. They are still there big array folks. ®


Biting the hand that feeds IT © 1998–2020