4.005: you call that big storage?

Earlier this month, Hu Yoshida posted yet another missive in his never-ending series of hype about the virtues of array-based virtualization. In it, he cited records from Hitachi's tracking systems showing the top VSPs and USP-Vs ranked by total capacity. Oddly, the older USP-V racked up the largest capacity deployed on a Hitachi array, even though its maximum internal capacity is less than the newer VSP (a feat that Hu asserts is because the USP-V has been in the market longer (4 years vs. the VSP's 10 months).

I had to laugh, especially given Hitachi's long-standing (and ridiculous) claims of supporting more than 240-something PB of external capacity.

For the record, being launched in April 2009, VMAX has indeed been shipping longer than VSP, but not as long as the USP-V. VMAX also does not (at the time of this writing) support virtualization of external storage.

With those caveats, herewith the top 10 VMAX arrays, sorted by usable internal capacity:

That's right, folks. The smallest of the top-10 VMAX arrays is larger than all reported VSPs and all but 2 of the largest USP-Vs.

Note also that several of these VMAX arrays are over-provisioned. Leveraging Symmetrix Virtual Provisioning, these arrays are exporting more capacity than they physically support contain. This affords customers improved capacity utilization, driving up efficiencies and driving down acquisition and operational expenses. In addition, most of these arrays are already positioned to leverage the benefits of Symmetrix FAST VP (if they aren't already – you can't tell from this report).

I have to say, though, that I almost spewed coffee on my keyboard when I read Hu's claim that the largest USP-V was actually virtualizing TWENTY FOUR frames from different vendors.

In an age when floor space, power, cooling, maintenance charges and operational complexity are seen as negatives to the bottom line, I'm actually quite surprised that there is even one USP-V customer operating in such an extremely inefficient manner.

It is quite probable that this poor customer would realize significant savings were he/she to replace that multi-headed behemoth of intertwined FC switches and multi-vendor arrays with the elegant simplicity of a single VMAX.

At the very least, he or she wouldn't be such a lonely pioneer of mega-capacity consolidation.
 

technorati tags: VMAX,EMC,Symmetrix,Big Data,Hitachi,VSP,USP-V,capacity,virtualization,efficiency,utilization,virtual provisioning,FAST VP,Fully Automated Storage Tiering,Hitachi Math

Comments

[Alexios]

I just read this now, and went over to Hu's blog to read his. I have to correct a mistake here - Hu was showing the largest USPV/VSP externally attached storage capacity - he never made any claims about the largest internal storage arrays.

I honestly do not know whether the top 10 USPV/VSP internal storage arrays have as much storage as what you've listed.

[the storage anarchist]

Thanks for the comment Alexios, but I suspect that Hu would have mentioned the existence of larger USPV/VSP's in his response to this post.

Instead, he only said that Hitachi wasn't in a competition with EMC to build the largest arrays.

So while I too honestly don't KNOW whether there are larger USPV/VSPs, I do know that nobody from HDS has presented evidence thereof.