the storage anarchist

4.009: leading from the front

Earlier this week, IDC published the results of its  Storage User Demand Study, 2011 — Spring Edition: Unlocking the Minds of Storage Users. Among their findings this year was a notable use of outsourced storage, emerging demand for FCoE (but with limited commitment to the technology), and a predominant preference for midrange and modular storage.

Surveyed users also forecasted that little would change in the way they utilize storage subsystems over the coming year. If true, I would think this bodes well for EMC, especially in light of the results of two key findings presented the SUDS, 2011 report.

4.008: truth or d@re

Back in December 2010, EMC’s Enterprise Storage Division (ESD) released a major new software update for VMAX, embodied as Enginuity 5875. Among the more than 50 new features was  the Data at Rest Encryption feature (which we internally abbreviate as “D@RE”). And then back in May, we updated D@RE with support for RSA’s external key manager as a complement to the embedded RSA key manager in the original release.

Admittedly, Data at Rest Encryption is a feature that is offered by very few storage platforms – it is almost exclusively found only on enterprise-class arrays, in fact. And of all the implementations, Symmetrix VMAX’s D@RE implementation is highly differentiated – a breed apart from would-be competitors (as is FAST VP, VMAX’s automated storage tiering implementation, but that’s not today’s story).

Separating VMAX D@RE from everyone else  are features such as:

• Support for any and all drive types supported by VMAX. Where some other implementations are limited to offering encryption only on special drives with built-in encryption, VMAX D@RE encrypts all the data on all the Flash EFD drives, enterprise 10K and 15K HDDs, and 7200rpm “slow-spin” HDDs;
• A unique key for each and every drive in the system. With up to 2400 unique keys in a full-blown VMAX, the life of a crypto-criminal is much more difficult, especially as compared to competitive offerings that support a max of 31 keys for the entire array (the more data protected by a single key, the easier it is to find the key);
• Complete and transparent data at rest encryption for any and all hosts, applications and storage services, including Virtual Provisioning, FAST VP, SRDF, TimeFinder, VAAI, etc.
• Automated assignment of unique keys to every replacement drive and rekeying of data as the drives are rebuilt;
• Virtually undetectable performance overhead for either encryption or decryption (see chart at right);
• The ability to remove the keys from the array altogether when physically relocating the array as added protection against the accidental or malicious loss of the array (or drives) during the move. Deliver the array and the keys to the new locale separately, and restart the array without delay after the two are reunited.

To my knowledge, no other enterprise storage array offers all of these native capabilities of VMAX D@RE.

Arguable, I could stop there. But wait…

It gets BETTER!

4.007: vmax hits the big screen...again!

Last June we shipped 8 VMAX systems to Detroit for the filming of the movie “The Double” which stars Richard Gere, Martin Sheen and a list of other top names. Like all of the product placements we do, we simply provide the producers with the systems and they choose how to use them.

The trailer for The Double has been released and VMAX plays a very prominent role in several of the scenes, which bodes well for its role in the actual film which hits theatres on Sept. 23rd.

 

Coming soon to a theatre near you: http://trailers.apple.com/trailers/independent/thedouble/

(Interesting coincidence of a post number, don’t you think?)

 

technorati tags: EMC, Symmetrix, VMAX, The Double

4.006: missing the point (yet again)

I guess I struck a nerve.

Although Hu Yoshida chose to show the top 10 largest Hitachi arrays as evidence of the benefits of virtualized external storage, his rebuttal to my response post claims that Hitachi isn't in competition with EMC to see who can ship the largest box.

Not surprising, I guess. Especially when the evidence reveals that there are no customers daring enough to push a Hitachi array beyond 1.4PB usable.

You can't compete if you can't demonstrate that you can deliver what customers want.

And that's exactly the point that Hu misses:

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

4.004: vmax and vmaxe cameo appearances

Since its introduction in April 2009, VMAX has appeared in numerous television shows, news digests, movies and even Mayor Bloomberg's recent press conference announcing Gotham City's new centralized data centers. It seems that producers, directors and video reporters are attracted to the signature bold and blue facade that EMC's industrial design engineers created for the world's most Powerful, most Trusted and Smartest storage array.

You may have seen the following appearances (clockwise from top left):

• 24 (Fox)
• Nikita (CW Network)
• Covert Affairs (USA Network)
• Mayor Bloomberg's Press Conference on NYC's new City Agency data center
• 60 Minutes report on Speed Traders at NYSE

 

 

 

 

 

 

 

 

 

 

But wait! There's more!

4.003: a big thing in a small package

Imagine:

• Start with the world's most Powerful, Trusted and Smart enterprise storage array, hardened by almost 23 years of protecting the world's most critical information assets.
• Scale down its Intel-based infrastructure and dial-back its innovative scale-out architecture to optimize for less-demanding enterprise environments.
• Remove the layers of complexity associated with supporting legacy hosts such as mainframes and iSeries to simplify configuration and operations.
• Eliminate physical drive and RAID configuration altogether and pre-configure the array at the factory for pool-based Virtual Provisioning to radically simplify resource allocation and management while maximizing utilization efficiency.
• Allow customers to add factory-configured Fully Automated Storage Tiering (FAST VP) to further drive down the acquisition AND operational costs of both capacity AND performance.
• For local and remote data protection, include the world's most widely adopted heterogeneous Continuous Data Protection and Remote Replication capability, EMC RecoverPoint.
• Simplify the product installation to no more than a 4 hours to power-up, and 4 minutes to first I/O after the keys are handed over to the customer.
• Package that all in standard 19" racks configured to optimize floor tile utilization, requiring only single-phase power as evidence of reduced power requirements and deployment simplicity.
• Oh, and don't forget the trademark blue LED bar and one of those fancy little "e" thingies that the VNX guys introduced earlier this year.

What do you get?