Please take this with as light-heartedly as you can — asXIV is really a perfect implementation of ‘storage communism,’ as my colleague often says. His reasoning behind this is that all the customer applications assigned to an XIV are treated equally: hence, the phrase storage communism. The net of this argument is that XIV unfortunately customers have very little flexibility and few options as a system gets loaded up – other than to add another system. Which of course is capitalism given the price points.

In the field we hear that the first thing an XIV sales person does is demonstrate that a double hard drive failure is less probable than the end of the world. This tells you there’s a problem. Let me make it clear: there are no RAID 6 capabilities to protect customers and a double hard drive failure that means bye-bye data. Other possible failures include: a PC failure, or a double drive tray and PC failure, …or single drive failure + single drive tray and PC failure. I am losing track of the permutations. You do the math.

I think it’s also valid to question the XIV’s performance, given that response times are in the 5 millisecond range (yes, five), and limitations when running single threaded workloads. If your apps are in no hurry, then this is the one for you.  In contrast, HDS does a great job with performance, reliability and availability with our Adaptable Modular Storage 2000 product line. We are already delivering enterprise-class features for the midrange.

Also with a maximum usable of 79TB of storage from the XIV, this can become expensive for customers who require more than 79TB or know they’ll outgrow that within a year or two of purchase. Since there are no tiering capabilities, customers would need another system if they grow past 79TB. I know, you must be thinking the same thing — that’s yet another island of storage, and an expensive island at that.

Federated Storage Defined
The folks at Wikibon recently published the following definition of federated storage:

Federated storage is the collection of autonomous storage resources governed by a common management system that provides rules about how data is stored, managed and migrated throughout the storage network. In this definition, storage resources include disk capacity managed by controllers or appliances controlling multiple arrays.

One core requirement implied by this definition is the ability to move application data within this federation without any user disruption whatsoever. The business driver here is that disruptions are very difficult to schedule and require enormous amounts of planning, often as much as six months. You’ll hear more on this topic in a future blog.

Tiered storage addresses this need well today, but it can get even better. While tiering optimizes storage efficiency within an array, when storage must be completely moved to another point of control (e.g. moved to a separate controller or appliance) tiered storage falls short because the move is disruptive to applications (although our technology allows customers to mitigate this significantly, to minutes only in some cases).

How Disruptive is Non-disruptive?
Many vendors will claim they can move data non-disruptively. As a customer you need to carefully read the fine print. For example, IBM’s marketing people will claim you can move data from one SVC to another non-disruptively. The fact is you can do this within an SVC cluster but not across clusters.

EMC is also fond of invoking the term non-disruptive, when really they mean less disruptive. Or in the case of migrations from DMX to V-Max, hugely disruptive– unless you think forklift upgrades are minor events.

The truth is Hitachi Data Systems is the only block-based storage vendor today that can offer federated storage and achieve truly non-disruptive migrations for open systems, even across generations of arrays.

How can Hitachi make this claim?
Hitachi offers High Availability Manager which is a software feature that allows data controlled by one USP V to be replicated/migrated to a completely separate array. Once the migration has been completed, the application can access the new target array with no reliance on the original system. You can decide to “fail over” when you want. One more thing that is actually very important to many customers: we can support asset replacement and retirement of OEM external storage assets without “any” disruption to the customers application.

Please check our video on HDS TV here.

Can EMC do this today? When will EMC be able to deliver truly non-disruptive migrations? Your guess is as good as mine.

As a customer, you have choices:

1. Buy functionalities today that meet your tactical and strategic requirements for federated storage, achieve fast ROI and future-proof investments, or…
2. Buy futures from vendors that have consistently forced you to endure expensive, time consuming and disruptive migrations when there are better options available.

When you think about it in these terms, the choice is pretty obvious.

I was in the UK last week for visits with our EMEA team and to attend Storage Expo.  I used to live in London as a student so it’s always interesting to see how things have changed, or not!   

On the storage front, it was my first time attending Storage Expo and I have to say that the HDS booth looked fantastic, and the UK team did a great job of answering our customers and prospects’questions.  There was a live demonstration or our storage economics tool which generated a lot of interest.  

Also, our CTO Hu Yoshida had a keynote and a breakout session.  Lots of interest here again.   Check out Hu’s blog at http://blogs.hds.com/hu/

I had a chance to chat about a few key topics with our team, partners and customers, so thank you for your time..and hope to see you soon in the US for some of you.

I particularly enjoyed meeting a fellow blogger, Matthew Yeager, with whom I had a great “BS-Free” discussion (it’s a Green technical term, I promise) about customer issues, the role of economics in the choice of a storage architecture, and many other topics.   Matthew writes a fantastic blog so please go check it out:  http://whatsthisgottodowithstorage.wordpress.com/

The InMage technology provides customers with remote replication and application failover in a single, easy to deploy and manage platform that provides comprehensive recovery capabilities for midmarket organizations.

I could go on, but I think Mr Duplessie really captured the essence  of this partnership in his recent blog.

For more details, please see the press release.

Looks like a bad plane ride these days for EMC on the VMax front.    You can turn your cell phone back on but don’t expect to sip champagne if you’re selling VMax for a living.  We’ve been looking for them in the field and like good seats on a plane, they’re scarce… but even discounted, they don’t sell.

How many VMax  are  out there?  Remember how it was code-named “Tigon”, an infertile hybrid cat?   What I’m hearing is really not that many despite many traditional sales techniques to entice customers. 

Interestingly enough, Mr. Burke from EMC avoided the question when I asked him directly on Michael Hay’s blog, essentially confirming that people are just not convinced.  

These are tough times, and customers are very smart and will thoroughly evaluate the economic and technological merits of new storage infrastructure investments.  Saying you’ve got a new system, that’s not compatible with the previous generations, and benchmarking it against your own previous poor performers is just not cutting it anymore, even with the great marketing spin EMC put on VMax.  

So what have you heard?

Take a look at the research article from the451 Group.

Note:  access is for subscribers, but I think there’s a guest option as well.  According to the research note,  “HDS claims to have bucked enterprise storage trend as it adds new features”.    

Of particular interest to me is the fact that at least 3 recent innovations that leverage our core replication technology to deliver unique operational efficiencies were mentioned: High Availability Manager (a fantastic capability for seamless data migration in open systems), the Hitachi Storage Cluster for Hyper V, and our Solution for VMware’s Site Recovery Manager 2 (SRM2).

If you didn’t catch this earlier, Hitachi really has some unique capabilities around data accessibility and data resilience, and what it all boils down to is not just the technology, but about how customers  enable operational efficiency through technology:

- Our asynchronous replication solution, Hitachi Universal Replication (HUR) makes a uniquely efficient use of the WAN for wide area capacity optimization. HUR leverages disk-based journaling, write order fidelity, and is really a tool that allows customers to better manage RPO and RTO requirements

- HUR can leverage dynamic provisioning, replication “thin” volumes to “thick” volumes and vice versa

- Talking about combinations and permutations, we have supported externally attached (virtualized) volumes for a while. This enables customers to combine all these features in an integrated fashion

- Hitachi supports multiple data center configurations including pass through configurations that optimize the use of storage

- Hitachi also integrates seamlessly in virtualized server environments (Hyper V and VMware, for example)

- Hitachi provides a high data accessibility option with High Availability Manager

The net-net is that we’ve been doing this for a while now – and we’re keeping our focus on delivering the highest levels of operational efficiency to our customers, and replication technology is critical in achieving this objective. Other 3 letter vendors can’t match these capabilities (that’s a fact) to the ultimate detriment of their customers.

Why should you care as a customer or prospect? In essence our rendition of dynamic provisioning (some call it “thin provisioning”) simplifies and adds operational agility to the storage administration process. It also lets customers purchase less storage capacity up front, deferring storage capacity upgrades in line with actual business usage. This results in operating costs savings (electricity and floor space) associated with keeping unused disk capacity spinning.

Hitachi Dynamic Provisioning software also provides performance improvements through proprietary automatic optimized wide-striping of data across all available disks. Unlike our competitors, Hitachi Dynamic Provisioning software runs on industry-leading Hitachi storage systems and is integrated with their advanced capabilities.

From a technology and operational standpoint, Dynamic Provisioning software allows storage to be allocated to an application without actually being physically mapped until it is used. This means the software allows storage allocations to exceed the amount of storage physically installed. It also means that the provisioning of storage to an application and the physical addition of storage are decoupled.

Putting a business hat on, you can net it out as a capability that extends the life of existing assets through higher utilization and that fosters major reduction of operations management cost and increased storage provisioning agility.

And remember that you can do all of this on systems that are already best in class…

I also want to point out in response to Mr. Burke’s blog comment about Flash drives that while EMC moved aggressively to announce support of Flash before other competitors, EMC did so at exorbitant price points. In addition, this was done with an unknown MTBF that could be influenced by the read/write ratio of a given workload.  Finally, little was said about the fact these new Flash devices were not the most cost effective solution for workloads that required both high random read  I/O performance and high throughput sequential transfer capabilities. In French you call this the “Flou Artistique” – a blurred vision maybe?

In a related conversation, one of my colleagues (we’ll call him Mr M.)  was asking me if we remembered Wide Sky and InVista. I suppose no one disputes EMC’s marketing capabilities, but it makes you wonder what this really means in the long run. HDS has now shipped over 12,500 controllers that are capable of storage virtualization, something that the Big Symm V-Max will never do. Hasta La Vista (InVista) is a few hundred at best.

Did I mention that we have many of those 12,500 systems actively virtualizing third party storage like EMC and leveraging dynamic provisioning, replication and migration capabilities? Customers are doing this because they get operational efficiency and flexibility out of their storage infrastructure. You can’t do that with a V-Max.

With all of its roadmap bells and whistles and hybridness, is V-Max Big Symm going to see the same fate as InVista?

Round One:  Barry the Tigon stuck in a head lock

Well, let’s talk about Barry’s comments on the USP V Platform and the Big Symm (aka “Tigon”; aka: V-miss). While Barry tried to “drive an angle,” it didn’t quite work. A few facts to remember:

- No storage virtualization on V-Max: 12000 HDS controllers out there
- New architecture that’s unproven compared to USP
- There are no performance benchmarks numbers on the V-Max. What do you have to hide? We have the highest independent benchmark (SPC-1 and SPC-2) in class
- FAST = Fully Automated Storage Tiering. Which is SLOW for EMC, as we’ve had this since 2005 and it’s still not available on V-Max
- Catch up to HDS on 3 data center pass-through (we spoke about this previously)
- V-Max Can’t integrate file, object and block services on a single storage platform
- V-Max can’t provide a common BC/DR platform for heterogeneous storage
- And it goes on and on….

I guess we’re “dictating the action”….So, what will we hear next that your guitar goes to 11?

In case you haven’t heard, HDS had a great fiscal year. You can slice it any way you want, but we’ve done great and better than many other vendors. EMC, not so much.

One last thing: If Martha had a recipe for success in storage, it would indeed include HAM!!

And for the other Barry (from IBM): Thank you for your post, I’m sure you’ve seen the comment on your blog.

An easy one is that we’re essentially eliminating business impact associated with open systems applications downtime, and this is big news because it means this capability now extends beyond mainframe.  Others can’t do that.

We’re competing with the pharmaceutical industry since we’re taking numerous headaches away.  Specifically, we’re easing the cost and risk associated with data migration.  Just think of the high number of hosts per storage frame you normally have to deal with, and how the ever-shrinking maintenance window is increasing  IT costs to migrate enterprise storage system.  This is more than a platform evolution, it’s a revolution in how our customers will be approaching the complex, risky and costly migration projects.

Another way to look at this, and actually another good operational advantage that can only be found on our platform is the drastic mitigation of application downtime risk.  When you look at the research out there (reputable analysts, not marketing stuff that someone made up) you will see that primary reasons that affect data accessibility relate to environmental factors, human errors (you don’t want me managing your storage), and other external interruption incidents (too many possibilities to list).

The net, net, and yes, the holly grail:  a reduction of  CAPEX and OPEX and a maximum leverage of the storage platform.  That’s how you bake business advantage in the infrastructure, and that’s also how IT can further extend their past storage investments…only one platform can do this, and it was never code-named after a feline lab experiment or a deep sea predator. Go figure…