StorageRap

Netapp & tiering - Just when they thought things were looking up...

Netapp has been on the hot seat ever since Tom Georgens, their CEO commented that tiering would soon be obsolete. Since then, a number of people have called him out on it, including yours truly (in a steering wheel cam), StorageBod, The Storage Architect, StorageZilla , a storage blogging wannabe, and last but not least, the Storage Anarchist.  To be fair, Georgens DID get support from the contrarian Drunken Data. 

At the end of his post, the Storage Anarchist asks:

Are they just defending their chosen path of Flash-as-cache instead of –as-a-tier? Or is it deeper than that? Is there something inherent in WAFL that makes it difficult to implement multiple different tiers within a single array? Or is it something else?

It's tempting to suspect WAFL's snapshot mechanism is the problem, but there is nothing about file level snapshots that would preclude storage tiering. Storage tiering depends on the ability to redirect block addresses across devices classes, which can be done at an abstraction layer below the file system level. In Netapp's case, the issue appears to be an interlock between WAFL and Netapp's underlying RAID layer.  So I'd say its mostly a Netapp RAID problem.

As writes come into a WAFL system, they are first staged to NVRAM in order to eliminate parity RAID write penalties and then they are written to "nearby" blocks using a tightly coupled relationship between the file system and its underlying RAID subsystem.  This design has an unusual and intricate knowledge of disk drive operations and status within the RAID array.  In other words, the file system in a Netapp machine is intricately coupled to the physical characteristics of the underlying storage hardware, which means creating block abstraction layers is highly improbable. The text-image below is from Netapp's Patent filing  6,138,126 dated October 24, 2000.

Now it's possible that this patent does not indicate the implementation within Filers today, but I'd say there is a good chance it explains Netapp's reluctance to embrace tiering. If this turns out to be Netapp's tiering shortcoming, Netapp would need to virtualize their RAID implementation in order to get to a point where they could start working on tiering. 

Holy cow!!  Is it possible that Netapp is actually THAT FAR behind in storage virtualization - not to mention the next wave of the technology - tiering?

If this analysis is correct, it may be that the only way to get tiering (not caching) with a Netapp system is to connect their V-Series filer to a third party array that offers tiering. If that's the case, will Netapp support it, seeing as how they don't have it on their home-grown Filers?

The hot seat could get a lot hotter.

The SWCSA rides again: A smackback for Georgens' whacked fast smack

No, it's not a SWCSA rap, but it is a steering wheel cam, complete with a surprise ending- inspired by Stu @ at EMC.   

Forget Netapp, is 3PAR vulnerable to "good enough" competition?

In a self-described FUD piece today StorageBod wonders about Netapp's future.  To put a finer point on his thoughts, in a comment he wrote:

Your first billion was the easiest billion; the rest gets harder...there's a target pointed in the middle of your foreheads' now. You are going to have to run even faster, even to stand still. Can you do it and can you do it without increasing your product set?

Normally I would enjoy this sort of badgering, but in a subsequent comment he wrote:

Complaint about NetApp is how vulnerable they are...they are not the only ones tho'...there are more vulnerable companies out there; 3Par, Compellant, Isilon, BlueArc etc, etc...the trailing pack who need to grow quickly or get bought.

OK, at least he mentioned 3PAR first! After all, we are larger than the rest of the pack he mentioned, not to mention in a much stronger financial position. To put a finer point on it, 3PAR is not vulnerable to debt (we have none), nor to cash weaknesses ($108 Million and increasing every year).

So what vulnerability is StorageBod imagining?  I suspect it was similar to those voiced by EMC blogger Chuck Hollis:

But, as you point out, it doesn't strike many of us as a defensible position long-term. It's just too easy for competitors to provide a "good enough" and attack those rich margins.

EMC tended to think it was in an unassailable position a decade ago with the Symmetrix. We were quite wrong. If I was doing a storage startup, it'd be pointed directly at draining NetApp's profit pool.

I also think that single-product companies lose the benefit of hybridization -- combining multiple technologies in new and interesting ways.

My take on this is that the storage industry tends to have different dynamics than most other industries. Yes size matters and Netapp and 3PAR and everybody else plays by those rules, but after achieving a critical mass, size is less important than paying attention to details.  Doing things more effectively  - not just in a more grandiose fashion - makes the largest difference.

We are not concerned about competitors trying to copy us and providing "good enough".  A competitor's assessment of "good enough" will likely not be adequate to many customers. It's how we grew our business over the last 10 years inside the jaws of EMC's formerly unassailable Symmetrix business.  I was an independent outsider when 3PAR began and to tell the truth, I thought the folks at 3PAR were out of their minds. But 3PAR has steadily grown and continues to gain market share - primarily in the high end of the market.  Admittedly, the high end has not been a place for hottest growth over the last decade, but we've climbed and are still steadily climbing.  As the service provider model of IT evolves and gains traction, we like our chances with our products and technologies there. FWIW, our new mid range F-class systems are doing very well, but we probably need a larger reseller channel to address the number of mid-range opportunities we are seeing.  That is a growth problem, not a shrinkage problem.

3PAR's capacity guarantee program works because we consistently deliver utilization levels that our customers didn't think were possible and we stand behind it with a contract.  Customers continue to check it out and are coming to the understanding that great utilization comes from a system designed for optimal efficiency and not simply to be "good enough".  If you stop thinking about storage administration as managing disk layouts you are on the right track. 3PAR admins don't manage disk layouts.

The question of hybridization and crossover potential is very interesting. Innovation can come from trying to tie disparate things together and this sort of integration is incredibly valuable when done well.  However, a hybridization mind set often assumes that most core innovation has already been done and that most future gains will come from integrating across functional boundaries. 3PAR doesn't think fundamental storage technology is even close to being fully developed. The problems customers assume they have to live with should not be tolerated. 

So yes, it's possible that we are vulnerable. The storms of technology change could make 3PAR and Netapp irrelevant in the years to come. Speaking only for 3PAR, we believe there is still a gold mine in revolutionizing storage efficiency and will continue to compete based on that belief. 

A conversation with Charlotte Melen of Comic Relief

The UK-based charity, Comic Relief, is once again using 3PAR storage as part of its IT infrastructure for raising millions of Pounds during it's nationwide Sport Relief campaign the weekend of March 19-21.  StorageRap spoke with Comic Relief's Web Technology Manager, Charlotte Melen recently about the intangible benefits of working for Comic Relief and what technologies they use for their donations platform.   Besides 3PAR, other key vendors include HP, Cisco, VMware and Oracle along with payment services from Paypal and RBS.

A conversation with Jordan Gross & Michael Shanks of Ultraspeed

Ultraspeed describes their hosting business as providing enterprise level solutions at mid-market prices.  In this interview, Jordan Gross and Michael Shanks of Ultraspeed talk about how they do it; from running diskless, DC-powered servers, to implementing virtual systems with 3PAR virtual storage and operating data centers in London and Amsterdam.

Customer says 3PAR's online upgrade process is "Easy as Pie!"

From a customer's blog:

In the last few weeks 3PAR released a major software upgrade for their arrays which enables a boatload of new features, including enhanced thin provisioning, autonomic provisioning, and RAID-MP. Today I performed the upgrade to Inform OS 2.3.1, and it went without a hitch and was quite easy. Unlike high-end arrays from Hitachi, EMC, and IBM, the upgrade process is not complex and took no more than an hour of time.

The whole blog post is here:   Thanks for the kind words,  Derek!

Click on the image below to find out about our capacity guarantee program. The program EMC doesn't want you to check out.

Is your storage vendor a doctor, a used car salesman or just without a capacity guarantee?

There's been a dysfunctional discussion of capacity guarantee programs over on Chuck's blog. There had been more sensible, independent discussions on the Storage Architect's blog, but that apparently wasn't good enough for EMC - a company without a capacity guarantee program of their own.  Unfortunately, Chuck decided to shut down comments on his post, citing an overload of vendor hash - which could continue to go on as long as there is breath left in any bloggers from Netapp.

Chuck's post poses the question - do you want to buy from a doctor or a used car salesman.  The suggestion he makes is that EMC treats you like a doctor while 3PAR, HDS and Netapp treat you like  used car salesmen. 

The doctor picture he used was this one:

Which reminded me of Scrubs - but of course there are other doctor images he could have used:

In case you've been shunning the news, this is Dr. Conrad Murray.

The used car salesman picture was pretty funny:

I'd suggest Chuck is using classic used car sales tactics: "Who loves ya baby? The warranty them guys offer don't protect you from nuthin'. Your engine will blow up the day after the warranty expires. All they want is your munny!"  

Still, seeing as how he was linking this image to 3PAR (in one way or another), I'd have hoped he would have used a picture like this instead:

You might not end up buying that car, but you should at least check it out.

 

Chuck characterizes capacity guarantee programs as not being in the customer's best interests. That would be true if 3PAR, HDS and Netapp wanted to increase the number of unhappy customers they have, but that is just CRAZY EMC thought diarrheaship:

 

Instead, I'm pretty sure we all want our customers to be very happy with their storage solution:

 

Yes, 3PAR's capacity guarantee is a way to attract customers, but it's much more than that - it's a way to back up our efficiency claims by putting our money where our mouths are:

 

RecoveryMonkey had a post recently about FUD and the ridiculous corner case claims storage vendors sometimes make about each other.   3PAR has been telling customers for years that our products are more efficient than theirs and we are now backing it up with our capacity guarantee. It's not FUD, it's not spin and its definitely not a corner case.

3PARvaTAR Episode #2: What will Mr. Oracle do for an encore?

.

There are many things Larry Ellison can do.  If he wanted to run for public office, he certainly wouldn't have to worry about campaign funding.  I mean, if he can buy a bad NBA basketball team, he can certainly afford a series of popularity ads showing his over flowing empathy. But if he still wants to be the CEO of the largest software company in the world - it's not clear that getting into the hardware business will help him do it. Time will tell.