Charles Makes a Point (or Two)

EMC wins the Data Domain battle. 

http://www.cnbc.com/id/31829763/site/14081545

No real surprise to me, but an exciting thing for sure.  What I find interesting in CNBC's article is the continued speculation that NTAP may chase down CommVault, FalconStor, or Sepaton.  Even more interesting is the notion that NTAP might put themselves up for sale.  Of course, as an ex-EMCer, the idea they might put themselves on the auction block is not a new rumor, but I haven't seen too many folks repeating that idea outside 76 South Street or EMC Field offices.

I don't plan on making this a rumor mill blog, but this one's pretty good. StreetInsider.com and other financial sites are speculating that if EMC wins the battle for Data Domain (how could they not?), NTAP will go after CommVault.

Now THAT's an interesting move that has a wild chance at success!  (In case you couldn't tell, that was written with a lot of sarcasm).

If I were CommVault folks, I'd be worried right about now.  NTAP has a great track record of buying software companies and turning them into, well, bought companies.  Topio went away, Spinnaker is nowhere to really be seen outside of a roadmap slide that shows the same 'Coming Soon' graphic quarter after quarter, the Decru product seems to show up less and less every time I cross paths with NTAP -- are you detecting a theme here?  

NTAP does some things very well.  They should be rightly credited with driving the unified storage market to the point it is at today, pushing the thinking of the marketplace to places many didn't think it would go.  They have proven that 'good enough' in many situations is really good enough, and unified storage platforms can effectively solve many storage needs in the middle and upper middle marketplace.

They also do some things not so well.  They don't utilize space on the array very efficiently.  Their implementation of Fibre Channel is a little less performant than I'd like it to be at scale.  Their track record of acquiring at least moderately successful software companies and turning them into a game-changing feature or product line is, well, less than stellar.  They tend to get a little too testy when someone questions their technical methodologies.  Nothing horrific.  They aren't a bad company, and their technology is good, just not as good as others, in my opinion.

To me, this acquisition just doesn't make sense.  NTAP doesn't have a history of being able to sell software effectively.  Bringing a company like CommVault into the fold will take superior execution and understanding that the model for selling software can be quite different than that of selling hardware.  It took EMC several tries to grasp this, and it almost didn't work out very well for them (and in some cases it could be debated that they grasped it in time.  Legato, anyone?).  

How do you go from all but acquiring another hardware player that seems a perfect fit to a forced software buy?  You're not going to take CommVault and integrate it into the filers like you could the DD code.  Even if they could make it work, it would suck down so much performance on the array you'd have to buy FOUR of them to get anything accomplished in your environment.  Do you buy them and just leave them alone, letting them do their thing but add to the bottom line?  Maybe, but that doesn't really seem to gain them much.  Or do you swallow them up hoping it makes you more attractive to HP and they then gobble you both up to replace their anemic and ailing EVA line and obtain a modern backup product?  That doesn't seem to be 'in your face' enough for Donatelli to do, but it might just be enough of a poke in Tucci's eye to do it.  It would certainly stir the pot up a little more, and would make some rational sense.  It seems more likely to me that HP will pursue heavy R & D in the LeftHand product and try to turn some of that 'Invent' power loose to turn the storage world upside down.

What a weird day this turned out to be.  

Chuck Hollis did a pretty decent job (in my opinion) of putting a good public face on the EMC Data Domain acquisition on his blog.  Steve Duplessie is missing the boat a little bit (again, my opinion) in his blog entry on the issue, but I do think he gets a couple of things right.

Steve's point about EMC having 82 ways to do dedupe is misguided and feeds into a FUD-Fest for all EMC's competitors in the marketplace.  Now maybe this should be blamed on EMC's marketing group for not delivering a crystal clear message around deduplication, compression, and single instance storage.  I can buy that argument.  But laying this cacauphony of competing dedupe strategies in the marketplace at EMC's feet isn't right or fair.  Every player in the market has some responsibility for that issue. 

I also don't see EMC having another way of deduplicating data as a negative.  I quite frankly get tired of hearing the mantra'd pablem of "EMC has 82 ways of doing <insert functionality here>.  Which one will they try to sell you today?"  That drivel typically comes from the same camp that tries to fix their plumbing problems at home with a hammer and then wonders why the bathroom is full of water.  Get over it.  If you had billions in the bank to buy companies that fit your long-term strategy you'd do the same thing.  Good strategies aren't built around a single way of doing things.  That's what got EMC into so much trouble in the early part of 2000-2001.  Everything was done their way (Symmetrix) or you were an idiot and not worthy to buy their technology.  EMC provides choice to their customers and flexibility in how to design a solution for their most pressing information problems.  Why does everyone beat them up for that?

Anyway, I could go on for a whole post on that topic alone, so let's get back to the topic of the moment.  The acquisition makes perfect sense on two levels:

1. It stops a major competitor in the marketplace from getting better.  So what if this is a defensive move on EMC's part?  Defense wins championships.  Good for Joe and the EMC Board for executing an excellent defensive maneuver.  As a shareholder, I applaud them for not letting NTAP walk in and change the marketplace (again).  Thank you for finally recognizing that while backup as we know it is in a death spiral, the spiral is slow, and EMC needs to do more than try to convince everyone source-based dedupe is the salve that cures all wounds.  Now, go add to the investment and turn the R & D group loose on this code and get it everywhere as fast as possible.  Don't kill the product, don't take a 5 year ramp to understand how to use it, just go get it done!  I want to see products with elements of this code embedded in them within a year.  You brag about all your R & D, now let's see something real come out of it.
2. The code is good.  The device just works, and it isn't because of the hardware.  It's because of DD's code and approach.  Why not get the best code you can for this feature?  EMC knows more about backup than just about anybody in the marketplace, and when they turn this product line loose on their sales force, watch what happens.  It will be nothing short of amazing, if history is any past indication of potential success.  EMC spends a lot of time training their folks on backup, as well they should, and the only real challenge they'll have is getting their faithful followers to stop spouting the 'Data Domain sucks' mantra.

As a reseller of both EMC and Data Domain, this is a winning combination for us.  We no longer have to hear about how bad DD is from EMC, and fend off the lesser (though workable) Quantum solution when we believe target dedupe is called for.  We will get better support from the larger EMC support org, and have everything under one roof.  That helps our business quite a bit.  It takes some of the best minds in backup in the industry and puts them in one house, which for the partner community makes life easier.  Woo Hoo!

That said, here's what I don't like: 

1. EMC paid way too much for the feature, at least on the face of it.  It's going to be tough to recoup this, even with stellar execution.  They should have bought this company at least 2 years ago.   It was a miss on their part to not have done so.  I'm sure if you add in the lost opportunity cost for NTAP, EMC will make out like bandits, but in Joe's stellar track record of acquisitions, I just think this one is at least a partial miss, only because the timing was so late.  But, sometimes you have to overpay and suck it up.  This is probably one of those times.  It just makes me wonder what else is being missed that could change the landscape of the industry?
2. I fear Quantum is dead.  This is where things get a little ugly.  Can Quantum survive on tape alone?  I doubt it.  Their engine has been soundly decried as inadequate by their largest proponent.  That's not good for business.  I like the tape products for what they do, and it will be disappointing to see Quantum flounder further, as they have some really good folks over there who work hard to do what they do.  Perhaps EMC will finally make it official and forgive the $100M they loaned them by just buying them up, finally putting a tape product directly into their catalog.  There are lots of reasons this doesn't make sense, but some that do.  We'll obviously have to wait and see.

At the end of the day, target dedupe is a technology with a very limited lifespan, just as all VTL type products.  CDP technologies, automated information movement platforms, and improved compression techniques that save replication bandwidth costs will make 'backup' as we know it a dead idea in a matter of years.  How many, I can't say.  But if EMC (and others) keep going down the path of newer, tighter, faster compression and dedupe algorithms that make it possible to transmit terabyte data sets across less than OC-level bandwidth in reasonable timeframes, and maybe even T1/T3 types of bandwidth, we won't be having a conversation about backup anymore.  This applies across the board, little AX4/NX4 companies and V-Max companies alike.  They all suffer from the same problems, and these technologies allow for the problem to be solved at both ends of the scale spectrum. 

So get on the pony and ride, EMC.  Ride fast and get this acquisition done and the product into R & D.  Get us new stuff ASAP!

Why am I occupying real estate in cyberspace?

This is the question I'll try to answer in this, my first blog post.

Why, in the name of all that is good and holy, am I writing a blog? There are probably billions of people in the world that know more than I do about any one of the topics I might post about. So why would I do this? Well, the fact of the matter is, my boss wants me to.

I asked him not to make me do it, so if you end up getting upset over something I write, take it up with him. :-] When I asked him why he wanted me to do this, his answer was pretty simple. I tell people what I think, based upon reason and facts, and I communicate what I think with passion based on those reasons. He didn't put it QUITE that way, but that's what he meant. I think.

I'm not sure how that qualifies me to be a blogger. I really don't. I regularly read Chad Sakac's blog over at VirtualGeek, Chuck Hollis' blog, StorageZilla, Storage Anarchist, Barry Whyte, and a lot of other guys and gals out there and never once put myself in the category of people that should regularly be read by a card-carrying, dyed-in-the-wool, proud to be geek. Not once. Still don't.

That said, I'm supposed to write. What can you expect from me? You can expect a lot of opinion. I'm probably not going to tell you how to configure your Avamar system for maximum throughput of de-duplicated bits across a converged network. I'm probably not going to give you great bits of Linux tweaking advice or try to be crowned the ESX guru of the century with sage advice on how not to tune all the kernel parameters. I'll tell you what I think of things going on in the technology world. I'll tell you how I think they really matter, or really don't matter, to real customers, with real data centers, and real jobs they're trying to keep. I'll try to make sense out of the hype, the homerism, and the marketing stuff and boil it down. If I do that, then maybe people will read. If I miss the mark, probably not.

Who am I?

I'm the newest member of IDS' engineering team. I come from almost 8 years of experience at EMC. While there, I supported Sprint PCS, the Channel, the Proven Professional program (yes, you can blame me for a lot of the questions on the E20-521 exam and a few others), and the Commercial Division. I was a Systems Engineer, Technical Consultant, District Channel Manager, Technology Solutions Manager, and a Global Solutions Architect. I did a lot of things in 8 years. Before that, I spent several years in the telco space, with a CLEC and an (at the time) up-start wireless carrier.

Why does any of that matter? To you, it might not. To customers, it means that I've seen a lot of different things. I've been involved in complete project failures, and partial project successes. I've helped customers who have 'data centers' the size of a small broom cabinet to customers with data centers the size of a shopping mall do one thing: meld the technical and the business.

That's why I do what I do (besides the fact it feeds my seven kids -- do you KNOW how much food seven kids can eat? That's another blog for another day :-]). Anyway, it's what I do. I knew from the time I took apart an Apple IIe in 5th grade and made it work with the LOGO turtle robot, that making computers do things for people in ways that mattered was what I wanted to do.

So, that's what I try to do.

I'm not always right (mostly not), but I always have a reason for what I think. I can always tell you why I think what I think and endeavor to do so in terms that make sense TO YOU. You don't have to agree with me. You don't have to like me. I honestly don't care either way. I'm going to make more than a few of you upset, I'm sure. I'll probably start more than a few flame wars, and I'm okay with that. As long as things stay civil, we'll all have some fun with spirited debate (assuming anyone actually reads my drivel). I have always thought that Chuck Hollis' approach to things was the right way to go -- let comments come and allow them to be seen even when they disagree with you, but I won't allow this blog to become a sounding board of derogatory remarks or silliness. Comments will be moderated.

SO, without further ado.............

Why the V-Max was cool, but not all that exciting to me.

Now before all you EMCers go off telling me I've betrayed the family and how could I defame the good name Symmetrix, hear me out. And anti-EMCers, back off. There's no blood in the water here or reason for you to take a swipe. I could fill reams of paper with the utter ho-hum nature of your last 3 or 4 product "updates".

I'm very impressed with the technology. I'm floored by the technology, actually. I think it's quite amazing what's been done to take DMX concepts into a virtualized hardware layer that then (without too much hyperbole) can infinitely scale (there's probably still some hyperbole there, because nothing scales infinitely outside of Time, but still).  The scale we're talking about here is truly astounding for a storage subsystem.

The fact that manageability has taken a quantum leap forward for the Symmetrix is an indication that the engineering sea change that was supposed to have happened several years ago may have actually begun to occur, and Symmetrix Engineering may have begun to realize that 1) not all customers are idiots who can't manage complex technology, but 2) not all customers want to obtain a PhD in how to manage storage technology because some of them have lives. That's a whole lot of goodness as far as I'm concerned.

The geek in me looks at this thing and says 'holy cow, how'd they really do that'? The fact that this technology enables VMware to truly scale and become serious about commoditizing the compute layer is utterly awesome. This, I think, along with a truly modularized server layer and the converged network, is what VMware needs in order to become the de facto data center OS.

I'm glad they moved to commodity processors. I see a ton of potential in management and down-market mobility afforded by moving to a commodity processor platform. I think this is an infinitely cool machine.

The business guy in me says 'great, another device on the market that is supposed to save the world, but only plays to the top 5%' (or less). I'm not sure how else to see this. Part of it is that I play in a space, and have for several years now, that looks at systems like the DMX, or V-Max, where to acquire one is more than the entire total cost of their infrastructure, including plumbing, electrical, the parking lot, the soda machine, oh, and IT. I get that my perspective is a little bit skewed toward the middle to lower end of the market. I'm happy to play here, because in my experience, they listen more, are more receptive to new ideas, and generally have a passion about what they do, more than most people working in large IT shops do. They're not a cog in the wheel, they ARE the wheel, so to speak.

So what set me off about the whole V-Max thing is how this is 'the vision of the future data center'. That's great. 150 of the data centers of the world will be able to take advantage of these ground-breaking features, functions, and benefits.

Okay, I'm being hyperbolic now, but you get the point. There's no down-stream message. If you don't play with V-Max, you aren't doing anything worth talking about. If you're not going to deploy something that can support 8 bazillion drives, you don't need the uber-integration with VMware (or perhaps aren't worthy of it).

Once again, EMC has basically laid it out that you aren't going to be included in the wave of data center efficiency if your data center consists of 3 or 4 ESX hosts running less than 100 VMs. Apparently it's okay for you to still do everything manually, with no end to end visibility and management capability.

Okay, now I'm being harsh. But again, you get the point.

Don't get me wrong, I love CLARiiON. I've sold and architected a LOT of it. It's a superb platform to everything in its space, hands down, bar none; NAS, SAN, whatever. What I guess I'm upset about is that EMC thinks the only place to revolutionize the industry is in the top 5%. And no, quite frankly, I do NOT consider the CX4 revolutionary. Putting modular connectivity was a must to stay ahead, not a revolutionary idea (servers have had PCIe slots you can put different multi-port cards into for years). But it goes deeper than that. Go back and compare the CX4 launch to the V-Max. Not even close in comparison. The CX4 launch was a blip on the sub-radar of the V-Max. There was no passion to it, no earth-shattering feel to it, just another generation of CLARiiON. 'yay'.

I understand how much revenue comes from that top space, but how much GROWTH? Not much, if any. I feel like EMC missed the opportunity to REALLY turn the tables upside down. Why not go completely downstream (not to the AX4 or CX4-120 space, but that CX4-240 or 480 level and up) with this massively scalable virtualized engine and introduce GREATER than 5 9s to the mid market? Scalable doesn't only mean bigger. It means it can grow and contract. It means it can start out small, AND SMALL MEANS <96 DRIVES IS AFFORDABLE.

This architecture should support that concept. These are Intel processors now, with even more commodity parts, right? Then bring the joy of mass production TO the masses, guys. Scale this baby down and turn the storage world upside down. How could HDS possibly compete with that? NTAP, are you kidding me? They couldn't touch it. Don't even get me started on Compellent, Xiotech, or 3Par. And Equallogic, errr, Dell? Right.

I'm sold on the V-Max conceptually. It's the reality I'm left to deal with, though, and I'm not feeling it. At least not yet.