« 1.028: benchmarketing. badly. | Main | 1.030: flash as cache - really? »

November 10, 2008

1.029: atmos. with, and without, the sphere

Wind Star I'm just back from vacation cruising several Italian, French and Spanish ports aboard the Wind Star on the Mediterranean with my wife. It was a relaxing, multi-cultural Adventures Afloat trip arranged by her employer (Elderhostel), a not-for-profit who specialize in educational travel and learning opportunities. With a foundational belief that learning is an integral part of a healthy and fulfilling life, the organization offers its unique Adventures in Lifelong Learning to anyone who is interested - at an exceptional value! So, if you're looking for a travel programme with more than just the usual tourist trap visits, I encourage you to visit their web site and/or order their free catalog.

Oh, and don't let the name fool you: participation is quite diverse, and you'd better be in good shape or you might just get left behind.

Anyway, being on such a trip with my wife, I wisely avoided all things work for the duration.

Preserving the atmosphere, you might say.

But so much has gone on in the past couple of weeks, I thought I'd take a stab at connecting some of the key sights from my cruise with a few of the more interesting events of the past week or so.

So let's have a little fun. Shall we?

italy and napoleon

Napolean's Exile to Elba

Our cruise departed from Rome (actually, the nearby port of Civitavecchia), and visited lots of really cool sites. The first port of call included a shore visit to Napoleon's exile home on the Italian island of Elba.

The whole theme of world dominance followed by crash-and-burn exile reminded me of Hu Yoshida's ill-fated attempts to establish technological independence of Hitachi's approach to storage virtualization (here and again here).

I say "ill-fated" because not only has Hu once again demonstrated his abject lack of true understanding of his competitors' products, but he has also riled up the wrath of Sir Whyte in the process. BarryW has not only rebuffed Hu's original misrepresentations of SAN vs. Storage virtualization, he has now also embarked on what looks to be a multi-episode tutorial on how SVC really works.

Good sport, that. But a word of advice, BarryW - you may indeed be embarking on a Lifelong Learning adventure of your own!

monaco and prince albert ii

On US Election Day our port of call was Monaco. And our excursions took us to visit the the Monaco Cathedral, the Prince's Palace and of course the Monte Carlo Casino ("Burke. Barry Burke." I said, as I handed them my passport). 

You know, you've just gotta admire a guy who is the head of state of the world's most densely populated sovereign country. He's not flashy nor seemingly authoritarian - he just seems to quietly rule his (quite wealthy) country of 36,000 with a benevolent hand. But several of my cruise-mates were totally surprised to witness that the good Prince chose to hang out with all the American visitors and ex-pats down at the Stars'N'Bars on Election Night 2008 (and yes, apparently he was rooting for Obama).

By the way - it is interesting to note that citizens of Monaco are not even allowed to enter into the Monte Carlo Casino. Turns out that the country owns the majority stake in the Casino, and laws prohibit the conflict of interests of owners gambling against themselves.

Seems somewhat similar to the twisted knot that StorageBod has lured NetApp into with his WAFL is a Platypus discourse a couple of weeks ago.


nice is nice. benchmarketing - not so much.

Harbour_of_Nice One of my favorite stops was Nice, and it was actually very nice. That's Nice, as in the resort city in Provence-Alpes-Côte d'Azur (aka, the French Riviera). Even though it rained cats and dogs the whole time we were there, the city just has the feeling of a warm embrace, and most of us agreed we'd like to go back for a longer visit.

Not so nice, on the other hand, was the reaction to my previous post about benchmarketing. While most managed not to attack me personally, almost all missed my point altogether. At the core, my complaint isn't about science experiments at all - it was (and is) all about the continued use of a  benchmark suite which has no bearing on reality as a comparison tool.

And not only because the configurations that vendors run them on are ludicrous. Which, indeed, they are, as one end-user noted. But even he's been misled - he runs the SPCs on "real" configurations, and I assert he still gets misleading results.

Why? Because indeed, as IBM and ESG admit, benchmarks like the SPCs do not capture the workload dynamics that result from running multiple different applications against a single array.

And whether or not those multiple applications are each running in a VM on a single host, or if they are each actually running on different physical servers truly makes no difference. The bottom line is non of the SPCs capture the true essence of multiple dynamic workloads on the same array.

The simple fact is that the SPC's don't present a workload that looks ANYTHING like what an array like Symmetrix routinely supports.

In the real world, an array like Symmetrix is rarely afforded the luxury of supporting a single application running on a single host - it happens, but it's not the mainstream normal use case. No, in the typical Symmetrix use case, I/O requests from multiple different applications running on multiple different hosts arrive on each and every front-end port, and these requests are for a very disparate group of LUNs or Volumes. This chaotic stream of requests arriving at a given front-end port is effectively randomized across all the target back-end devices, even though the net result may well be sequential requests to each LUN device. And between each I/O request to a given LUN there is typically some sort of delay while the host application processes the retrieved data; meanwhile some other application will probably post its I/O request to some other set of LUNs or Volumes.

And unlike any other array on the planet, the Symmetrix will sift through all these chaotic I/O streams and dynamically adjust its queuing priorities, pre-fetch and cache aging algorithms to deliver the fastest possible response times for each application.

The SPC benchmarks look nothing like this. There are relatively few LUNs required by the tests, and these are typically spread across as many spindles and the benchmarketing vendor can support. All I/O is generated by a single host, and the I/O requests are created in a specific, stochastic order, sent as quickly as possible down each I/O port. Each LUN receives a predictable percentage of the I/O requests, yet these are artificially randomized such that cache hits are minimized to ratios well below the real-world norm for most applications.

In essence, the SPC's measure nothing more than the efficiency the disk I/O path of a cache miss, which tells you nothing about how efficiently and effectively the storage array delivers cache hit I/Os. 

And as a result, these SPC benchmarks are of no use when trying to compare how an enterprise-class array will handle real-world workloads. Maybe they're sufficient for less intelligent arrays with less advanced algorithms and limited caching capabilities (IBM's SVC and DS8000 come to mind), but these simplistic benchmarks are nothing but misleading for truly advanced storage arrays.

Does the SPC care? I think not. Nor does the competition want to do anything to change the status quo - witness the fact that nobody (and I mean NOBODY) has stepped forward in the past year (not to mention few weeks) to work with Dr. Kartik on a better benchmark.

barcelona and els quatre gats

4Gats_17 The last stop on our cruise was the city of Barcelona - truly a city of energy and excitement. From the revolutionary architectural works of Catalan Modernisme pioneer Antoni Gaudi, to the hangout of famed artist Pablo Picaso, to the awe-inspiring Temple Expiatori de la Sagrada Família, Barcelona is truly a wonder to visit (mind your wallet as you stroll on La Rambla, though - Barcelona is the training grounds for pickpockets and La Rambla is where they get their masters degrees).

One of the more memorable stops in Barcelona was dinner at the famous (and fabulous) 4Cats Restaurant - a Bohemian-esque throwback where Picaso held his first solo art exhibition, and where he also spent many the evening wining and dining the worlds' challenges away with his contemporaries.

The proprietor of the 4Cats was also a visionary, for he managed somehow to retain a number of Picaso's sketches, many of which adorn the walls of the dining room along with other originals and prints of the famous artiste.

Visiting the city where Gaudi and Picaso made their marks was an excellent precursor to Monday's Atmos announcement. Both men were paragons of innovation; both saw new possibilities where other saw only a country devastated by years of war, tyranny and fascism. And both led the way to a new era of artistic and architectural excellence.

As undoubtedly will Atmos.

Sure - there's lots of hype around Atmos, but hey - what else do we have to get excited about this week?

Seriously, though, I am somewhat taken aback by the reaction of some to the announcement, especially those that haven't taken the time to try to understand what Atmos really means. Granted, everyone will see anything new through the filters of their own localized realities. But some of the reactions are just plain silly.

For example:

  • Atmos isn't anything like a WAFS - if only because WAFS could never scale to the scope of Atmos. If it could, heck - the smart guys who have been building Atmos would have built it upon WAFS. And Google would have built their global infrastructure on WAFS. Heck, even Akami doesn't use a WAFS to get their cached objects close to the users. No - a wide-area file system simply isn't robust enough to handle the scale and scope of the world Atmos was designed for. Nor could any existing WAFS handle the multi-tenancy, secure storage domains and dynamic policies that are the foundation of Atmos.
  • And speaking of policies, some seem to have missed the fact that Atmos policies are established BEFORE an object is stored, not defined afterwards. In this manner, the storing application truly has to have no knowledge about the policies - just insert the objects, and let the system figure out how the established policies apply to the object. Transparently. UPDATE: Steve Todd's post offers more Under the Hood insight into Atmos' policy engine.
  • As to the assertions of "proprietary," Atmos is as open as it gets - you can use SOAP, NFS, CIFS and several other standard interfaces to insert and retrieve objects. Sure, there's a lot of unique features in Atmos that aren't present in any other storage platform today - but isn't that always the case with something that's "new"? And EMC has announced that you'll be able to buy the SW to run on your own hardware, should you choose - so where's the "lock-in"?
    Interestingly, EMC faced similar complaints about Centera when it was introduced in 2002, but even still there are today over 200 applications that are integrated with Centera using one or more of its APIs. And EMC led the way to define XAM, and Centera is the first to support it. So enough with the conspiracy theories already...

Now, granted, most of the nay-saying over Atmos is coming from would-be competitors who now will struggle through the stages of denial and deferral until they finally come to grips with the value proposition of the technology and enter into acceptance and finally come around to attempt to deliver some form of competitive response. We've already seen the attacks from almost all of the expected fronts, in fact. Hopefully, the few we haven't heard from yet are taking the time to let this all sink in first before they react- a wise move, IMHO, for there is lots more to Atmos than the early nay-sayers have even begun to understand.

Still, many others see fit to attack Atmos because they just can't see any use for it - it has no recognizable place within their own storage domains. And if they don't understand the need for it, then by gosh, nobody needs it. One user even laughed that "nobody" buys storage in increments of 120TB, cloud or otherwise.

It's all a matter of perspective, I guess.

Just because not everyone needs a Google file system doesn't mean that only Google does. Atmos seeks to blaze a new approach to "cloud" storage (oh how I hate that term), to create a global storage platform that is not only cost-effective to install and grow, but extremely efficient to operate as well...set-it-and-forget-it cloud storage. And trust me, if your business thinks in petabytes or even exabytes of unstructured data, you're already looking for a totally new storage paradigm, because nothing - and I mean NOTHING - built on current commercial file systems or databases will handle that kind of storage.

Finally, perhaps the biggest laugh I got from Monday's announcement coverage was one writer's back-handed assertion that Atmos threatened EMC's core Symmetrix business. I chuckle because there's not a lot of Symmetrix going into environments to support shedloads of photographs of drunken teenagers, and honestly, that's not really the Symmetrix target market. Nor is Atmos architected for the kind of random I/O workloads typically deployed on a Symmetrix. Unlike the confusion IBM has created between XIV and the soon-to-be-retired DS8000, Symmetrix, CLARiiON, Celerra, Centera and Atmos each offer value propositions optimized for very clearly defined market segments and use cases.

I laugh again just now as I write this - a silly thought just jumped into my mind:

How the heck would you design an SPC benchmark
to measure the performance of Atmos?

I dunno. But I bet someone will try.


PS: apologies to the Storage Architect...see, I didn't do a tear-down in my coverage of Atmos like you thought I would. As soon as I start getting predictable, I'm going to try to change!



TrackBack URL for this entry:

Listed below are links to weblogs that reference 1.029: atmos. with, and without, the sphere:


Feed You can follow this conversation by subscribing to the comment feed for this post.

Barry Whyte

Welcome Back. Hidden in there was an attack on IBM, (DS8K, SVC) ... VERY predictable... you have to admit though, enough snipe'ing and I;ve dragged Hu back into the game :)

Stephen Foskett

Welcome back indeed! You were missed at this most crucial time for Atmos!

Seriously, though, I'm still trying to get my little brain around what this thing can do. "Atmos policies are established BEFORE an abject is stored, not defined afterwards. In this manner, the storing application truly has to have no knowledge about the policies" How do you establish policies for something before it exists? Or does Atmos only "do" generic policies for vast sets of data? Or maybe all objects have to take on one of a few pre-existing policies? And can you change a policy granularly or are objects grouped somehow?

Or did I miss all this in a presentation somewhere?

Thanks for helping me see the light!

the storage anarchist

I'm not the hands-on expert for this, but I do know that Atmos policies can be based on the attributes of each stored object - things such as owner/creator, create location, size, create date, access date, object type, etc. Of course there are additional attributes that can be specified via the SOAP (etc.) interface, but these aren't necessarily required, enabling abjects stored via the NFS/CIFS interfaces to have policies applied to them.

I suspect Steve or one of the others will explain this in more detail...

Chris M Evans

Barry, I don't know what to say: your post is almost friendly! Still, good to have you back.

Martin G

I love the idea of abjects being stored...Is that abject horrors?

But to honest, you pretty much said what I expected you to say about Atmos, it's someone else's baby and you may think it's pretty but you'll let them do the talking. And that is really to your credit. The cruise obviously did you good!!


"Still, many others see fit to attack Atmos because they just can't see any use for it - it has no recognizable place within their own storage domains. And if they don't understand the need for it, then by gosh, nobody needs it. One user even laughed that "nobody" buys storage in increments of 120TB, cloud or otherwise.
It's all a matter of perspective, I guess."

Interesting change of tune, coming from you! Are you referring to Atmos or XIV?? ;)



You mention the "soon-to-be-retired-DS8000".

Are you making a statement of fact about that product being retired soon?

Or are you spreading FUD? If you don't know for a fact that it is being retired soon, you're spreading FUD.

So which is it, Barry?

I got fifty bucks on door #2!

the storage anarchist

Welcome back, SRJ! Still hiding your IP address from reverse DNS, I see.

That's OK - you're still welcome here.

The DS8000 is now over 48 months old. Customers coming off of lease are being offered a "new" DS8000 ("turbo") that brings no new features or capabilities from the original except perhaps RAID 6. Other than that, it is still an array with only 2Gb/s drives, only 2 reboot-to-change partitions, only 8GB of write cache and one that doesn't even offer thin provisioning, or SATA drives, or dynamic LUN relocation, or flash drives, or ... well, you get the picture.

And yes, given that EMC is replacing DS8000's with CLARiiON's on a daily basis, I'm willing to put up $50 that says IBM replaces and/or retires this archaic hunk of junk in 2009...are you in?

As to Atmos vs. XIV...umm, let me see. One is a one-size-fits-all block storage device that requires you buy 180TB to get 80TB usable - no more, and no less. And the other is a cloud-optimized, policy-driven object storage platform available in 120, 240 and 360TB configurations that will seemlessly integrate and scale to support billions of objects and multiple petabytes geographically distributed around the world operating under a single namespace.

No, sir, I am not changing my tune.



I feel I ought to be slightly offended at your accusation that I'm somehow hiding something about my identity. I wouldn't even know HOW to hide my IP address from reverse DNS. Since we already settled the fact (via private e-mail) that I don't work for IBM and never have, I can only assume that your accusation is an attempt to somehow discredit or devalue my comments. Fair enough, I suppose...it's your blog. It's still slightly offensive, but hey - you work for EMC...what should a guy expect?

No new features except RAID 6, eh? Either you have been asleep at the wheel and not keeping tabs on the competition (which I obviously doubt), or this is another fine example of why EMC has the reputation it has.

As for the bet... I'm also confident that IBM will make changes to the product in 2009. But due to the fact that I have yet to see a single DS8000 be replaced by a Symm (let alone some slow Windows-based modular platform) in any of the customers I've dealt with over the past several years (quite a few), I am not convinced they will change the architecture. So, if they retire it completely, you win. If they replace it with a totally different architecture (something like the Symm, USP, or even an XIV-type architecture), you also win. However, if they simply update it with an evolutionary upgrade (upgrading to POWER 6 hardware and introducing new software features like thin-provisioning, for example) and change the name, I win. You still in?

Referring again to your comments about Atmos vs. XIV... my point was not to compare the products, which may not have been clear. My point was that you, rather emphatically, made that EXACT SAME argument against the XIV when it was announced. Now that someone has made the same argument against Atmos, you are rather dismissive of the argument. If it's crazy for someone to buy storage in 80TB chunks, how much crazier is it to buy in 120TB+ chunks, regardless of what it's for or how it's used!?!

Indeed, sir, you have most definitely changed your tune. Your readers aren't tone-deaf!

BTW, in case your competitive team hasn't informed you yet, XIV is now available in a much smaller capacity. (And no, I'm not referring to Capacity on Demand.) Either wake those guys up, or (if you did know) spare us your mis-information. After your XIV "pre-announcement," I'd find it hard to believe you weren't up to date with the latest XIV news! For shame!

the storage anarchist


Be not offended. I routinely check the RDNS of IP addresses of the comments I receive. It is the rare one that can't be resolved, and yours is one of those. If not by your own action, then you might want to look into it. Makes you very anonymous.

As to new features in the DS8000, well, sir, the only features I've seen of late (other than RAID 6 and a new drive capacity or two) have been proprietary lock-ins to new z-Series enhancements (EAVs, HyperPAVs, etc.) - features IBM inhibits or delays its competitors from supporting by their licensing policies.

On the other hand, I've listed several features that have NOT been delivered on the DS8000 that are already available on both DMX and Hitachi's USP-V variants - what have you to say about those?

And no, I won't take your bet as defined. I'll take it straight up - IBM comes out with ANY new DS8000-class product this year, be it new architecture, P6 processors on the current hunk of tin, or even just a new name (DS8000 Turbo Mark II), and I win. They don't by December 31, 2009, and I'll send $50.00US to your favorite charity.

As to my "tune", let's set the record straight first. The smallest XIV configuration available, according to every single spec sheet and >fact sheet I can find today on IBM.com is still 180 1TB drives.

And so is the LARGEST XIV - if you buy TWO, they work as two separate 180TB/80TB systems.

But the important part of my assertion is that your "regardless of how it is used" qualifier does not apply - in fact, the use case makes ALL THE DIFFERENCE!

The fact is that XIV is being positioned as general-purpose storage, not something optimized for "CLOUD". And in general-purpose land, 180 drives and 80TB usable is HUGE...in fact, I suspect that 80TB usable is larger than the average DS8000 leaving the factory last quarter.

Atmos/Infiniflex, on the other hand, is targeted at CLOUD, where 80 or 120 or 180 or even 360 TB is tiny. Different use case, and in fact a relatively NEW use case - one not addressed by XIV, since IT CAN'T SCALE UP (at least not yet). Atmos scales up by adding storage enclosures into a single management domain and globally distributed namespace, and TODAY Atmos supports storage domains measured in petabytes and in billions of objects.


As to new, smaller XIV's - I'll have to admit that I haven't heard about them yet. And since IBM hasn't modified the spec sheets, I suspect there's a lot of people at IBM who haven't heard about them yet either.

But it makes sense - 80TB is indeed far too much for general purpose, and probably makes for more cost than the market will bear - a learning that EMC's Centera folks gained over 4 years ago, when they first started offering smaller configurations.

I'll have the competitive guys look into your assertion ASAP - thanks for the heads up!


Always glad to contribute factual information to the discussion here, Barry! Let me know whenever I can be of service!

Well, it seems our bet is off...but you've served my purpose in exposing your FUD and deflating your trumped up "soon-to-be-retired" claim. A very small sampling of some of the other incremental new features that have been introduced to the DS8000 include Space Efficient FlashCopy, Storage Pool striping, support for up to 1024 disks, Dynamic Volume Expansion for both open systems and mainframe environments, etc, etc... And yes, it does support SATA drives, and has long since supported FATA drives.

As to features that the Symm has rushed to market with (mostly because EMC's main strength is its marketing department) such as flash drives, puh-lease! The restrictions on the Symm configurations with flash drives are so ridiculous as to not even be worth a second look! How many flash drives does it take to swamp that slow DMX, Barry? How much time and money is it going to take your R&D team to revamp the architecture to allow flash drives to provide some actual value to your customers? Who BUYS that???!

Interestingly, one would assume that a DMX with flash drives could easily blow away SPC-1 benchmarks set by all of your competitors. Why not silence all of your critics with one swift, devastating blow? The Lord only knows what your marketing department could do with that ammunition!!!

About XIV positioning - haven't we covered this already?? IBM has never positioned the XIV as anything but a "Web 2.0" storage platform. The fact that you're still trying to reposition it for them just to keep your faulty arguments alive is just plain silliness. It would be like Tony Pearson constantly claiming that Atmos is positioned for production OLTP workloads. Silly. I didn't question or try to re-define the use-case for Atmos - why continue to do so for the XIV? You're free to argue that XIV isn't a good Web 2.0 platform...but your readers can see right through your straw man "general purpose" redefinition.

Now, it's possible that IBM will start to position it as such, once they implement some additional features not currently needed in the Web 2.0 environment. If/when that happens (I have absolutely no knowledge one way or the other), I'm sure we'll be discussing it again here.

Looking forward to it.

BTW - I do use the free OpenDNS service, but have not knowingly blocked reverse lookups. Perhaps it is a default feature of their service? In any event, I'm not sure what value there is in knowing that my ISP is Comcast. If you want to know something about me, you've got my e-mail address....ask away!

the storage anarchist

Sorry to see you back out of the bet, but that doesn't prove anything. In fact, my conditions are consistent with the ineveitable retirement of the DS8000 in 2009.

The list of features you provide were all delivered by DS8000 competitors AT LEAST one year earlier, with the exception of the proprietary lock-in DVE.

And no, the DS8000 DOES NOT support SATA drives until next year, as you can see for yourself here (quote):

Product Preview
Serial ATA (SATA) disk drives: IBM Intends to enhance the configuration options of the DS8000 series with support for:

1 TB 7,200 RPM SATA disk drives, doubling the raw capacity of existing models up to 1024 TB for DS8300 Turbo Models and up to 384 TB for DS8100 Turbo Models. IBM intends to provide this capability in early 2009.

BTW - did you perhaps confuse the new entry-level SVC "pink" for a new smaller XIV? My sources at IBM deny the existence of any smaller XIV configs. I'm beginning to suspect the credibility of your assertions...

And for XIV positioning, I'm not redefining the use case - I'm repeating what I've seen in IBM presentations to EMC customers.

But let's say it really is "Web 2.0 storage". Tell me again how an SVC in front of an XIV makes for a "Web 2.0 platform" - why would IBM even offer that? And can you explain how a Web 2.0 platform that only scales to 80 usable terabytes is supposed to be "bulk storage"? For that matter, how many "Web 2.0" applications use block storage? Web 2.0 is all about Objects!!


Finally, as per the flash drives. If all it took was marketing to bring them to market, then why haven't IBM figured out how to integrate them into ANY of their platforms yet - almost a year after EMC's "marketing department" figured it out? They're no available (or even pre-announced) on the DS8000 nor any of the storage platforms that they OEM - not even the DCS9900 which is supposedly for "high performance computing."

And you miss totally why BarryW is just starting to figure out - it's not about the maximum number of IOPS you can support - you can always stripe your workload across a huge number of 15K rpm drives for IOPS. The flash drive value proposition is RESPONSE TIME for LARGE working sets. DMX has been delivering the lowest possible response time for years, thanks to it's intelligent cache; flash drives help accellerate performance without requiring a total re-tool of hardware, software or applications.

Even saved one customer several MILLION dollars in unnecessary z10 MIPS (see here).

But throw all the FUD you want about flash: one thing is inarguable. If you need the performance of flash, there is only one storage supplier able to deliver today - EMC.

Too bad you are unwilling to put your money where your mouth is on the bet, though. I guess you agree that IBM has to replace the DS8000 with SOMETHING in 2009, even if it is only a processor bump.



I stand corrected on the SATA drives. It seems the feature release has been pushed back. My point stands though, that IBM has continually improved the DS8000 since its release...something that is only possible because of its core architecture. And it's really a misnomer to say that it doesn't support SATA anyway, since it has supported FATA for a long time, but nonetheless, I conceed the point.

By no means have I mistaken the SVC EE for the new smaller XIV package. While it has become an instant hit with some of my smaller customers, the SVC Entry Edition is not easily mistaken for an XIV system.

Doubt me if you must...I'd be shocked to see you pull back the leash on your competitive team just because your supposed "source(s)" at IBM aren't giving you the time of day.

"...repeating what I've seen in IBM presentations to EMC customers."

--Wow. So was it the same "sources" at IBM (who surprisingly know absolutely nothing of the new smaller XIV configuration, BTW...) who gave you that bit of information? Or were you sitting in those customer presentations yourself? Curious that IBM would be giving presentations to customers about a product that hadn't even been announced yet! Your "sources" must be a VERY unique brand...only able to see into the future, and never able to see the now! Every marketing department ought to have a few "sources" like those!!!

About flash.....the fact that IBM hasn't announced flash drives REINFORCES my point! The market hasn't decided yet where flash provides the most value. IBM is certainly not ignoring the technology - you've groaned about Barry W's SVC flash experiment repeatedly. Instead of rushing to market for the sole purpose of getting bragging rights, IBM seems to prefer to settle on a solution that actually adds value to the equation...a term not afforded to the DMX flash conundrum.

You are partly correct about response time often being more important than IOPS. My sizing exercises for System i customers have proven it to me in many situations. Thankfully the DS8000's strong suit is response time (particularly when compared to the laggard DMX), even without flash and the astronomical price now associated with it, thanks to EMC and the laggard. That would be one of the primary reasons why System i customers almost invariably choose the DS8000 for external disk and why the laggard continues to flounder in that market. The poor DMX gets implemented only to get ripped back out several months later because it can't keep up. In those situations, you can't help but feel sorry for that shiny "new" box as it gets replaced by a seasoned pro.

And my money is right here waiting, and has been since 2006...right around the time you guys started predicting the demise of the DS8000. I'm not surprised to see a false prophet back out of a bet when it comes to a prediction even HE can't get wrong! Yes, Barry, the rest of the world is moving on to POWER 6! The DS8000 will get an update because POWER 5 is being replaced...not because the DS8000 architecture is lacking, as you insinuate. In contrast, your assertion that the XIV is the inevitable replacement for the DS8000 is laughable at best. I'd take that bet ANY DAY! Speaking of putting your money where your mouth is...how about it?

Great chatting with you!

the storage anarchist

Getting a little squirmy, I see, what with all your back-tracking and redirection. Been taking lessons from TonyP perchance :)?

So, let's sort this all out for anyone who cares to read these comments:

1) Yes, indeed, the DS8000 that you can buy today will be replaced with a new one by the end of 2009.

2) Flash drives are indeed about response time, and customers looking to shorten batch windows and improve TPS can get a proven solution today from only one storage supplier (while IBM's marketing department looks frantically for ways to cover for engineers who can only do science experiments).

3) Your exposure to iSeries customers is acutely limited, because a large percentage of them have been buying the only non-IBM external storage alternative from EMC for the last 10 years.

4) You have inside information about future IBM products that you feel necessary to flaunt over me as if I'm stoopid and uninformed. So be it.

5) You have no apparent that SATA is signigicantly different and harder to support than "FATA." Hint: totally different electrical interfaces AND different command sets (not to mention block sizes, reliability, queue depths, etc.). FATA was a cheap Fibre Channel drive, by the way, and not FC tacked on to an ATA drive.

6) "Continuous improvement" in your eyes doesn't include key features like thin provisioning, dynamic cache partitioning, SATA, or Flash drives, increasing write cache - all features offered by competitors for months if not years.

7) Your job involves giving advice to customers about storage configurations.

If I'm right about that last one, I'm thinking your customers might want to get a second opinion.

At least we agree on one thing - the XIV is indeed a laughable replacement for the DS8000.

In fact, given the recent admissions by IBM to inquisitive prospects that the XIV data loss risk I have presented is indeed accurate, it's a pretty laughable replacement for ANY block storage platform.


Squirmy?! I'm as sure-footed as a mountain goat! =)

Ahh...the limitations of electronic communications... Oh well.

1. Agreed. After all, those POWER 6 systems are a dominant force in the industry. Why continue to manufacture POWER 5 just for the DS8000?

2. Nice try. IBM engineers could take the easy route too, and just plug in some flash drives with minor modifications to the drawers and code. Most customers expect more than shoddy marketecture though...

3. =) I will kindly disagree with you on this one. I might point out a very large retail sporting goods company as just ONE example to back up my claims. The iSeries is particularly strong in certain verticals...I happen to focus on them. EMC actually approached me to help build their iSeries customer base a couple of years ago. You can guess how my response probably went. I assure you that I have a particularly broad and comprehensive exposure to iSeries environments.

4. I apologize if you took it that way - it was not my intent to degrade you in any way...only your FUD. And Barry, wouldn't you agree that I and the rest of your readers would be justified in making that EXACT SAME comment about you and your "pre-announcement" of the XIV? Be honest with yourself here. And for the record, I have absolutely no inside knowledge of FUTURE products. This is a configuration being sold NOW. Rest assured that I was not one of the first to hear about it either.

5. Thanks for the (quite unnecessary) explanation. Still not sure how electrical interfaces and command sets matter to the customer if what they're after is a lower tier of disk for a lower cost. The differences you mention (and some that you don't) all fall in favor of FATA!!!

6. Are you confusing the term "continuous" with "all-encompassing"? You're putting words in my mouth again...

7. True. And yes, ALL of my customers get second opinions on every engagement...what customer doesn't? Thankfully, they tend to like my opinions more often than not. Particularly in the iSeries world...

Have a good one Barry!

The comments to this entry are closed.

anarchy cannot be moderated

the storage anarchist

View Barry Burke's profile on LinkedIn Digg Facebook FriendFeed LinkedIn Ning Other... Other... Other... Pandora Technorati Twitter Typepad YouTube


I am unabashedly an employee of EMC, but the opinions expressed here are entirely my own. I am a blogger who works at EMC, not an EMC blogger. This is my blog, and not EMC's. Content published here is not read or approved in advance by EMC and does not necessarily reflect the views and opinions of EMC.

search & follow

search blogs by many emc employees:

search this blog only:

 posts feed
      Subscribe by Email
 comments feed

 visit the anarchist @home
follow me on twitter follow me on twitter

TwitterCounter for @storageanarchy

recommended reads

privacy policy

This blog uses Google Ads to serve relevant ads with posts & comments. Google may use DoubleClick cookies to collect information (not including your name, address, email address, or telephone number) about your visits to this and other websites in order to provide ads about goods and services of interest to you. If you would like more information about this practice and your options for not having this information used by Google, please visit the Google Privacy Center.

All comments and trackbacks are moderated. Courteous comments always welcomed.

Email addresses are requested for validation of comment submitters only, and will not be shared or sold.

Use OpenDNS