* Posts by MityDK

38 publicly visible posts • joined 22 May 2014

La La La, I can't hear you: FCC responds to net neut concerns

MityDK

Net Neutrality is government censorship.

The internet got along just fine without government interference. The people who want Net Neutrality want to be able to impose governmental controls on speech and decide who can say what.

Is that "hate speech"? Well, you're not allowed on the net, bub.

Give me corporate profiteering over government censorship every day of the week and twice on Sunday.

Oh and BTW, elections have consequences, a wise man once said. You don't get to lose every branch of government and still make the rules.

Always late to the party, IBM reveals itself to be NVMe fanboy

MityDK

To clarify, SVC in the data path isn't a problem for latency or features for customers, it's a problem related to vendor lock in, complexity, etc. SVC technology is decent, and has a lot of uses. Many enterprises I work with are unhappy about having to use SVC to get data services, and every storage offering IBM has uses some form of SVC, full blown, stripped down, embedded, whatnot, in their platform and customers want to move away from that.

NVMeF promises to fully decouple data services from JBOF in a granular fashion, removing the legacy monolithic stack limitations, while squeezing even more latency out of the flow. You're correct, IBM can't build that. My comment was really just that IBM need to acquire the technology and do it immediately, because they are very late in coming to this realization, and their current proprietary flash offerings are now legacy.

Open-source storage that doesn't suck? Our man tries to break TrueNAS

MityDK

Re: CIFS vs SMB

SMB in this case refers to the application layer network protocol Microsoft uses for their OS to talk to each other, called Server Message Block.

The first version was called CIFS, common internet file system, and was terrible. Since then, they have released version 2.x and 3.x and are now on 3.1.1 for windows 10.

So when people say CIFS, they may be referring to SMB in general although technically CIFS was really SMB 1.0. Samba is the linux/unix based implementation of SMB.

SMB didn't really start working halfway acceptably until 2.1, arguably, but there's really no way to not use SMB if you are using MS in the enterprise.

Seagate flashes 60TB (yes, sixty) SSD monster

MityDK

10/10 trolling.

HDS freezes high-end storage hardware investment

MityDK

Re: HDS Following EMC's Lead

Unless EMC can fix Xtremio's major code problems with scale out, VMAX 3 with their new code and all flash direction are not going anywhere.

I wouldn't be surprised to see xtremio hit the shelf, and VMAX take it's place. You can't have enterprise all flash in a platform that keeps crashing and won't scale out as advertised--that's xtremio today. VMAX has been far more stable of course, but with the removal of enginuity for their new code, we shall see if it survives.

Sick of storage vendors? Me too. Let's build the darn stuff ourselves

MityDK

Nice troll piece fishing for outrage from storage guys. Ridiculous.

Memory and storage boundary changes

MityDK

I'm pretty sure it's meant to say NVDIMM-N, but it's latency is in the 10s of nanoseconds. There's some problems with the chart, but overall it's useful as a relative measure.

Four crucial deals to pluck Violin Memory away from the trash can

MityDK

Re: There are so many Flash memory providers though.

They are a hardware defined solution, which meant they had a substantial advantage for years. That advantage has since slowly gone away until now it is a significant liability. To develop the next platform on hardware, or to move to a software defined solution using COTS takes a lot of time and money to build, which they do not have--either of--and this is why they went from being a really great 1st gen AFA option to a almost universally ignored 2nd wave AFA.

Even if the FSP platform is good, they are so far behind the curve in almost every aspect business wise they probably can't recover and must sell. Whoever buys them will simply have a decent product that will have a really hard time competing in the marketplace against much better next gen tech AFA competitors, but I think still has some value in their existing install bases.

my 2c

EMC's hardware 'quantum leap' is more of a brisk catchup stroll

MityDK

Re: So, let's see

Well is that 60K list for 1 node or for 4 nodes? .. since the minimum configuration is 4 nodes. If it's 60K list for 4 nodes, and Street price is like 25-30K for 4 low end servers with some disk, that's not expensive. If that is for 1 node, then the pricing discount would have to be really high in order to make sense.

All-flash hope-dash: The future is hybrid

MityDK

Re: Agree, hybrid is here to stay

I doubt it would be any faster than their current hybrid arrays for VSI!

Industry vet Khosla kicks Dell-EMC in the innovation crotch

MityDK

Re: Innovation is purchased

Some more acquisitions that turned into multi billion dollar LOBs post acquisition.

VMWare

XtremIO

Data General

Kalpana

and a new one,

Solidfire.

Large companies buy, integrate distribute and support with incremental improvements on existing tech.

Small companies, startups, innovate and create--and take all the risk for failure with investor capital. I think it's a good model that works pretty well all in all.

Gartner sees enterprise SSD-HDD revenue crossover in 2017

MityDK

Bad troll is bad.

NetApp needs more than SolidFire: Slip Simplivity into your Xmas stocking

MityDK

Haha Chris is running NetApp like a fantasy baseball team.

Who else should they acquire? Brocade perhaps?

Cisco needs to get off its backside if it's to remain storage king in 2016

MityDK

Re: Remain storage king

Was hoping someone would jump in and explain exactly how Cisco is the storage king, alas.

No really, is there a hidden history of storage from another world where Cisco is the primary storage vendor of choice that someone with this esoteric and arcane knowledge is willing to share?

Could NetApp's purchase of SolidFire see the end of ONTAP?

MityDK

Re: Perhaps the worst article ever.

Ontap 8 is new and fresh and innovative? Is this George Kurian? You're supposed to disclose before you begin a rant like this.

Only small and subtle differences between NetApp CDOT and Xtremio or Kaminario? OK now you've just told everyone you're completely ignorant as to how these architectures are radically different from each other and that you should not be taken seriously.

The only thing you said with any truth was that Solidfire is different from Ontap, and it fills a gap that NetApp has in their offerings, which is for a viable all flash offering that can actually scale, something they don't remotely have. If they can somehow get Santricity, ONTAP, and Element to be managed/play well together, that would be great. Historically they have not been able to integrate acquired technologies either quickly or elegantly. It looks like a good play for NetApp I think. We'll see how their execution goes.

NetApp sings to Solidfire: All I want for Christmas is buying you

MityDK

Everything negative that everyone has been saying about CDOT and AFF was just validated by this purchase. Flash ray: DEAD. Good thing NetApp has 5B in cash to absorb the losses from these types of terrible decisions.

I wonder what Cisco will do now?

We Kidd you not: Ex-NetApp CTO Jay speaks his brains on storage tech

MityDK

Re: And now we know why Netapp has languished for years

Would love to know which of his insights were completely ridiculous and which weren't, and what do you see in your crystal ball that he has gotten so clearly wrong to you?

Perhaps not anything in his forecasting that was unexpected or exceptionally imaginative, granted. So what did he miss that's a gamechanger? Tell me more.

Could NetApp buy SolidFire? It would be outside its comfort zone

MityDK

Why in the world would NetApp acquire a technology that is essentially exactly what they already have had for years and years?

Pretty sure NetApp was the original hybrid vendor, with their PAM cards or Flash Cache read caching in flash and NVRAM handling writes in memory, with HDD to persist the data.

Nimble's I/O handling architecture is almost identical to NetApp in many ways and they really bring no value add to what NetApp is offering today.

What they did better was selling a block system with CASL that worked great as a hybrid at a fraction of the cost of NetApp, eliminated the utter BS licensing scams that NetApp was inflicting on their customers, and implemented a super clean, easy to use GUI with a great management program, proactive wellness or Infosight as they call it now I suppose.

NetApp's block efficiencies sucked and still suck because of WAFL, their software was insanely expensive, maintenance renewals were highway robbery, their GUI wasn't easy to use, and they had no proactive management of the array.

If NetApp acquires Nimble, what do they get out of the deal? An array that functions basically just like their current hardware does, with unportable and incompatible software and management features, and oh by the way, doesn't support NAS protocols. What they need is a super fast all flash array that they can bring under their NTAP / CDOT feature/management layer to provide performance/scalability their hardware can't do, while still giving their customers all the rich feature sets that NTAP has provided for years, not the other way around.

Nimble doesn't seem like a great fit.

MityDK

Re: NetApp acquiring SF? Keep dreaming

"It's a joke at the Enterprise Level."

This, exactly this.

And that's not something they can fix, it's a fundamental part of their architecture and would require them building an all new product. Just look at how they handle metadata per node, or access to the primary LUN, or MPIO, or node failover, or iSCSI throughput limitations, etc etc.. it's just not really enterprise gear.

MityDK

Re: wut?

"Its had a tough few years for ONTAP due to the transition but its integration into multiple ecosystems is unparalleled."

Stop drinking the kool aid brother, NetApp has had more than a few tough years with NTAP and it's integration USED to be unparalleled, but they sat around for years on their laurels and now are really a legacy player, they are not driving innovation into any spaces for years now.

The main area where they are completely dead in the water is in their all flash array offerings. Santricity has no value in the enterprise, and AFF is simply not performant or scalable enough when compared to the industry leaders and visionaries.

Tiering up: Our man struggles to make sense of the storage landscape

MityDK

The only useful part of your post was where you accurately self portray as an insufferable pedant.

Off-key Violin Memory stuck on a bridge over troubled waters

MityDK

Re: will the whole company be acquired?

The problem with being acquired is that they are a hardware based solution. So their R&D and tech turn times are always going to be expensive, slow, and behind everyone else who is a software based solution.

So why would anyone buy yesterdays technology that can't easily move to whatever tomorrow brings. That's why their stock is so low imo, their product line today is pretty good.. but tomorrow looks like a dead end. They have no money for future R&D and new tech development.

EMC-Dell dynamic duo: Mike's my ‘brother from another mother’ – Tucci

MityDK

Quite simply.. there's a ton of product overlap, and EMC's products in almost every case.. VNX, VMAX, ISILON, Xtremio, Atmos, Scale IO, VMWare, Vspex Blue, Data Domain are either market leaders or far superior to what Dell has.

Dell's value proposition is hey look how super cheap our kit is! Did we mention it's basically free?

Dell's days as a storage company *cough* are over.

You know how they are going to pay their debt load? No more R&D cash burn on the EMC side.

Pure next in line to put boot into Dell

MityDK

Re: Hmm...

Nonsense. Competition isn't howling at all, more like shaking their head at the mountain of debt Dell is taking on to do this deal, and the inevitable bloodletting as redundant positions and technologies are shut down and eliminated. The only competitor I see really bent out of shape is HP, but only because they blew their chance at acquiring EMC over a dispute on the price. Meg Whitman looks bad in this deal. But her criticisms of the deal are still accurate--it's just that HP has the same problems too.

The incredible IT hulk: Dell + EMC - did someone say 'synergy'?

MityDK

Re: Interesting merge, let's see how it ends

Cisco MUST acquire a storage company or two, one for file and one for block. As of right now, they are completely shut out of the converged/hyperconverged arena with this merger.

Nutanix, Simplivity, Violin, Kaminario, Tegile, Tintri are all available for a song right now.

Cisco must get bigger or become much smaller as they get shut out of deals.

NetApp slims down latest controller, beefs up channel efforts

MityDK

Still not buying the "scale out" argument from NetApp. It's not scale out.

Also not buying into the All flash FAS improvements to NTAP. ONTAP still sucks for all flash.

Lastly, not excited about 5$/GB RAW pricing either. That's really quite expensive still.

Amazing innovation however, putting two controllers into one smaller box. Compelling.

Nimble flashes the all-flash array as ‘intense’ consolidation period approaches

MityDK

Re: Not so fast...

Yes, both these things are weaknesses of Nimble. Their lack of a File protocol also has hurt them.

The Dedup comes into play when you are talking about $/GB of SSD vs $/GB of NL-SAS. They could get away with just compression with the deep and cheaps providing data persistence. At a 2:1 ratio which is what they typically get with just compression, it's going to be harder to make that $/GB number work vs competitors in the all flash space when there's no cheap 8TB drives providing the capacity.

CASL wasn't "written for flash". It's a great block OE and works really well, but writes coming into the Nimble never touched flash, as far as I understand it, writes are dealt with in DRAM (with a BBU to make it NVRAM) and then laid down in big stripes onto disk. The SSD layer was read caching only. CASL might work well for flash also, because of the way they aggregate writes into single large stripes to be written, but it's heritage is spinning disk entirely.

File protocol is less important, but it's always hurt them vs NetApp and Tegile. As an AFA, probably won't matter as much. As a hybrid, yes definitely it has taken them out of deals.

Nimble makes a great product, but it's going to have some major challenges vs Pure and Xtremio among the other players in the AFA space.

Smaller EMC VNXe unit revealed, then hidden again

MityDK

Blech.

NetApp cackles as cheaper FlashRay lurches out of the door

MityDK

Re: Hmmmm

NetApp announced nothing here, other than to say they are dropping their pants on price, undoubtedly because they are losing so badly to the other players in the field, oh and they will offer 7 years of support to compete against Pure Storage's Forever flash program.

EMC did the same thing with Xtremio, albeit that happened at EMCWorld.

Flash Ray still does not exist.

Bottom line is these things were done to try and protect NetApp's existing install base. Their fundamental underlying architectural and OE problems are not fixed, and they will not be winning any competitive Net New accounts with this stuff. It is however, a step in the right direction.

This article is almost entirely pure hype with no substance. Nice Job El Reg.

NetApp's customers resisting Clustered ONTAP transition

MityDK

Re: CDOT fail

Sounds like you guys are migrating TO a 4 year old legacy array. That's the problem right there. CDOT is not ONTAP, and it's not simple, not easy and not elegant. CDOT's big features? Federated move+manage. Extremely compelling tech about 5 years ago--today.. not so much.

Hyperconverged solutions can't live without flash

MityDK

Nodes Dedicated to storage?

"Two nodes are MCS+NVMe "godlike" nodes where the really sexy workloads live. Four are storage-heavy nodes that have heaps of storage and a bunch of really fast PCI-E or NVMe storage."

Oh you mean like an all flash or Hybrid storage array?

Novel concept.

NetApp veep: 'We've shifted 750,000 all-flash arrays'. Er, really?

MityDK
FAIL

Simply put, NetApp hasn't sold 750,000 EF Arrays. The EF platform may have been sold that many times over the decades of it's existence through many different companies, but for NetApp to say that is simply false. And no amount of spin is going to polish up the turd that is NetApp's current flash story, be it all flash FAS with ONTAP, EF series with Santricity, or Flash Ray with Mars. It only looks good compared to Hitachi or EMC's legacy platforms, not against any of the new vendors.

Let's talk about the (real) price of flash and spinning disks

MityDK

Apples and Oranges, mate

This article was supposed to be about the REAL costs of spinning vs flash. Real costs take into account things like maintenance, power, cooling, rackspace, support, and also look at data efficiencies which flash is built around, deduplication, pattern removal, compression etc which are the hallmarks of all flash or hybrid type solutions.

I find this article to be unserious. I feel like the author is trying to prop up the horse and buggy market by telling us combustion powered cars are more expensive and will continue to be for some time.

SanDisk opens its cages, sets its mutants FREE

MityDK

It had to happen

I was waiting for that other shoe to drop... Sandisk couldn't very well produce flash for it's own competitors now could it? That would cause some major heartburn for both parties.

This makes quite a bit of good sense imo, just wonder if Nexgen will be able to survive in the marketplace without the big backing of Sandisk. I'm betting no, but it's possible. It's decent tech, but nothing revolutionary.

Pure: We've created the Everlasting Gobstopper of Storage – 'Forever Flash'

MityDK

Re: It's called leasing

Except it's not just the flash, it's the controller also. So it's not 1Mips for 100K forever.

CPU performance increases dramatically every upgrade, and maintenance costs are separate from hardware acquisition costs. So not like a regular lease exactly.

PEAK ARRAY: Cold fingers of Death stroke Big Biz disk boxes

MityDK

Um, yes I believe it because I see it every week.

These upstarts are moving into these traditional shops with small footprints and point solutions. Cloud storage is also taking some but not a lot yet, cloud computing is more compelling than storage because of bandwidth and security concerns.

But hybrid and all flash are absolutely going in with a very high acceptance rate into the big 3's territory, not for primary production or big scale out file, but as smaller deployments for VDI or Database, no question.

JJ Abrams and Star Wars: I've got a bad feeling about this

MityDK

Re: Amongst the worst...

I hate all of you. Ewoks and Jar-Jar were only surpassed in their terrible awful out of placedness, uselessness and badness by the collective performance of the young Anakin, I thought that kid in Episode one was the worst actor with the worst lines ever until I saw episode 2 and 3, in which Hayden Christensen made me simultaneously cry and homicidally angry with the sheer vast ineptitude of his performance, quite possibly the worst acting work of a bad script ever executed by anyone in every possible instance of the multiverse from forever to eternity.

JJ Abrams can't possibly do worse than Lucas in Episodes 1-3. DOUBLE PLUS UNPOSSIBLE.

Hey, who wants a 40TB all-flash Pure box? I dunno, you got $160k?

MityDK

Re: ... what?

They are talking about effective capacity, which takes into account their deduplication (which they do on a 512B block size, so it's extremely effective), their compression (which is done on variable block size starting from 512B, so again, super effective), and their pattern removal. Thin provisioning has nothing to do with it.

Actual raw usable from the 5.5TB unit is about 4TB, because they use some space for their Purity OE and the Metadata tables and whatnot. The numbers they publish for RAW are just actual raw disk without any overhead applied to them, so the numbers are a little less. But their focus is on minimizing the data footprint rather than raw vs usable, they care about effective capacity.

It has everything to do with data efficiency. Their target markets are Database, VDI and Virtualized environments. VDI will give you 10x+ effective capacity because of so much duplication of data. Virtualized environments are up in the 6x range.

Database is not much for dedup but will compress ok. Dedup comes into play for database when people start making copies of the database, because Pure uses pointer based zero footprint copies that use just a bit of metadata. So Database can vary from 2x efficiency up to 8 to 10 or more depending on how many copies DBAs are making.

Now, you would never want to put unstructured data on these arrays that doesn't dedup or compress... that would be very bad and your $/GB would be through the roof. All Flash arrays aren't for every kind of data type until prices come way way down and densities go way way up.

Anyhoo--that's how they are doing it, and as someone who has installed a dozen of these things for various customers, it works fantastically well. Super fast with great efficiency rates, typically we see 4x-10x, DB on the low side, and VDI on the high side.