click to visit home page
leading the way to the new storage frontier .....
click to read the article -  reaching for the petabyte SSD
petabyte SSDs ..
image shows software factory - click to see storage software directory
SSD software ....
image shows megabyte waving the winners trophy - there are over 200 SSD oems - which ones matter? - click to read article
top SSD oems ..
high availabaility SSD arrays
high availability ..
read the article on SSD ASAPs
auto tiering SSDs ..
the fastest SSDs - click to read article
the fastest SSDs ..

rackmount SSDs

after AFAs - what's the next box?

a winter's tale of SSD market influences

controllernomics and risk reward with big memory "flash as RAM"

where are we heading with memory intensive systems and software?
re rackmount SSDs
by Zsolt Kerekes, editor -
I've been reporting on the rackmount SSD market since the early 1990s.

What's the main reason that most users look for rackmount SSDs today?

In an earlier phase of the market it was mostly about speed (IOPS performance and low latency).

But as predicted in many earlier SSD analyst articles the reasons for rackmount SSD adoption are now many fold:-
  • run faster
  • do more than old style legacy HDD architected systems
The enterprise market has moved to the point where nearly all enterprise data touches SSDs .

So you can't live without them.

There's a lot of complicated stuff going on in this market at the controller, software, architecture and business levels.

And yet despite the size of the market - many user needs still aren't being satisfied by suitable products.

Evolving through turbulent market chaos and technology change in 12 years of enterprise flash the rackmount has emerged as the hot zone of survivalist thinking for SSD storage architects.

It's the form factor where SSD software, micro cloud architecture and amazing utilization efficiency techniques can come together in ways which are impossible to achieve at the drive or server bound layers - even when it's nearly impossible to guess what the next generation box you buy will look like.

There are no easy answers.

In recent years the rackmount SSD market appears to have settled into a predictable latency zoned pattern of products:- performance or capacity optimized AFAs, SDS, hybrid storage arrays etc) but what's next?

I think I have the answer. For more about this see my January 2017 blog - After AFA?
SSD ad - click for more info

For many of these AFA startups a single customer like that is bigger than their whole business plan.
the dreams and illusions of "our product is better than EMC" startups

It's been a tradition in the computer market that users and integrators look to see what their suppliers say about the future of the market and defer to those visions.

Other good places to look for answers were universities (theoretical concepts) and market research companies (numbers).

None of that works with enterprise SSDs.

This is disruptive market where what happens next doesn't follow on the smooth curve trajectory of what happened before.
Enterprise flash - the Survive and Thrive Guide

growing user confidence will spur enterprise flash consolidation
Editor:- April 21, 2015 - In an new article today on I look at drivers, mechanisms and routes towards consolidation in the enterprise SSD systems market along with some other outrageous and dangerous ideas.

"90% of the enterprise SSD companies which you know have no good reasons to survive." the article

At the high end business level - for SanDisk - the ability to monetize flash at the rackmount systems level (which is the most efficient way to convert raw flash chips into usable enterprise SSDs) is a rational next step.
What will SanDisk really get from Fusion-io?

We haven't reached stability yet in reference enterprise designs and use cases.
what kind of SSD world can we expect in 2015?

Whenever a significantly new rackmount SSD comes to market there are some vital things I need to know in order to place it accurately in my mental map - of how it fits in the market.
the 30 seconds - checklist

SSD endurance
high availability SSDs
the top SSD companies
7 roles for datacenter SSDs
roadmap to the Petabyte SSD
MLC Flash wars in the enterprise
What do enterprise SSD users want?
What an Interface Says About an SSD
How fast can your SSD run backwards?
playing the enterprise SSD box riddle game

The simplest way for vendors to signal to the world that they are masters and commanders of the enterprise flash array high seas - rather than merely floating barges of chips which can be swept along in any direction by the latest technology gust of wind - is to hoist new colors of SSD pricing.
Exiting the Astrological Age of Enterprise SSD Pricing

Notes from SSD market history

The product shown below, from Imperial Technology
(which is no longer in business) is an example of a
rackmount SSD accelerated SAN router which was
featured here on in June 2003.
MegaRam-5000 from  Imperial Technology
MegaRam-5000 Enterprise SSD SAN router
from Imperial Technology
SSD ad - click for more info

rackmount SSD news

other SSD news / DWPD / SSD cloud / high availability SSDs
Western Digital buys Tegile

Editor:- August 29, 2017 - Western Digital announced today that it has agreed to acquire Tegile. The price was not disclosed.

Editor's comments:- Tegile was already using a customer of WDC drives (SSDs, HDDs and the InfiniFlash white box SSD array from SanDisk). So Tegile's flexible pricing models for buying storage were already a good showcase for how to integrate these technologies in a user friendly way.

One of the business risks of Tegile's business model was that its ideal customers were buying usable storage based on utility model pricing and cost expectations which seemed predictable and scalable upto about the tail end of 2016. Unfortunately those cost predictions have been shattered and ruined by the rising prices of memory and associated shortages in 2017.

A few years ago I discussed the risks of the utility model with Tegile - which at that time seemed to be containable technically (because they were obviously related to expectations of reliability, learning from similar customers doing similar things and efficiencies). Tegile's business model meant that external finance could depend on a predictable curve of customer value and cost.

When memory prices rise by 50% or more (instead of going down) those curves mean that repeat customer sales can't follow smoothly from what happened before.

Who's to blame for the costs? Well the SSD companies which were getting most of the benefit. So that's why I think Tegile couldn't sustain itself as an independent company.

For WDC you could interpret this acquisition as a long delayed response similar in thinking to Seagate's acquisition of Dot Hill Systems.

Tegile can provide Western Digital with a workable platform and channel to get SSDs and HDDs into the low end enterprise.

Analyzing where the costs should fairly be allocated between different business units and comparing those to what the market will tolerate while satisfying ant-trust regulators will fuel some interesting questions for the new owner when it takes hold next week.

How much did WD pay for Tegile?

Later:- August 30, 2017 - WD Expands its Graveyard with Tegile Acquisition - a blog written by AFA competitor Nimbus - says this...

"It's widely known that Tegile was running out of cash. No acquirers showed up as the product is ill-suited for the cloud. Existing VC's saw Tintri's horrific IPO and concluded that unprofitable storage companies are DOA in the public markets. The Tegile deal was a loss for the VC's that pumped $175 million into it (WD being among them). Rather than take the full loss, WD paid well under $100 million to acquire it."

AccelStor's new 4U 100GbE HA NVMe AFA

Editor:- August 2, 2017 - AccelStor today announced a new high availability all-NVMe flash storage array, the NeoSapphire H810. The 4U rackmount SSD which uses Intel's Xeon Purley platform and has 100GbE connectivity delivers upto 6x the performance of the company's previous NeoSapphire P310 all-NVMe flash array will be on display next week at the Flash Memory Summit.

WekaIO compares cloud storage pools to IBM FlashSystem

Editor:- July 12, 2017 -WekaIO - a cloud storage software company today emerged from stealth and announced details of its cloud-native scalable file system which the company says can deliver performance comparable to rackmount SSDs / AFAs.

Editor's comments:- The notable thing for me in this announcement was that WekaIO uses a performance benchmark compared against an IBM FlashSystem 900 (the decendant of the RamSan world's fastest storage systems from TMS.)

WekaIO says "Utilizing only 120 cloud compute instances with locally attached storage, WekaIO completed 1,000 simultaneous software builds compared to 240 on IBM's high-end FlashSystem 900. The WekaIO software utilized only 5% of the AWS compute instance resources, leaving 95% available to run customer applications."

That's an ambitious positioning statement and offers users a glimpse into the kind of performance they can get by using flash assisted cloud services. Like other modern SSD fabric software software - "WekaIO eliminates bottlenecks and storage silos by aggregating local SSDs inside the servers into one logical pool, which is then presented as a single namespace to the host applications."

hard delays from invisibly fixed soft SSD errors can break apps
that's why you need better storage analytics - says Enmotus

Editor:- June 15, 2017 - Using SSDs as its prime example - but with a warning shot towards the future adoption of NVDIMMs - a new blog - storage analytics impact performance and scaling - by Jim O'Reilly - on the Enmotus blog site - describes how soft errors can contribute to application failure due to unexpected sluggish response times even when the data is automatically repaired by SSD controllers and when the self-aware status of the SSDs is that they are all working exactly as designed.

That's the needs analysis argument for storage analytics such as the software from Enmotus which supports the company's FuzeDrive Virtual SSD.

Jim says - "Storage analytics gather data on the fly from a wide list of "virtual sensors" and is able to not only build a picture of physical storage devices and connections, but also of the compute instance performances and VLANs in the cluster. This data is continually crunched looking for aberrant behavior." the article

Editor's comments:- in my 2012 article - will SSDs end bottlenecks? - I said "Bottlenecks in the pure SSD datacenter will be much more serious than in the HDD world - because responding slowly will be equivalent to transaction failure."

And in a 2011 article - the new SSD uncertainty principle - I shared the (new to me) wisdom collected by long term reliability studies of enterprise flash done by STEC - that many flavors of flash controller management contained within them the seeds of performance crashes which would only become apparent after years of use as the data integrity algorithms escalated to progressively more retries and stronger ECC to deliver reliable data from wearing out (but still usable) flash.

So I agree with Jim O'Reilly. You do need more sophisticated datasystems analytics then whether or not an SSD has failed.

The variable quality of latency can be a source of incredibly long delays in server DRAM too.

Micron dares skin in the SSD box game

Editor:- May 5, 2017 - Micron this week announced its long overdue plans for entering the rackmount SSD market.

Micron's ambitions revolve around SolidScale - a 2U box stuffed with NVMe SSDs and interconnected in a fabric using software from Excelero.

Micron is seeking early validation customers and technology partners now and says its platform is expected to begin volume production in early 2018.

Editor's comments:- see my article and analysis in SSD news - Micron dares skin in the SSD box game

How do banks use big memory systems to detect fraud?

Editor:- January 9, 2017 - In the early 2000s I started hearing stories from vendors of ultrafast SSDs about how their fast memory systems were helping banks to not only ease the choke points in their transactions but also provide insights into fraud prevention.

A new white paper GridGain Systems provides a good introduction and synthesis of the various roles of in-memory computing in accelerating financial fraud detection and prevention (pdf) which includes many named bank examples.

storage security articles and news
This paper describes how in memory computing provides the low latency data sharing backbone which is needed to enable pattern detection for fradulent activity to be assessed in real-time while at the same time enabling genuine transactions to proceed quicky.

Among other things, the paper says...

"The move from disk to memory is a key factor in improving performance. However, simply moving to memory is not sufficient to guarantee the extremely high memory processing speeds needed at the enterprise level... Clients who have implemented the GridGain In-Memory Data Fabric to detect and prevent fraud in their transactions have found that they can process those transactions about 1,000 times faster." the article (pdf)

U.S. Department of Veteran's Affairs uses RAID Inc. in 5PB SDS

Editor:- December 7, 2016 - A customer news story from RAID Inc. - Department of Veterans Affairs Selects RAID Inc. for Multi-Petabyte Microsoft Storage Spaces Deployment - includes the useful ratio metric that "400TB of flash-accelerated hot tier storage" were used to support 5PB of cold tier data in an InfiniBand attached fault tolerant array which supports over 460,000 devices in more than 280 sites.

See also:- "ratio" - mentions in

Pure says it's ready to ship petabyte SSDs

Editor:- October 12, 2016 - Pure Storage today announced availability of its of petabyte-scale rackmount SSD - the FlashArray//m - which in 7U includes 512TB of raw flash delivering 1.5PB of effective capacity (based on its customer use metrics).

Re resilience Pure says this product family has 99.9999% availability across the installed base, which equates to only 31.5 seconds of downtime on average per year.

Editor's comments:- In my 2013 article - impacts of the enterprise SSD software event horizon - I discussed the improving efficiencies we could still expect to see in pure SSD arrays as more layers of ancient HDD architecture were removed from archeologically stratified software stacks.

Pure disclosed in a 2015 white paper - Building HA enterprise flash storage from commodity components (pdf) - that in real-world applications its customer base averaged 5.4x more effective storage than the physical storage in the system excluding gains from thin provisioning. And that provides some context for their effective to raw flash capacity ratio of 3 in the press release - which seems reasonable after you take into account that some raw capacity is "lost" due to reliability strategies.

You can also see the signficance of 30 seconds in the above pdf too.

You can get a comparitive idea of the elasticity of SSD vendor promises about effective capacity by clicking on the link which mines archived news.

See also:- petabyte SSDs

Kaminario offers free iPads to boost K2 tryouts

Editor:- October 4, 2016 - I saw a promotional email offer from Kaminario today which I think may backfire as it seems to be in direct conflict with the ethical principles of buyers in many large organizations.

The promotional email says "Test and evaluate a Kaminario K2 all flash array with up to 50TB capacity for as little as $1.25 per GB and iPAD management console for 45 days. Try it today and the iPad is yours to keep."

Editor's comments:- I think the offer will turn off buyers in big companies - because the inducement of a free iPad to take part in the evaluation sounds like a personal gift rather than having any benefit for the evaluating organization. Seems to me that the marketers in Kaminario have been reading too many consumer marketing comics.

Violin issues going concern warning

Editor:- September 14, 2016 - Violin Memory today filed a FORM 10-Q (pdf) with the SEC which provides a snapshot of the company's poistion for the quarter ended July 31, 2016. Among other things:-
  • Violin's revenue had fallen by 72% compared to the year ago. Product revenue was $2 million and services revenue was $5.4 million (unaudited).
  • Violin has issued a going concern warning which concludes - "Failure to generate sufficient revenue, increase gross margins, control or reduce operating costs and to raise sufficient funds may result in an inability of the Company to continue as a going concern."
See also:- 90% of the enterprise SSD companies which you know have no good reasons to survive

Nimbus re-emerges from stealth with 1PB / U raw HA SSD

Editor:- August 9, 2016 - Nimbus Data Systems has emerged from its self imposed exit into marcomms stealth mode with the announcement of a new range of Ethernet/FC/Infiniband attached rackmount SSDs based on its new ExaFlash OS with GA in Q4 2016.

Entry level products start in a 2U box with 50TB raw capacity for under $50K and for larger configurations Nimbus says its ExaFlash offers an effective price point as low as $0.19 per effective gigabyte (including all software and hardware).

Higher density boxes in this product line - D-series models - will have 4.5 PB raw capacity in 4U (12 PB effective).

Re the architecture - I haven't seen details - Nimbus says there is no data network between the storage arrays themselves, guaranteeing that performance truly scales in lock-step with capacity and with consistent latency.

4 petabytes raw 12 effective in 4U

video above shows the 4PB raw ExaFlash at FMS

Editor's comments:- if there are to be sustainable roles in the future consolidated enterprise SSD systems market for AFA vendors which previously sold arrays of SAS/SATA SSDs - and who don't own their own semiconductor fabs - the only viable ways to establish such platform brand identities are with SSD software and architecture.

There's a huge gap between the technological aspiration which Nimbus talks about and the weakness of its past marketing and the kind of funding which we've seen competitors in this market burn through in the past with mixed results.

In the next few quarters I hope we'll hear more from Nimbus about its business development plans and customer adoption.

See also:- roadmap to the Petabyte SSD, the unreal positioning of many flash array "startups"

Pure Storage says its AFA revenue in Q1 2016 was more than the leading HDD array brand

Editor:- June 21, 2016 - Scott Dietzen, CEO - Pure Storage says in his recent blog - Reinforcing a generational shift in data center storage - "...not only were we the fastest-growing storage vendor named in IDC's report, but we cracked of the top 10 storage vendors (for revenue) globally not just for all-flash storage, but for ALL external enterprise storage."

Editor's comments:- this result in the real world of market revenue tracking is broadly in line with a long range prediction I made in 2009 - in which I said "50% of the (enterprise) hard disk market will no longer exist in 5 years, and none of it will exist in 10 years (except in museums)."

See also:- terabyte talliers and storage market research

memory intensive data architecture emerges in a new family of latency roled boxes - unstealthed by Symbolic IO

Editor:- May 25, 2016 - 1 petabyte usable storage in 2U along with a flash backed RAM rich server family which uses patented CPU level aware cache-centric data reduction to deliver high compute performance are among the new offerings unveiled today by Symbolic IO which has emerged from stealth mode.

Founder & CEO, Symbolic IO - Brian Ignomirello, said - "This industry hasn't really innovated in more than 20 years, even the latest offerings based on flash have limitations that cannot be overcome. Our goal at Symbolic IO was to completely redefine and rethink the way computing architectures work. We've completely changed how binary is handled and reinvented the way it's processed, which goes way beyond the industry's current excitement for hyper-conversion."

the fastest SSDs - click to read article
.. the fastest SSDs
Giving a clue to performance Ignomirello said - "One of our early tests, allows us to run a full cable class content delivery network over 80+ nodes, while streaming 80+ full-featured movies simultaneously on one channel and requires less than 8% of the CPU capacity and we had plenty of headroom to run more. IRIS (Intensified RAM Intelligent Server) is 10,000 times faster than today's flash."

Editor's comments:- I hadn't spoken with Symbolic IO (when I wrote this) but my first impression was that the company is in line with at least 3 strategic trends that you've been reading about on in recent years:- Their company profile summarizes their capability like this...

"Symbolic IO is the first computational defined storage solution solely focused on advanced computational algorithmic compute engine, which materializes and dematerializes data effectively becoming the fastest, most dense, portable and secure, media and hardware agnostic storage solution."

For more about the company's background see this article - Symbolic IO Rewrites Rules For Storage on Information Week.

From the marketing point of view it's interesting to see that in its launch press release Symbolic IO positions itself in the DIMM Wars context in this way "IRIS... is 10 times faster than 3D XPoint."

Symbolic IO says the new systems will be start to become generally available in late Q4 2016.

From an enterprise segmentation viewpoint the IRIS systems will be proprietary. There is space for such approaches in the future market consolidation roadmap because not everyone needs the fastest performance. But many webscale SSD companies are already using data reduction techniques for their own utilizations and acceleration purposes.

The new thing - if there is a new thing - is that Symbolic IO will make available boxes which incorporate modern data architectures from a single source.

Although like all new systems companies they'll have to wade their way through the apps accreditation and compatibility lists before their revenues create any ripples - an adoption dampening factor I wrote about in my 2013 article Scary Skyera.

See also:- towards SSD everywhere software

Avere ranked #1 in Google's cloud partner search list

Editor:- March 16 , 2016 - How well does Avere Systems (and its virtual edge filer) work as a gateway to Google's cloud services? Apparently very well - as Avere today announced it had been named "Google Cloud Platform Technology Partner of the Year" for 2015.

Pivot3 acquires NexGen

Editor:- January 27, 2016 - NexGen Storage announced today it has agreed to be acquired by Pivot3.

it's not really RAID
Editor's comments:- The last time I wrote about Pivot3 was 7 years ago. I had a good feeling about their big controller architecture thinking which was being applied to hard drive arrays but I viewed it more as a valuable efficiency boost to buy breathing space for the last gasp years of enterprise HDD rather than the new direction I was focused on - which was heading towards the solid state storage datacenter. And so - from my point of view - I had nothing more to say.

On the other hand we're heard about NexGen many times in recent years.

Combining the software and architecture from these 2 companies could produce a platform with characteristics comparable to the best upwardly stretched efforts of much better known competitors if Pivot3 and NexGen can draw the integration boundaries in the right places (and get it done quickly enough).

7 out of top 10 SSD companies are systems companies

editor:- January 7, 2016 - Rackmount SSD companies dominated the top 10 zone of the new 34th quarterly edition of the Top SSD Companies published today by - with 7 out of the top 10 being in the rackmount SSD business.

EMC was the 2nd fastest climber and this period marked Kaminario's best rank in the more than 5 years it has appeared in this series.

Looking back at the dominance of rackmount systems makers in past editions in this series - the pattern first became clear in Q2 2013 when it was 8 of the top 10 companies.

The compelling technology necessities driving this trend were noted in my 2013 SSD year transitions article. The top level idea is the same today as it was then.

"The rack has become the most important form factor at which level enterprise SSD vendors must focus their strategic product ideas. What we're seeing in the market today at the rack level - are efficiencies and competitive advantages which accrue from combining and integrating design factors at many levels within large SSD arrays (at the memory utilization level, the SSD controller level, the drive interface level, the flash array organization level and multiple levels up and down the system software and apps software stacks). Mastering the design possibilities of SSD at the rack level enables new levels of competitive advantages for vendors."

It's the precise details which have changed since 2013. Hence all those recent AFA and big data SSD acquisitions.

And the market destination has changed too (90% of enterprise vendors will disappear) which means it's less safe for SSD outsiders to sit back and wait to see what happens.

Permabit shrinks data in new flash boxes from BiTMICRO

Editor:- October 20, 2015 - Permabit today announced that its inline dedupe and compression software is used in BiTMICRO's new rackmount SSD white boxes - which include a 1U iSCSI appliance (20x 2.5" TB SSD shown at FMS) and a 3U fast SSD server (8x PCIe SSDs) which is due to be shipped this quarter.

Dell buys EMC - the SSD view

good for Dell-EMC - long term

good for AFA and hybrid competitors - short term

disruption and changes for SSD suppliers - short term

Editor:- October 13, 2015 - Dell yesterday announced it has agreed to acquire EMC for approximately $67 billion. The acquisition also included EMC's stake in the storage software company VMware - which will remain in public ownership.

Editor's comments:- In the short term this fixes a problem for Dell (its weakness in enterprise storage) and offers a credible way for EMC to adapt to a long term future in which its storage products become more commoditized and accessible to smaller businesses (something which Dell has historically been good at with its server business.)

The competitive landscape in enterprise storage is complex but a long term SSD centric summary goes something like this.

Servers have become a commodity. And there is little or no scope for genuine competitive value differentation options to be offered within the server market. (Being able to offer the same memories or SSDs in servers as everyone else - does not decommodify server product lines BTW.)

In contrast - enterprise storage - which in the HDD and post tape library and post optical storage era (2001 to 2008) had been coasting towards oblivious commoditization - has been temporarily reprieved from that fate (2009 to 2018) by the disruptive impact of SSD memory technologies which enabled the construction of 5 to 6 role differentiated types of new storage boxes which could deliver value to users in ways which were technically unimaginable and unfeasible with classically tiered memory and storage.

Having misfired its original entry into the enterprise flash market in 2008 - EMC has in recent years managed to accumulate credible industry leading proprietary IP and product lines in 2 of the 5 above storage box segments (which will satisfy projected enterprise storage needs in the post HDD era) meanwhile treading water in the other 3 main box segments (indicating its aspiration to occupy part of those other crowded beachheads if possible).

Assuming all goes well with the acquisition process - the Dell-EMC product line will enable EMC storage to be more competitive in the short term with existing products and to maybe credibly add another notch to the list of product types for which it has aspirations for clear leadership.

But the acute efficiency pressures on the server and storage markets which are emerging from SSD centric software and data architectures will mean that traditional product lines from both vendors will shrink away.

And those lost revenues will stay gone forever. The old ways and the old purchase orders won't be coming back. That's why it's important for both companies to draw in new smaller customers and to nurture them (if possible) into the new sustainable sold state storage and server product lines.

What about impacts for the SSD market?

Anyone who competes with Dell or EMC will - for the next year - have an easier ride - due to the inward focus which sucks away the attention of the talent following such acquisitions.

The SSD market as a whole will continue to supply memory and SSDs to the new company - and probably can look forward to getting more business in 18 months time.

But it won't simply be more of the same. Some SSD vendors may see big changes when Dell EOLs systems and modules which are cannibalistic and compete within the combined product lines.

NexentaStor available with InfiniFlash

Editor:- September 3, 2015 - Nexenta recently announced support for SanDisk's InfiniFlash AFA box.

List price for the integrated solution including, perpetual software licenses, controllers, InfiniFlash, 3 year support and installation can be as low as $1.500/Raw TB.

See also:- towards enterprise hardware consolidation, SSD prices

"more lanes of SAS than anyone else" - new 4U SavageStor

Editor:- July 28, 2015 - As the rackmount SSD market heads towards future consolidation - new business opportunities are being created for those brave hardware companies which accept the challenge of providing simple hardware platforms (which provide high density or efficiency or performance or other combinations of valued technical features optimized for known use cases) while also being willing to sell them unbundled from expensive frivolous software.

In that category - Savage IO today launched its SavageStor - a 4U server storage box - which - using a COTS array of hot swappable SAS SSDs - can provide upto 288TB flash capacity with 25GB/s peak internal bandwidth with useful RAS features for embedded systems integrators who need high flash density in an untied / open platform.

Savage IO says it "products are intentionally sold software-free, to further eliminate performance drains and costs caused by poor integration, vendor lock-in, rigidly defined management, and unjustifiable licensing schemes."

Editor's comments:- I spoke to the company recently and most of you will instantly know if it's the right type of box for you or not.

fast rackmount SSDs from EMC, IBM, Pure... which is cheapest? (maybe)

Editor:- July 9, 2015 - In a recent blog about the competitiveness of fast rackmount SSDs - Why I Hate Cost/GB Discussions - Michael Martin, FlashSystems Specialist - IBM - leads you through a series of arguments to convince you that - when measured on a 5 year ownership basis (against a very specific set of parameters) his company's fast rackmount SSDs are cheaper to own than competitive models from EMC and Pure.

Among other things Michael says - "Why is everyone so focused on the initial cost when it comprises such a small percentage of the "real" or total cost of the storage array?"

One interesting boundary condition question which Michael Martin looks at is - what is if EMC gave you a FREE VMAX? How would that compare to the IBM V9000 FlashSystem's TCO?

I like that style of analysis - because it's one I've used a lot myself in the past 12 years or so - in various market forecasts where I looked at the cost of one type of product being zero but another type of product (SSD) still being cheaper or better.

Editor's comments:- recently we've seen survey data from Tegile suggesting that for a significant proportion of enterprise users the ROI on their enterprise flash investment can be as little as 1 or 2 years - which suggests that looking at the 5 year cost, or the initial purchase cost are equally unreliable expectations.

For most users - the uncertainty of capturing reliable predictive cost benefit data to justify the acquisition of enterprise flash arrays was discussed in my article - Exiting the Astrological Age of Enterprise SSD Pricing.

The reasons for choosing one system over another include so many user preferences and associated customer service values that the 5 year predicted cost from a particular web site are not likely to be the decisive factor for most users - who will prefer to trust their own analysis.

As long as you don't take the rankings in Michael Martin's blog too seriously - as gospel - and don't come away with the idea that IBM's FlashSystem is always the best and cheapest fast rackmount SSD - it's a fun read. the article

Conspicuously absent however in this discussion - given the 5 year cost justification timeframe - is a new class of fast rackmount SSDs which will be emerging in the next year - based on arrays of 2.5" NVMe SSDs - which will have the same impact on this segment of the market (IBM, EMC, Violin etc) as did flash on RAM SSDs. (Implode the costs and explode the scalability and market roadmaps.)

See also:- SSD costs and justifications 2001 to 2015

SolidFire opens sales channel in Japan

Editor:- March 19, 2015 - SolidFire today announced it has expanded its sales reach into Japan with the opening of a new office in Tokyo and a distribution agreement with ITOCHU Techno-Solutions.
SSD ad - click for more info

storage search banner

Sir Squeaks-a-Bit - image for rackmount SSD page ... If he had his way... Sir Squeaks-a-Bit would stretch all rotating disk pretenders on the rack and remove their wobbly heads.
Why did Nimbus enter the SAS SSD controller market?
sauce for the SSD box gander - analysis and interview
SSD ad - click for more info

NVMe and the FlashSystem 900?
Editor:- December 7, 2016 - NVMe was one of the big SSD ideas of the year which was mentioned by several contributors.

Hold onto that thought.

"The only thing better than an improved protocol like NVMe, is no protocol" - says Woody Hutsell, Technologist, Evangelist - IBM in his new blog - Stop waiting on NVMe all flash arrays.

Among other things Woody says - "There is no storage protocol inside the IBM FlashSystem 900. Once the data hits the interface controller it ceases to be SCSI or PCI or NVMe. The only thing better than an improved protocol like NVMe, is no protocol. The FlashSystem 900, like many prior generations of FlashSystem solutions treats the flash inside the system like memory. The result is unmatched latency characteristics." the article

Latency was the central theme of Woody's SSD bookmarks for readers earlier this year too.

Woody has been extolling the virtues of low latency enterprise SSD storage to me and my readers for over 15 years.

I always relax when reading Woody's writings about solid state storage as I can be secure in the knowledge that everything he says is reliable.

Software is the data heat pump which can transform the entropy of flash memory arrays from mere storage systems into higher value RAM.
Where are we heading with memory systems and software?

SSD ad - click for more info

Many factors at play in enterprise SSD market behavior still don't appear as explicit assumptions in product marketing plans.
Decloaking hidden segments in the enterprise

With next generation software and architecture - 1 petabyte of flash rackmount storage will replace 10 to 50 petabytes of HDD storage in legacy enterprise infrastructure and also run faster.
utilization and the enterprise SSD software event horizon

In 1978 a 45MB enterprise SSD system from StorageTek cost $400,000 which was about half the price of the rotating IBM mainframe storage it could replace while at the same time running applications faster.

Some of the deepest thinking going on in the SSD market right now is focused on rackmount SSDs. (Or enterprise flash arrays - if you think that sounds better.)
new SSD thinking inside the box

SSD market perspective