rackmount SSD newsother
SSD news / DWPD /
SSD cloud /
|re IBM's FlashSystem 9100
Editor:- July 18, 2018 - A recent blog -
the FlashSystem 9100 NVMe with FCM - by Barry Whyte at IBM - provided for me - a
satisfying sequel and finale to the story of whatever happened to the longest
running enterprise SSD accelerator product line in the history of the market -
the SAM>RamSan>FlashSystem - which were all
fast big shared memory boxes.
(The new heir in the family saga -
the FlashSystem 9100 is a 2U box with NVMe SSDs inside which provides 403TB
usable uncompressed - and GbE, FC or SAS host connectivity.)
get a taster of the family story in these 2 marker articles - selected from
my numerous scribblings.
IBM's FlashSystem 9100?
the same kind of horse show (in
role) but with a different technology animal inside and the recent
changes in the design architecture today in 2018 are as significant as when TMS
redesigned the main memory array in the RamSan product line from RAM to flash in
their 2007 model - the
Barry Whyte's new blog says among things:-
storage development team in Hursley started work on the design of a new
generation box back over 3 years ago when I was still based in the UK. The idea
was to build a low rack density, and high performance control enclosure that
could take NVMe Flash drives, both in terms of NAND Flash based, and look to the
future of SCM technologies, such as 3D Xpoint, Z-SSD and whatever else will
come along." ...read
Editor's comments:- throughout the 30 or so years
history of the RamSan and the multi OS supported SAM - Shared Access Memory
system which came before and the new FlashSystem (which cane after (and which
may have changed its name again depending on when you read this) is the the
idea of a product line which evolves to accomodate new memory technologies but
retains the legacy purpose of putting data in a box where it can be accessed by
many different servers at the lowest practical latency cost.
Dell EMC adopts M.2 SSD array concept
17, 2018 - The idea of using M.2
SSDs as the raw flash elements mounted on
enterprise PCIe SSD
carriers and trays has gaining ground since it was proposed as an evolutionary
step by Liqid in
The M.2 array concept has the performance benefit of proportionality
(from NVMe PCIe scalability) coupled with the strategic business merit that M.2
is a competitively priced,
high volume form
factor which ensures that such modules will be at the forefront of new
technology adoption while also including within its ranks good value for money.
recent story -
EMC Takes a Stab at 1PB/1U With High Density M.2 Sleds (on
StorageReview.com) - shows a picture of a Dell EMC module with upto 10 M.2
SSDs in a single sled. ...read
Nimbus samples 100TB SAS SSDs
Editor:- March 19, 2018
- Nimbus Data Systems
has made another significant advance in the development of multipetabyte
energy-efficient solid state storage racks with the
today that it's sampling 100TB 3.5
SAS SSDs with
DC100 has balanced performance 100K
IOPS R/W and
up to 500 MBps throughput and consumes 0.1 watts/TB - which Nimbus says is 85%
lower than competing drives used in similar array applications - such as the
Micron's 7.68TB 5100
Nimbus says the use cases are:-
is expected to be summer 2018.
- Data centers and cloud infrastructure (scale, efficiency)
- Scale-out systems (object and file storage)
- Edge computing (IoT, embedded applications)
ExaDrive technology and
I asked Thomas Isakovich,
CEO and founder of Nimbus some questions about the new ExaDrive technology.
Editor - The
announced by your flash partners last year used planar 2D flash. Does
the 100TB family use 3D flash? Knowing the answer one way or another will
enable some people to make their own judgements about incremental upsides in the
next year or so's roadmap. And also form a view about specification stability
Tom Isakovich - Yes 3D flash for the ExaDrive DC.
- The issue of cost per drive is an interesting one too. But the companies you
were working with last year have experience in processes which can produce a
high confidence reliable SSD for high value, mission critical markets (like
military) in which the reliability of every single SSD is critical. So my guess
would be that for integrators who have a serious interest in the ExaDrive DC100
they will be looking at the cost of drive failures on a system population
basis and the value of less drives and less heat per TB is more important
than the headline cost of a single failed drive.
Tom Isakovich - I have
an interesting subject for you to consider on the topic of "reliability".
Namely, is an SSD any less reliable than an all-flash array? I contend that it
is not. In fact, an SSD is more reliable.
- Our ExaDrive DC has flash redundancy internally, with the ability to
lose about 8% of flash dies without any downtime, data loss or capacity
reduction. This is analogous to
RAID in a traditional
all-flash array that protects against media failure. So on the notion of media
redundancy, they are equally redundant.
I'm thinking more on this. But empirically, an SSD is more
reliable than a System. The user can achieve desired redundancy in their overall
architecture, taking this into consideration.
- The ExaDrive DC has a 2.5 million hour MTBF with no moving parts.
That is about 6 times longer than the typical all-flash array (which includes)
many active and moving parts. All-flash arrays have integrated power supplies,
active controllers, fans, and other components prone to failure.
Gen-Z 1.0 now available to view
Editor:- February 13,
2018 - The Gen-Z Consortium
that the Gen-Z Core Specification 1.0 is publicly available on its website.
memory media independence and high bandwidth coupled with low latency enables
advanced workloads and technologies for end-to-end secure connectivity from node
level to rack scale.
Editor's comments:- Gen-Z follows in the
multidecade footsteps of
Infiniband and then
recently PCIe memory fabrics - but Gen-Z was born with with confident
expectations that because of SCM DIMM wars andthe memoryfication of the
enterprise there is a real business potential that
could become the mainstream instead of sitting in the side lines of HPC.
rev 1.0 specification is a 980 plus page pdf - which I haven't read through yet
- but which shows definite promise of a being a thought provoking page turner.
what I've seen so far the thinking looks like a modern, secure and media
agnostic way to request or respond to byte and block addressable (or
addressed by default as the next component) data packets between a huge
scalable population of components which can be memory devices, processors or
Kaminario no longer wants to supply hardware
January 17, 2018 - 2017 was a difficult year for AFA vendors whose primary IP
was software - as they couldn't be sure how much they would have to pay for
their memory based hardware and couldn't be sure either if and when they
would get it. However, even without the
shortages it was inevitable that vendors would one day have to align
themselves with new trends
more strongly delineated standard product roles.
That day has
dawned for Kaminario
- which had already churned its hardware deliverables suppliers several
times since entering the
market in June
it is exiting the hardware market as a supplier and is switching to a software
business model. The company's K2 arrays will be supplied in future by Tech
Data. Kaminario will continue to provide centralized support management for all
datacenter implementations based on Kaminario software.
commented on linkedin to Eyal David, CTO -
Kaminario - who had posted a link to The Register's - coverage of this news
the Software Defined initiative: Kaminario exits the hardware business.
said - "Yup it's the same reason that wordprocessors became floppies on
pcs and CAE became tapes for workstations instead of both being boxes. If you
can't design hardware and chips then don't expect your customers to keep buying
someone else's better box just to get to use your software." ...read
The Register article
Goes Software-Defined by Chris M
Evans on his site - Architecting
Chris says among other things... "As NVMe becomes
widely available as a storage protocol, NVMe over Fabrics allows high-speed
communication between servers, controllers and storage. The logical conclusion
is that we will see hardware distil down to racks of enclosures and servers with
high-speed networking in between. The Software Defined Data Centre will allow
these hardware components to be aggregated into storage arrays, disaggregated
solutions or HCI as required." ...read Chris's
AFA market revenue grew to $1.6B in 3Q17 - says Dell'Oro
December 6, 2017 - "AFA market revenue grew 33% yoy in 3Q17, reaching
$1.6 Billion" according to a new report -
Systems Quarterly - published by Dell'Oro
"All Flash Array is a very important technology
segment in external storage. In fact, as a percentage of external storage
revenue, it has been growing dramaticallyfrom 22% in 3Q16 to 28% in 3Q17.
So every vendor is determined to expand their position in all-flash storage
systems" said Jimmy
Yu, VP at Dell'Oro Group.
Editor's comments:- Dell'Oro's press
release lists the 5 biggest vendors and the company can provide more analytical
data in their purchaseable reports.
more market research stories
AccelStor doesn't use capacitor holdup to boost new HA arrays
November 6, 2017 - The complex interdependencies between
hold up time on
RAM flash caches
and reliability in
SSDs has been
many times in StorageSearch.com.
today about its new 2U flash array for the
market - the
(pdf) (array of 24 SATA SSDs with 8x 10GbE SFP+ or 4x 16G FC connectivity) -
"Some vendors adopt NVRAM as a write cache and use
supercapacitors to provide energy to write the RAM content into flash in the
event of a power failure. However, supercapacitors can still cause a single
point of failure. AccelStor aims to provide comprehensive data protection. With
the special write-through design, its NeoSapphire AFAs acknowledge the
completion of incoming I/O only when 100% of the data has been written on the
AccelStor became known for their high performance arrays for
optimized market. The new H510 also includes data
including cryptographic erase.
Many flash arrays includes some kind
of performance hit during software upgrades and maintenance. Accelstor says
its shared nothing architecture requires no maintenance window. "You can
simply perform the maintenance on a single node while receiving the full
performance and capabilities of the secondary node."
comments:- I wrote about Accelstor's thinking about the use of NVMs and arrays
failover gotchas in
article last year.
DCIG compares flash arrays from Dell EMC and Pure Storage
October 18, 2017 - Power consumption and data center footprint are among the key
differences noted in a new report -
Dell EMC XtremIO and Pure Storage Flash Arrays Differ - by DCIG.
In the introduction DCIG
says - "All-flash data centers are coming and with every all-flash array
providing higher levels of performance than previous generations of storage
arrays, enterprises need to examine key underlying features that go deeper than
simply fast they perform. Their underlying architecture, the storage protocols
they support, and the software they use to deliver these features are all
features that impact how effective and efficient the array will be in your
storage market research
Infinidat secures $95 million C round
Editor:- October 3, 2017 - Infinidat today
it has closed a $95 million Series C financing round. Equity raised by the
company to date totals $325 million.
Infinidat says that several
hundred enterprise customers have adopted its (hybrid storage)
with more than 2 exabytes of storage deployed globally.
comments:- Although we've become accustomed to storage box makers reporting
funding rounds like this
and so in that respect this wouldn't attract much comment from me - the
interesting thing from an
trends viewpoint is this funding story shows that the
hybrid storage appliance
model for the enterprise - in which SSDs and HDDs both played a part - is
still being regarded by investors as a valid business model. Although the
of segments in the market which have product gaps still remains - as ever
shortages of 2017 demonstrated that solid state storage makers couldn't
make enough SSDs with their in place production plants to sustain the needs of
the SSD market even at inflated
CAEN launches high availability 2U FC AFA
September 15, 2017 - CAEN
Engineering today introduced the
CEI-826-FXD - a 2U 10GbE / 16G FC AFA (with 26 native 12Gb SAS bays) for
applications such as big data, HPC, Hadoop etc.
dual-active controller architecture enables both controllers to concurrently
provide storage services in real time. Active-Active architecture doubles the
available host bandwidth and cache hit ratio, ensuring the greatest utilization
of system resources and maximum throughput. If one controller fails, the other
controller transparently takes over all storage services. In addition to storage
services, management services can transparently pass to the secondary
The CAEN array offers high availability with no single
point of failure. All critical components are hot pluggable andengineered with
full redundancy. Thanks to this robust design, this system can withstand
multiple component failures and achieves 99.999% availability. The CAEN
CEI-826-FXD solution supports RAID levels 0 ,1 ,0+1 ,3 ,5 ,6 ,10 ,30 ,50, 60,
and N-way mirror.
Western Digital buys Tegile
Editor:- August 29, 2017
- Western Digital
today that it has agreed to acquire Tegile. The price was
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.
of the business risks of Tegile's business model was that its ideal customers
were buying usable storage based on
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
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.
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
For WDC you could interpret this acquisition as a long
delayed response similar in thinking to
of Dot Hill Systems.
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.
much did WD pay for Tegile?
Later:- August 30, 2017 -
Expands its Graveyard with Tegile Acquisition - a blog written by AFA
competitor Nimbus - says
"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."
WekaIO compares cloud storage pools to IBM FlashSystem
July 12, 2017 -WekaIO - a
today emerged from stealth and
details of its cloud-native scalable file system which the company says can
deliver performance comparable to
rackmount SSDs /
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
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."
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
why you need better storage analytics - says Enmotus
15, 2017 - Using SSDs as its prime example - but with a warning shot towards
the future adoption of NVDIMMs - a new blog -
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
That's the needs analysis argument for storage analytics
such as the software from Enmotus
which supports the company's FuzeDrive
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."
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.
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
long delays in server DRAM too.
Micron dares skin in the SSD box game
5, 2017 - Micron
its long overdue plans for entering the
rackmount SSD market.
Micron's ambitions revolve around
a 2U box stuffed with NVMe SSDs and interconnected in a fabric using software
is seeking early validation customers and technology partners now and says its
platform is expected to begin volume production in early 2018.
comments:- see my article and analysis in
SSD news - Micron
dares skin in the SSD box game
U.S. Department of Veteran's Affairs uses RAID Inc. in 5PB SDS
Editor:- December 7, 2016 - A customer news story from RAID Inc. -
of Veterans Affairs Selects RAID Inc. for Multi-Petabyte Microsoft Storage
- includes the useful ratio metric that "400TB of flash-accelerated
hot tier storage" were used to support 5PB of cold tier data in an
fault tolerant array which supports over 460,000 devices in more than 280
- mentions in StorageSearch.com
Pure says it's ready to ship petabyte SSDs
October 12, 2016 - Pure Storage
availability of its of petabyte-scale rackmount SSD - the
- which in 7U includes 512TB of raw flash delivering 1.5PB of effective
capacity (based on its customer use metrics).
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.
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
Pure disclosed in a 2015 white paper -
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
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
capacity by clicking on the link which mines archived news.
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.
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."
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
Violin issues going concern warning
September 14, 2016 - Violin
Memory today filed a
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).
of the enterprise SSD companies which you know have no good reasons to survive
- 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."
Nimbus re-emerges from stealth with 1PB / U raw HA SSD
August 9, 2016 - Nimbus
Data Systems has emerged from its self imposed exit into
mode with the
of a new range of Ethernet/FC/Infiniband attached rackmount SSDs based
on its new
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
effective gigabyte (including all software and hardware).
density boxes in this product line - D-series models - will have 4.5 PB raw
capacity in 4U (12 PB effective).
- 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.
video above shows the 4PB raw ExaFlash
Editor's comments:- if there are to be sustainable
roles in the future
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.
roadmap to the
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 -
says in his recent blog -
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."
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)."
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
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."
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."
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 StorageSearch.com in recent years:-
company profile summarizes their capability like this...
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."
about the company's background see this article -
IO Rewrites Rules For Storage on Information
From the marketing point of view it's interesting to see that
in its launch press release Symbolic IO positions itself in the
context in this way "IRIS... is 10 times faster than 3D XPoint."
IO says the new systems will be start to become generally available in late Q4
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
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
also:- towards SSD
Avere ranked #1 in Google's cloud partner search list
March 16 , 2016 - How well does Avere Systems (and
its virtual edge filer) work as a
Google's cloud services?
Apparently very well - as Avere today
it had been named "Google Cloud Platform Technology Partner of the Year"
Pivot3 acquires NexGen
Editor:- January 27, 2016 -
today it has agreed to be acquired by Pivot3.
comments:- The last time I wrote about Pivot3 was 7 years ago. I had a
good feeling about their
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
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
January 7, 2016 - Rackmount SSD companies dominated the top 10 zone of the
34th quarterly edition
of the Top SSD
Companies published today by StorageSearch.com
- 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.
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
SSD year transitions article. The top level idea is the same today as it
"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."
the precise details which have changed since 2013. Hence all those recent AFA
and big data SSD acquisitions.
And the market
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
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
good for AFA and hybrid competitors - short term
and changes for SSD suppliers - short term
Editor:- October 13, 2015 - Dell yesterday
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
commoditized and accessible to smaller businesses (something which Dell has
historically been good at with its server business.)
landscape in enterprise storage is
but a long term SSD centric summary goes something like this.
have become a commodity. And there is little or no scope for genuine
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.
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
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.
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.
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.
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
September 3, 2015 - Nexenta
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
enterprise hardware consolidation,
"more lanes of SAS than anyone else" - new 4U
Editor:- July 28, 2015 - As the
rackmount SSD market
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
In that category - Savage IO today
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."
comments:- I spoke to the company recently and most of you will
if it's the right type of box for you or not.
fast rackmount SSDs from EMC, IBM, Pure... which is cheapest?
Editor:- July 9, 2015 - In a recent blog about the
competitiveness of fast rackmount SSDs -
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.
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?"
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.
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
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 -
the Astrological Age of Enterprise SSD Pricing.
The reasons for
choosing one system over another include so
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.
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. ...read
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.)
also:- SSD costs and
justifications 2001 to 2015
SolidFire opens sales channel in Japan
19, 2015 - SolidFire
it has expanded its sales reach into Japan with the opening of a new office
in Tokyo and a distribution agreement with
||If he had his way... Sir Squeaks-a-Bit
would stretch all rotating disk pretenders on the rack and remove their
|Do you remember the movie
Back to the Future?|
If you could go back in time (not to the 1950s but
to the 1970s, 1980s. 1990s and early 2000s) and take with you (not the idea
of skateboarding) but instead a truckload of modern memory chips and SSDs
(along with compatible adapters) what impact would that have?
analysis leads onto the consideration of "back from the future"
memory ideas and what their viability could be today.
|are we ready for
infinitely faster RAM?
|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|