 |
| leading the way to the
new storage frontier | |
... |
| ..... |
|
the SSD
bookmarks
the Top
SSD Companies
storage news - 2000
to 2017
can you
trust SSD market data?
Surviving SSD
sudden power loss |
|
| . |
|
 |
|
| . |
|
| Datalight's
SSD firmware to boldly go |
Editor:- September 17, 2015 - Datalight
today said its embedded filesystem (Reliance
Nitro) and FTL (FlashFX
Tera) have been selected by NASA for use
onboard future manned spacecraft in the
Orion
program.
 Editor's
comments:- NASA has had a lot of
mentions
by SSD and storage vendors in articles and news here on the mouse site. Some of
the application contexts have been ground based - but many have also been in
space.
FYI the spacecraft image shown here isn't from NASA - it's from
my
1990s
unfinished online SF novel. One of many which I may resume when the
SSD market slows down and becomes
more
predictable. (That's an excuse you can borrow and use yourself.) | | |
|
| . |
|
RRAM SSDs in 2016?
Crossbar gets $35 million series D funding
|
Editor:- September 14, 2015 - Crossbar today
announced
it has completed a $35 million Series D funding round bringing total
investment to $85 million to date.
Crossbar plans to use the funds to continue the
commercial ramp of its
RRAM NVM memory
technology which is based on a simple device structure using CMOS friendly
materials and standard manufacturing processes. It can be stacked in 3D, making
it possible to combine logic and memory onto a single chip at the latest
technology node.
Crossbar is currently working with beta customers to
bring products to market in 2016. | | |
|
| . |
|
 |
|
| . |
|
|
|
|
| . |
|
| the unsung hero of 3D
endurance |
Editor:- September 15, 2015 - One of the
interesting surprises about 3D
nand flash which emerged
early in
2014
was that the endurance
- reported by SSD designers - was better than you would have expected if you
had taken as your starting point - assumptions about 2D nand with similar
capacity and next generation (smaller) planar geometries.
Part of the
explanation - which I discussed last year - was the use of different materials.
But there's more to it than that as I realized today in a new (to
me) white paper
The
V-Nand paradigm shift (pdf) which came in a an email blast from Samsung.
In
Samsung's version of 3D - the charge is held in a silicon nitride charge trap -
which has better insulating properties than conventional 2D materials - and
lower leakage. (Essential if you think about it to even get a hope of doing
more levels.) That's the bit I already wrote about.
What I didn't
appreciate before was this.
The SiN charge trap requires a lower
voltage to program each cell than traditional 2D (floating gate) designs. (The
destructive effect of the energy in these write pulses is one of the
contributory factors to cell wear in 2D.)
The combination of better
insulation and less destructive write process would give you a better endurance
figure for the same flash process geometry in nanometers.
But a 3rd
element in Samsung's 32 layer 3D (which you could say is the sneaky pragmatic
business decision bit) is that these devices weren't 2Xnm geomtery at all.
Samsung decided to bring this technology to market with a mature
proven 3Xnm process. (3Xnm gives you better endurance anyway than 2Xnm in 2D
flash.)
So when Samsung talk about their 32 layer V-nand - with 35,000
P/E cycles "offering 10x increase in
endurance
over the 3,000 cycles provided by planar (2D) NAND" there are several
ingredients which combine to get this headline figure. And that's why this
paper is useful.
As to how much of that "10x" will continue
to be sustainable as more layers are added and as cell sizes get smaller - will
remain to be seen. Samsung's paper suggests that they are hopeful about aiming
at 100 layers in the next few years.
But it's clear that a lower
write pulse voltage is one of the unsung heroes in this better endurance
story. ...read
the white paper
PS - not everyone is convinced about the
market transforming imminence of Samsung's 3D nand.
In his August
2015 paper -
Flash
Technology:Annual Update (pdf) - Jim Handy founder Objective Analysis
said "Samsung is shipping at a loss and we have found no evidence of a
data sheet." Furthermore Jim is sceptical about the 3D nand industry's
assertions that " the big ramp will be in 2017." | | |
|
| . |
|
|
|
| . |
|
| spreading the word about
SSD |
Editor:- September 23, 2015 - Like ghostwriters
- their identities remain largely unknown - even when their works are widely
read.
I'm talking here about PR agencies which have done good work in
the storage industry.
I've recently updated my own list of
editor proven PR
agencies - to clear out the dead links.
For vendors who are new to
the SSD and storage market this list (which has been online since 2001) can be
a useful way to find a communications partner who will help to spread the word
about what you do throughout the fragmented media jungle. ...see the list | | |
|
| . |
|
|
|
| . |
|
| SAS SSD
market size - as interpreted by Micron |
Editor:- September 3, 2015 - If you're interested in the possible size and
direction of the SAS SSD
market - here's some data supplied to me today by Micron.
This
was in response to some questions I asked yesterday about a growth figure "59%"
which they had quoted in a
press
release (in August) about their first new SAS SSDs developed as part of
their
collaboration
agreement with Seagate. |
| SAS SSD market - a view
based on Micron's marketing assessments of various data sources revised in
August 2015 |
| Metric
|
2015
|
2019
|
CAGR
|
| Revenue ($M)
|
1,973
|
3,730
|
17%
|
| Gigabytes (M )
|
1,828
|
11,700
|
59%
|
| Units (M)
|
2.4
|
5.1
|
21%
| |
| Memory companies like Micron create, suck in and
analyze thousands of analyst hours of raw and structured statistics about
components and drives. And although - just as for anyone else - the fine
details of such projections and interpretations can turn out to be
wrong
- it's nevertheless very helpful to understand some of the publicly viewable
raw data which drives the thinking behind related product plans. | | |
|
| . |
|
SanDisk and enterprise
software?
after 4 years something is clear... |
Editor:- September 1, 2015 - How long does it
take for new enterprise SSD products (and vendors) to become part of the
mental compass in your mind map? ...The reference points by which you
think about new projects and compare your reading of new products?
In
an earlier blog on these pages -
the new enterprise
aristocrats of SSD - I said "that 4 years may be long enough to
earn a company its place for elevation into the elite ranks of the aristocracy -
for class-act companies which have been seen regularly in all the right places -
such as the Top SSD
Companies Lists."
That was about
enterprise SSD boxes
(which have been changing
a lot). Longer than 4 years and they've changed out of recognition. Sooner
than that and not enough people understand
where they
fit in.
But how about
SSD software?
History
shows us that few enterprise SSD software solutions have survived close
contact with the companies which
acquired them
for more than a handful of quarters.
But there have been exceptions.
In
a
recent
blog Rich
Petersen Director of Marketing, Software Solutions at
SanDisk
reflects on what's new in version 4 of
FlashSoft (announced
yesterday). Which among other things include:-
- write-back caching support
- improved stability mechanisms to reduce impacts from rogue VMs
Rich
starts his blog with "3 years ago at VMworld 2012, we introduced FlashSoft
software for VMware vSphere..."
And he ends it with "the best
feature in FlashSoft 4.0 is peace of mind."
Of course there's some
technology involved and you can read about the details in various links. But
sometimes when it comes to reading about products like this - the thing which
makes it worth reading about in more detail at all is that this product has
been evolving in the market and in these pages for 4 years.
Which
makes it one of the important angles of reference in the enterprise SSD
caching compass.
But there are others too.
Seagate recently (in
August 2015)
acquired for itself a new magnetic storage caching compass too in the shape
of Dot Hill. This
comes in a different kind of package and aims in a different direction in
which the hard drive elements are seen as part of the solution instead of the
source of the problem. | | |
|
. |
|
So we're looking at a list
of 10 well known suppliers of flash arrays.
Probably you've spent
days already (or weeks) going through the features, which types of SSDs are
inside the arrays etc, etc.
Now line them all up again in your mind.
Now imagine that every single one of these products is actually the
same hardware.
And when I say the same - I mean the same. |
| towards
consolidation in the enterprise SSD market | | |
| |
 |
| ... | |
SSD news - September
2015 |
DCIG publishes new edition of its AFA Buyers Guide
Editor:-
September 30, 2015 - DCIG
recently
announced
a new edition of its All-Flash Array Buyer's Guide (60 pages, free signup)
which - from a desk based research stance - describes, comments on, and
compares in depth the features of key products in this category from 18
selected vendors in the market (AMI, Dell, EMC, Fujitsu, HDS, HP, Huawei, IBM,
iXsystems, Kaminario, NetApp, Nimbus Data, Oracle, Pure Storage, SolidFire,
Tegile, Violin Memory and X-IO).
Editor's comments:- One of
the roles for this document which DCIG suggest is as a "short list"
for quickly and conveniently getting your hands on consistently-presented,
in-depth datasheets for a market snapshot of products from a range of credible
sources.
As to how the sample list of vendors is cast - DCIG clearly
stated they do not merely rely on vendors paying them for inclusion in the
list. Nevertheless one of the problems with the authority of any "buyers
guide" is the degree of inclusivity and (by implication) the
transparency of filtering criteria.
When you include hundreds of
products in such a guide from all known vendors - then the sampling process is
transparent (and those not in the guide - need to make better efforts to
communicate with their market) but when you have a guide which samples only a
small percentage of vendors then inevitably questions get asked about how those
in the sample were chosen.
My guess on the representational value of
the companies listed in the guide is that it's compatible with the kind of
shortlist you'd get by sampling from 3 broad criteria.
- companies added into the list based on public revenue criteria and
corporate brand strength (to ensure inclusion of older, long established
storage companies)
- companies added into the list based on search strength, or social media
derived ranking rather than revenue (to ensure sampling of some newer
companies)
- companies added into the list for arbitrary reasons (maybe they've got a
particularly interesting feature which the authors want to discuss as a
counterpoint to others, or maybe the authors have some special relationship
with the company which means they know more about it)
It took me about
30 seconds after seeing DCIG's vendor list that the above (or some reverse
analysis thought process like it) is probably as good an explanation as any
for DCIG to have constructed its list.
I'm not saying that's how
they did it. But if you had to construct a vendor list of reduced size (and
DCIG does have to because - due to their format - it would be cumbersome,
repetitious and wasteful of analyst time to scale the guide to hundreds of
vendors) this is as good a way as any other - for the purpose of discussing
representational features in the AFA market.
So in that respect
(unlike others) I don't have any quarrel with the sample they've chosen.
It
sure wouldn't be my list. But DCIG's authors are aiming to produce a different
kind of guide and they see their added value as coming from their proprietary
vendor scoring criteria. And that necessitates a different kind of list.
In
a free competitive market - reports compete for your attention - just as much
as products. And you don't have to like every feature to learn something
useful from them.
DCIG's scoring criteria is where I part company
with DCIG's thinking. And this is a gulf I can't bridge.
I just have
to look away from these pages to prevent my crystal ball cracking for reasons
I explained when discussing an earlier version of this guide back in
March 2014.
I think the scoring concept intrinsically suggests a much more
stable, restricted and naive model of the SSD enterprise than is currently the
case. In some respects the scoring concepts are like a bridge too far and
sometimes to the wrong places and sometimes entirely missing some critical
destinations.
Nevertheless I'm sure DCIG's new guide will serve
adequately for many people who see things the same way as the guide
creators do and who like their way of doing things. So I'm sure there
will be more editions of this guide in future.
It's not DCIG's fault
that the enterprise SSD market resembles at times the navigational uncertainty
of Lost in Space (tv series) when in the very first episode the rocket
gets hit by a meteor storm.
In the SSD market we've been through a
whole bunch of similar cosmic disturbances and our rocket was launched with no
clear destinations in mind at the outset. The best we can hope for is plausible
pragmatic reinterpretations at convenient refueking stops.
BTW - I'm
not suggesting that anyone else could do a better scoring job by using different
methodologies.
Instead what I'm saying is that such a style of
analysis is inappropriate because of current
defects in
enterprise SSD market models and the general understanding of them.
While
that situation persists - such simplistic "winner" style guides run
the risk of advocating the essential flavor of beef to vegetarians.
Nimble's sales growth via US distribution rates "Rising Star"
award
Editor:- September 28, 2015 - Nimble Storage was
recognized for its outstanding sales growth through US distribution channels -
it was
announced
today by the NPD Group whose sales
tracker research formed the basis of "Rising Star" awards presented
at a recent Global Technology Distribution
Council summit.
InnoDisk enables hot swap of tiny SATA DOMs
Editor:-
September 24, 2015 - InnoDisk
today
announced
an enhanced version of its previously available
Pin
7 power cable eliminator technology for use with small embedded SATA
SSDs - such as those used on server motherboards (and in particular the
company's
ServerDOM
SSDs which won a design award in
January 2015.
Innodisk's new SATA Pin 8 Vcc technology - which is available on motherboards
from top manufacturers - eliminates the need for a separate power cable and is
also compatible with hot swap.
Samsung opens new Silicon Valley semiconductor HQ
Editor:-
September 24, 2015 - Samsung
- which has had a campus in Silicon Valley since 1983 - has this week
formally opened its new Device Solutions America headquarters which will bring
together on a single campus over 700 employees who work in its
semiconductor business.
You can see more local details in the
San
Jose Mercury News.
Atmel - who?
Editor:- September 22, 2015 - It had
been a
long time since I last heard from Atmel (November 2005
according to my inbox - and that was about DVD chips) but 10 years is not so
long that I had entirely forgotten that they once had a distant connection to
the SSD market.
So when I saw an article alert to -
Dialog
and Atmel, 2 cultures to build 1 successful company? - by Eric Esteve, founder of
market research
company IPnest - that was my
way of learning the recent
announced
that Dialog Semiconductor
(which is not an SSD company) will acquire Atmel for $4.6 billion.
Eric
who worked for Atmel at the time writes - "In year 2000, Atmel had more
than $1,500 million of revenue from flash..
But he goes on to say
that in 2014 "their flash product line was almost dead" - however
they had "about $150 million of revenue related to other nvm".
Eric's
article reassured me that although my eye had been off the ball of Atmel - there
may have been good reasons (from an SSDcentric context). And it's a great way to
wrap up the story of a company from the history archive. ...read
Eric's article
new SSD market report from TMR
Editor:- September 18,
2015 - SSDs with capacities of 80GB and below accounted for approximately 36%
of the total $15 billion global SSD market revenue in 2014 - according to a new
market report
SSD
Market - Trends and Forecast 2015 - 2022 ($4,795 133 pages) published by
Transparency Market
Research which among other things profiles 10 leading SSD companies.
TMR
says that Samsung,
Intel and SanDisk accounted for
over 57% of market revenue.
See also:-
who does storage market
research?
Mangstor gets $10 million series B funding
Editor:-
September 17, 2015 - Mangstor
today announced
it has closed $10 million in Series B funding which will be used to fuel
growth in sales and engineering and business development.
"This
investment confirms our leadership in NVMe over fabrics technology which
delivers an order of magnitude higher performance at the lowest latency verses
legacy iSCSI and Fiber Channel" said Trevor Smith
CEO and co-founder of Mangstor .
Editor's
comments:- last week I had a 90 minutes one on one with Trevor which we
spent talking about gaps in the enterprise SSD market, Mangstor's technology
and the competitive positioning of its PCIe SSDs and systems. You can see some
of our discussion topics in their profile page.
revenue reported by Marvell was unreliable
Editor:-
September 11, 2015 - Marvell
today
announced
that it is downgrading its revenue expectations for the most recent quarter due
to business which the company had logged as booked - now having gone away - and
possibly having been booked in the wrong reporting period.
Reports
from financial observers quoted on
SeekingAlpha.com
speculate that "Marvell may have been boosting quarterly sales by
pulling them forward a quarter."
ZIPmagic has more full SSD compression profiles for Windows
Editor:-
September 8, 2015 - ZIPmagic Software
today launched a new version of their run time full SSD drive compression
utility - which now includes
Lempel-Ziv-Simon
Disk Compression (pdf)
4 different (preselectable) compression
modes are supported - which provide different compression ratios and have
different characteristics in terms of how soon the full compressed disk can
be used - ranging from immediately while the SSD is being compressed.
ZIPmagic
says "Lempel-Ziv-Simon Disk Compression supports all OSes from Windows XP
through to Windows Server 2016, whether 32 bit or 64 bit, from a single setup
package."
Editor's comments:- Australia based ZIPmagic -
which first appeared on this news page in
August 2014 - is
looking for SSD companies which may be interested in bundling their software.
They have an introductory rate of of $1 per device.
Because of its
background the company's web site is focused entirely on consumers but I
think that there may also be
industrial
applications for this kind of technology too. For oem inquiries contact Keith Tan
(Director of Sales & Marketing) via linkedin or Simon King (CTO) via email.
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 |
|
US Court says Netlist must pay posted bond
to Diablo
Editor:- September 2, 2015 - Netlist has been
ordered to pay Diablo
the full bond it posted in partial compensation for the profits which Diablo
lost while being restrained from manufacturing and shipping products during
part of the now completed lawsuit re
memory channel
storage IP according to an
announcement
today from Diablo.
Wikibon predicts when enterprise flash market will cross over
with HDD storage
Editor:- September 1, 2015 - A recently publihsed
blog - the
Status of Flash for Practitioners by David Floyer , CTO - Wikibon was recommended to me by a reader.
Unfortunately
a factual error stopped me dead at the preamble - "When enterprise
flash first came out in 2008"...
2008? - That's wrong. Vendors had already been promoting and selling
enterprise focused SSD systems and products for years before that. As those
vendors included my advertisers and their customers included my readers – I
was in a position to know. The
incremental creep
of enterprise flash deployment from its modest start in 2004 can be seen
in the history
of the SSD market and
archived SSD and
storage news.
OK - aside from that gripe - the Wikibon article
tackles the long running predictive game of pinning a year at which the
capacity orinented enterprise flash storage market will crossover the HDD part.
(The game gets easier as you get closer in time to the event being predicted. I
started publishing my own guesses about this in 2010.)
Wikibon
guesstimates today that - "spend on flash storage for latency is
projected to be about 29% in 2015, and break the 50% barrier in 2017. Also the
spend on flash for capacity is projected to be 1% in 2015, and break the 50%
barrier in 2021. HDDs are projected to be about 2% of total data center storage
revenue by the end of the forecast period in 2026."
See
also:- How
will the hard drive market fare... in a solid state storage world?,
can you
trust SSD market data? | |
| . |
|
What happened before? - See the
SSD news archive |
| |
| .. |
|
|
|
|
|
|
|
|
. |
|
|
|
. |
|
|
|
. |
|
| the fastest
SSDs? |
Raw speed used to be the most important success
factor for enterprise SSD vendors throughout most of the
market's
history - but today performance is just one of
many
segments.
Partly for that reason I hadn't updated the
fastest SSD companies
list for a while. But I have now. It includes some well known drives and
boxes but some newcomers to the market too. ...read the article | | |
|
. |
|
|
|
. |
|
|
|
. |
|
 |
|
. |
|
| "Are you still in the
camp that thinks proprietary hardware is the better path? Simply take a look at
the leading global hyperscalers, i.e. AWS, Azure, Google, Apple and how their
Data Centers look... How long before everyone else hops on the bandwagon?" |
| Marius Tudor,
VP Business Development Coho
Data - in his new blog
To
Cloud or Not to Cloud...Publicly | | |
|
. |
| . |
|
|
. |
|
hold up
capacitors in 2.5" MIL SSDs
do you really need them? |
Editor:- I've been looking at different aspects
of power hold up schemes in mission critical non volatile memory systems for
over 30 years.
But every time I revisit this vast topic and compare
fresh examples from the market - I learn something a little bit new.
My
new blog -
Zero
to three seconds - demonstrates the extreme range of hold up times
now in the market inside leading edge 2.5" military flash SSDs.
...read
the article | | |
|
.
. |
|
 |
|
.
. |
|
| |
