|
SSD news - June 15 -
30, 2013 SSD
market history
animal brands in the
SSD market
perspective
- comparing the SSD market to earlier tech disruptions |
| ....... |
does POS = Point Of SSD?
Editor:-
June 28, 2013 -
InnoDisk
recently published a case studies article which describes
how
its SSDs are being used in point of sale terminals.
The well
known advantages
of SSDs compared to HDDs
in these POS systems (InnoDisk specifically mentions lower vulnerability to
overheating so they don't need fans, which reduces noise and failure-prone
moving parts) aren't the only reason POS makes are turning to
industrial SSDs.
The higher operating temperature of some SSDs means that POS
terminals can be used in "weather exposed outdoor locations" (as in
the scenic pictures shown in the article).
From what I could see in the
examples mentioned - it seems that pretty soon if you if you squeeze past a
supermarket checkout or eat at an outdoor bar / restaurant - you won't be
too far away from a 2.5"
SSD. Which reminded me about my 2008 article -
You're Never More
than 20 Feet Away from a Rat (or a hard drive). Maybe it's time to rewrite
that one.
SanDisk invests in Panzura
Editor:- June 27, 2013 -
SanDisk today
announced
it has invested in Panzura
- which makes auto-tiering
(from NAS to the
cloud) rackmount SSD
ASAPs.
"Panzura is another excellent example of the important
role flash memory is playing in the transformation of the enterprise" said
Sumit Sadana,
executive VP and chief strategy officer of SanDisk.
See also:-
VCs in SSDs
LSI's enterprise PCIe flash - what I learned and had
confirmed
Editor:- June 26, 2013 - I had a useful conversation
last week with Rob
Callaghan who manages outbound marketing in LSI's Accelerated
Solutions Division.
When I say "useful" - I mean - useful
to me - because I haven't spent much time looking at the details of
LSI's
family of PCIe SSD products - due to my impression that it won't tell me
anything new about the long term architectural direction of this class of
product. Having said that LSI's PCIe flash products do provide a relatively
pain-free entry point for many users into the world of enterprise SSD storage -
and will generate lots of revenue for the company in the short to near term.
Not too bad for a company which I described as "approximately the
163rd company to enter the SSD market" - when LSI announced its entry into
SSDs in January 2010.
In that same 2010 news story - I used the headline - "LSI will
Compete with Fusion-io" - because it was a useful shortcut to my
guess-ahead at what LSI might end up doing. But with the benefit of hindsight
- that headline statement isn't strictly true. LSI doesn't compete at all with
Fusion-io on a slot by slot level. And at root is the growing fragmentation
within the PCIe SSD market itself.
I started to warn about this 2 years
ago in an article - don't
all PCIe SSDs look pretty much the same? And so the fragmentation within
PCIe flash products due to the
different roles these
products can play within the enterprise - was an obvious place to start my
conversation with Rob Callaghan as LSI already has 3 functionally distinct
types of products within its Nytro PCIe flash card product line.
Having
said that - there are another 3-4 classes of PCIe SSDs for which LSI doesn't
have any products at all.
It's a no-brainer to expect that LSI will
launch products to fill some of these other gaps too. But it's also clear to me
that due to the LSI's preferences and its business comfort zones with
controllers,
leveraging its RAID and
HDD legacy and
the need to provide a simple
SSD educational
interface to channel partners - the company isn't capable or doesn't have the
inclination to go after the same kind of high end
dark matter user apps
which other vendors like Fusion-io
and Virident etc
can reach - and even if LSI wanted to - they can't get there - because of
differences in philosophy in the
sizing of their
SSD controllers and assumptions about the
SSD software operating
environment which are conditioned by
fundamentally different
beliefs about the co-existence of SSD and HDD in the future datacenter.
Anyway
- back to my conversation with Rob Callaghan who had been talking to streams
of editors etc about LSI's upcoming product
announcement
(June 24) about more new Nytro stuff. I learned 3 things.
- the new thing - LSI's Nytro Elastic Cache. One part of flash can be
configured as read cache while another part can be configured for write cache
and for semi-permanent storage of often used data such as golden images of
desktops in VDIs. As a reliability
feature - the write cache and permanent data is mirrored on 2 separate regions
of flash on the same card.
I said - that could significantly reduce
the amount of flash capacity you need on the card - while offering some of the
reliability benefits of mirroring - because you don't need to mirror data which
you can easily read again.
Rob said - you're the first person I've
spoken to who got that. (The people I speak to in these interviews know how
to schmooze editors.)
I
said - there are so many ways of getting
SSD efficiency -
each time a company does something like this it means they can make money in the
market at a price point where a competitor - using more flash to solve the same
problem - is just bleeding their
VCs.
- the thing which LSI's PCIe SSDs don't do yet. I asked if LSI
supports low latency automatic mirroring - clustering across multiple PCIe SSD
cards - like some of the high-end products from other vendors do.
Rob
said no - they don't. It will come in future LSI products - and Rob hinted
that the way they do it may use a different physical mechanism than the method
I would have expected. (For me - the norm is PCIe chip level failover
supported by PLX).
- the thing I already thought I knew. The conversation confirmed to
me my earlier assumptions about LSI's positioning in the PCIe SSD market - and
limitations of their products. (For example LSI's Nytro WarpDrive doesn't have
scalability
symmetry.)
Rob said the typical end user of this product would
mostly have just a single LSI PCIe SSD card installed in a server. It would be
rare for them to have 2. (Editor - So if you want an environment in which
every slot can be a PCIe SSD - then you're looking at a different class of
product, and different software and a different bunch of vendors.) Editor's
comments:- As I said above - my gut feel is that LSI will do well in the
market with revenues from this generation of enterprise PCIe SSDs - in user
systems which can be satisfied by fast-enough SSD acceleration in HDD heavy
environments. But the company will have to change cars - rather than just switch
lanes in the future with both its controller architecture and software base -
if it wants to provide efficient solutions for SSD-centric datacenter
installations. My guess is - if that does happen - the only viable route would
be another significant
SSD company
acquisition - maybe in 2 years time.
For a company - like LSI -
which has already demonstrated that it can successfully leverage a
significant SSD IP acquisition - which it did with
SandForce - at
technical, marketing and business levels - that shouldn't present a fundamental
problem. But until it happens you're going to see a lot of confusingly different
but parallel courses being taken by vendors in this market - which aren't
inter-compatible.
And that will lead to the
paradoxical
oddity that maybe 2 of the top 3 companies in the
PCIe SSD market don't
really compete with each other at all.
Stec to be acquired by WD (that's all about the enterprise) - but
what will happen to Stec's military SSD business?
Editor:- June
24, 2013 -
WD today
announced
it has agreed to buy Stec
for approximately $340 million. Stec will be acquired by WD's subsidiary HGST - which is
already active in the enterprise SSD market.
Editor's comments:-
Stec is a company which knew how to design some types of enterprise SSDs - but
didn't have the know-how and channels to sell them and adapt them better to
market needs.
WD knows how to sell drives - but even with its HGST
subsidiary - only has a weak SSD product line. So in that sense there's a good
fit.
In the hard
drive world WD has often talked in the past about the importance it attaches
to business value and efficiency. And if you look at the price it paid for Stec
- the valuation it has placed on Stec - with its ongoing business, people and
brand was probably less than half of what Stec's controller IP (on its own)
would have been worth a year ago.
My guess is - it's only because WD / HGST already has enough people
with a good understanding of SSD IP that they can tolerate the high risk of
acquiring Stec - and filtering out the good bits of technology while having the
focus to discard dead-end products and pie in the sky thinking.
It's easy to see how enterprise users would benefit from this acquisition - but
less clear is the future of Stec's
military product
lines. The acquisition related
faqs document
(pdf) doesn't mention Stec's non enterprise SSD products at all. It merely
indicates that the status of all products will be reviewed in the period
after the acquisition closes.
My guess is that any company acquiring
Stec for its enterprise assets would probably divest the military SSD product
lines. (This isn't a new idea. I first touted it in a much earlier round of
speculation about Stec's future.) Another possibility is that the military
business might be assisted to do a management buy-out.)
the decorators move in to RunCore's new SSD HQ
Editor:-
June 24, 2013 - RunCore
today announced it
has completed the first phase of building its new headquarters and SSD
manufacturing complex in Hunan province, China which by the end of this year
will have the capacity to produce 1 million SSDs / month. |
 |
|
Micron reports SSD revenue
Editor:-
June 19, 2013 - Micron
today
announced
results for its 3rd quarter ended May 30. Among other things - its branded
SSD revenue grew 11% sequentially in Q3 to $178 million.
Software is why more enterprise users are talking to SanDisk
Editor:-
June 19, 2013 - SanDisk
recently
announced
a new version - 3.2 - of its
FlashSoft (SSD caching software)
for Windows Server ($3,000), and Linux ($3,500).
New in this release
is
high availability
support with low latency SSD mirroring for "safe write-back"
caching. Improvements include:- larger cache sizes upto 2TB per cache and upto
8TB cache per server. Also the number of volumes supported by a single cache has
increased from 255 to 2048.
Editor's comments:- I've reported
before about my many past
conversations with FlashSoft and my perceptions about the company from the
days when they were one of the leading independent hot enterprise SSD
software companies in the
3rd quarter of 2011
through to the first indications - about 6 months after the company had been
acquired by SanDisk in
February 2012 -
that contrary to what I had expected from earlier
acquisitions by
SanDisk - there were signs that FlashSoft wasn't just going to provide
another demonstration of Newton's law of the conservation of SSD momentum -
translated to a marketing frame of reference - in which we should not be
surprised to see what happens when a small enterprise SSD pellet fired at
high velocity smacks into a huge consumer SSD cannonball at rest.
So
when I spoke recently to Rich Petersen
Director, Marketing Management at SanDisk - who had earlier been VP of
Marketing at FlashSoft - I was quickly able to pick up the threads of these
earlier conversations we'd had. And I got an illuminating update on the
picture of how SanDisk is changing as a result of what it's still learning
about the enterprise SSD market since having acquired FlashSoft.
I
can't give you all the details here - because I covered 3 pages of notes during
this ideas packed dialog - more than I have ever taken in any previous SSD
company interview. Hearing about what has been happening in SanDisk and what
they've been learning from their customers - and how they've been adapting
those ideas to their SSD plans - I started getting that sense of easy
familiarity I used to get when talking to some of the leading enterprise SSD
companies.
It was a weird feeling. I had to keep reminding myself -
this is SanDisk I'm talking to. And they don't have much to write home about in
the way of enterprise
SSDs. - But despite those handicaps they've been talking to - and
learning from - all these enterprise users who wouldn't give them the
time of day if it wasn't for this software.
So it looks like the
Trojan Horse in SanDisk's enterprise SSD infiltration plan is built from 2
main planks.
- The FlashSoft product provided the foundations of a very capable
enterprise SSD software platform.
And instead of frittering this
acquisition away - as a tactical giveaway to merely sell a few branded SSDs
faster (as some other SSD companies have done) SanDisk is using the FlashSoft
product as a pivotal valued product in its own right. It's being sold - not
given away. It has been getting continuing investment into its development and
is playing a strategic part in seeding the enterprise grain into one of the
world's leading flash memory technology companies.
- FlashSoft supports leading 3rd party enterprise SSDs including products
which are - or could be - competitors to SanDisk's own SSDs. (The business case
for this was discussed in an earlier article.)
I asked if SanDisk has
a list of these products online. I was told - not yet - but it's coming soon.
The result is - many enterprise SSD users - who wouldn't dream of
approaching SanDisk to use its raw SSDs in their enterprise projects - seem more
than willing to use their enterprise SSD software and share their ideas about
enterprise SSD problems and related experiences.
In a Eureka moment I
said - "If I was being cynical I could say that acquiring FlashSoft is a
brilliant and sneaky marketing way for SanDisk to be having these conversations
and learning first hand from users the answers to - what do enterprise SSD
users want? and how would enterprise users change what they do if they were
offered different options? - instead of SanDisk wasting money on buying and
analyzing dozens of SSD
market analyst reports which
at best
- can only give a disconnected. partial and dated overview of what might be
happening in the minds of enterprise users."
Here are some of
the other new things I learned.
- SanDisk eats its own dog food. Being acquired by a Fortune 500 Company gave
FlashSoft an entree into many new applications within SanDisk itself. SanDisk
has been using FlashSoft cached SSDs to enhance its own servers which are used
in many critical parts of the business.
- SanDisk wants the enterprise to be a bigger part of its SSD business. And
while the company still has a very thin hardware enterprise SSD product line -
it's been using the FlashSoft product - aligned to partnerships with other
enterprise vendors such as NetApp, Dell and Virident etc to help build awareness
of SanDisk in the enterprise SSD market.
- SanDisk has learned that people often like the storage they've already got.
And so while they can't easily justify ripping and replacing their SANs - the
leveraging power of an SSD cache - which can deliver 3x as many VMs per
host - makes a much easier SSD economics use case.
- SanDisk says they've seen users re-evaluating and reviving once
abandoned VDI projects based on the efficiencies and performance they can now
see being promised by FlashSoft accelerated virtual desktops.
- While the standard SSD workhorse of the FlashSoft environment will usually
be PCIe SSDs or
SAS SSDs - the ability
of the product to concatenate separate devices of different types into a single
logical volume coupled with the ability to assign different cache priorities to
different SSDs means that users can also mix and match lower cost enterprise
SATA SSDs into the
mix.
- Final quick notes... The FlashSoft caching engine is the same on all
platforms. This release brings the Linux and Windows FlashSoft feature sets up
to the same level. SSD capacity is dynamically allocated - which simplifies
scalability. Writes to flash devices are disciplined by filters which reduce
random write amplification - which - coupled with read caching has the
beneficial spinoff that some SAN users can see upto 90% reduction in their SAN
I/O traffic.
What's it all about? - Can SanDisk - a leading
consumer semiconductor company - really transform itself into an enterprise
SSD heavyweight? If you'd asked me that question 16 months ago - I would have
said (and did say on these pages) an emphatic no!
When I learned that
FlashSoft had been acquired by SanDisk I thought (and wrote here) - that would
be the last we would hear of that particular enterprise SSD software company.
I was wrong about that.
Can the tiny FlashSoft inject enough raw
enterprise intelligence back into the giant which swallowed it - in a way which
is both palatable and can change the way the giant thinks and behaves?
It
looks like there's a lot of creative energy and resources going into that. And
with the help of its business partners and customers there's a growing
enterprise eco-system attaching itself to the SanDisk core.
You could
say - all that's missing now is a full spectrum enterprise SSD product line.
(And a track record.) But unlike other new companies who also want to get into
the enterprise market - SanDisk doesn't have to rely on what the analysts
say. They've now got their own unique window into the enterprise SSD user deep
thought stack.
Samsung enters PCIe SSD market
Editor:- June 17,
2013 - Samsung
has entered the PCIe SSD
market with an M.2 form
factor model (80mm x 22mm) aimed at
notebooks.
Samsung's XP941 - which weighs less than 6g - has a sequential read
performance of 1,400MB/s, and capacity up to 512GB.
Editor's
comments:- the
SSD notebook
market began the year before PCIe SSDs started being used in the
enterprise.
But in the first 5 years of its history (2006-2010) the
notebook SSD market was a disappointment to SSD evangelists like me - because
integration with PCs was so bad. And for years on these pages I ranted that
notebooks using SSDs would never be able to reach their true potential as long
as they were still wasting their inherently light CPU resources and latency
advantages by talking to the CPU via old fashioned
hard disk interfaces
like SATA.
The
exciting thing about today's announcement by Samsung is that consumer grade
PCIe SSDs for notebooks will enable a dramatically different user experience
which will help to create new markets.
Will there be a crossover into
the enterprise market?
It's inevitable that some people will ask -
what would an array of consumer priced PCIe SSDs look like in a box? And no
doubt you will probably see such products coming onto the market. And that
might lead to a temporary state of user confusion about expectations for PCIe
SSDs.
But setting aside for the moment the obvious considerations at
the single drive level of differences in
endurance
and performance
characteristics - I think the key differentiators of enterprise PCIe SSDs
compared to consumer
PCIe SSDs are the different degree of
data integrity
(higher for the enterprise),
power fail
management and support for fault tolerance.
| |
| . |
Hmm... it looks like you're seriously
interested in SSDs.
Take a look at these resources.
SSD market
history
SSD
market research analysts
About the publisher - 21
years guiding the enterprise market |
|
| |
....... |
the Top SSD Companies
can you
trust SSD market data?
how fast can your SSD
run backwards?
Ratios
of SSD capacity - server vs SAN
7 SSDs silos for the pure
SSD datacenter |
| ....... |
 |
| ....... |
| . |
how long for hard
drives in an SSD world?
exciting new
directions in rackmount SSDs
Adaptive R/W and
DSP ECC in flash SSD IP
Efficiency - making the
same SSD - with less chips
how will Memory
Channel SSDs impact PCIe SSDs? |
| . |
 |
| . |
|
|
| . |
| Who
competes with this SSD company? |
Editor:- June 20, 2013 - Almost the first
question you'll ask yourself when you start getting seriously interested in any
particular SSD company is - who are its strongest competitors?
If
you're buying SSDs it helps you get the best products and the best prices.
If
you're trying to understand what a company is doing or how it fits into your map
of the SSD world then identifying the placeholder of "most similar to"
is helpful.
And if your interest in an SSD company is because you're
looking for channel partners or investment opportunities - then knowing the
competition and seeing what they're doing tells you more about the upisde
potential and limiting factors bounding your selected company.
Answering
the questions:-
who makes this type of product?
closely
followed by...
and who else does something similar?
- have
been at the root and core of my
work in the last
20 years or so. Luckily the products have changed - and so the answers have
changed too. Otherwise it would get very boring.
Going back to the "who
else does this stuff?" type questions for SSD...
As a 1st level
filter - looking at the top level directories and news pages for topics like -
SAS SSDs,
PCIe SSDs,
2.5" SSDs,
industrial SSDs
etc can be a useful starting point.
But - as some of these markets
themselves start to fragment into distinctly different segments - the problem
for someone like me is deciding when is the right time to open up a new
category.
Too soon - and not enough readers may care. But if the topic
is important enough I'll do it anyway - which is what I did last year with
adaptive R/W
& DSP ECC flash IP.
Too late - and such a list gets populated
with so many companies that the list itself becomes almost useless.
For
that reason - you'll often see a note in the profile pages of each SSD company
on this site which says something about where you can look to find alternative
competitors.
And when the comparisons become interesting - because they
reveal different technology or market approaches - then this is discussed either
in a technology article, or a news story depending on when the difference became
clear.
In the enterprise PCIe SSD market - for example - it can take a
lot of research to answer the question of who really competes with whom? Partly
because things are changing so much and partly because the definition of what is
really a true alternative is relativistic and depends on where you're starting
from - not just on the raw technical specs and price of the SSD.
The
more significant the company - especially if they're in
the Top SSD Companies
List - the more likely you are to find a recent analysis about what
they're doing and who they compete with.
My assessments may not always
agree with yours. And even my assessments have been known to change with time -
as companies change what they're doing or if I learn something new about them.
Try
it yourself and see if you find it useful.
And those other links -
which appear in most of these company profile pages - which are called "editor
mentions on StorageSearch.com" - do a simple site search on the
company name - can also lead you to closely related analysis from archived news
stories too.
Recently in the - who competes with who category - I've
updated my profile for Virident.
Although there are over 40 companies in the enterprise
PCIe SSD market -
there are only maybe 4 to 6 which make sense to look at if you're interested in
this high-end level.
I referred to this example earlier today for a
reader who I know is really more interested in
Micron.
The
Virident "competes with" list isn't the same list as I would have
created for Micron - but at the PCIe SSD product line intersection there is a
common set of competitor overlap. So that's the best I can offer today.
On
this web site - you'll find a lot of valuable information below the "fold"
as marketers like to put it. (The fold is the top part of the web page which
you can see before you start scrolling.)
When you're interested in a
subject like SSDs - as I've learned from readers who've told me they spend
nearly as much time on the site as I do - the important thing is the quality of
the information and the usefulness of the concepts - rather than the exact
choice of typeface.
And it's unrealistic and futile to imagine that
complex products like SSDs can be described in a single sentence or parameter.
There's a lot more to it than that.
But knowing who the competitors
are - is a useful shortcut in understanding any company. | | |
| . |
|
|
. |
 |
. |
|
|
. |
 |
| . |
|
| . |
|
| . |
|
| . |
|
|
|
| |
