|
|
| HA
enterprise SSD arrays |
Editor:- January 26, 2012 - due to the growing
number of oems in the high availability rackmount SSD market StorageSearch.com today published
a new directory focusing on
HA enterprise SSD
arrays.
In my past 20 years of publishing enterprise buyers guides
- I've developed an instrinct for judging when the market is ready for a new
focused directory. |
 |
Sometimes I've been too
early - but with the momentum in the enterprise SSD market and the number of
HA SSD vendors already dipping into double digits - I think this is exactly
the right time for such a new directory. | | | |
| .... |
| Fusion-io's
revenue nearly trebles, but... |
Editor:- January 24, 2012 - Fusion-io today
announced
that revenue for its 2nd quarter ended December 31, 2011 was $84
million - which is 2.7x its revenue in the year ago period.
Editor's
comments:- like many other SSD companies nowadays FIO lost money in the
quarter and you can see the gory details by clicking on the links above and
going to their web site.
I'm not a financial guy - but I have
written
an article in which I share
my thoughts about why loss making SSD companies like Fusion-io are still
warming (rather than cooling) SSD interest in the VC investor climate. ...read the article | | |
| .... |
| Bottlenecks in the pure SSD
datacenter will be much more serious than in the HDD world |
When you're an expert in a subject it's
hard to understand the confusion that newcomers experience when they first meet
the topic.
Now to be fair - the enterprise SSD market is the most
complicated and confusing subject in the computer market - and even many so
called "storage experts" fail to see clearly what's going on - because
SSDs are about a lot more than just storage.
In a recent dialog with a
reader who was asking about a particular rackmount SSD supplier - I introduced
my concept of enterprise SSD market silos.
There will be 5 to 7
distinct silos in the pure SSD datacenter of the future.
Vendors - who
by design (or accident) - offer products which match the spec and price contours
of those silos - will have advantages over competitors whose products do too
much, too little or don't match the requirements in other dimensions (like
physical size and price).
I've been talking to SSD company founders and
investors about my enterprise SSD silo classifications for about 2 years -
having introduced the concept in my petabyte
SSD roadmap article.
But unless you spend all your time thinking about the future of the SSD market -
and new SSD designs - you won't understand 80% of what we talk about.
I
know that whatever I say or write about this roadmap topic - many of the
concepts that are clear to me - will make as much sense to most people as
explanations of string theory and Higgs boson.
Analogies can't help
guide you through complex decision making either.
All they can do is
alert you to the possibility that something which looks deceptively simple from
the outside may be more complicated and have serious repercussions if you make
the wrong vendor choice.
So
- having given up on referring to architecture and market models - here's what I
said earlier today about the SSD silo concept to a reader. Some of you may
find it helpful too.
A good way to think about what SSDs will
do in the 100 per cent SSD enterprise - is to set the limits for how an
enterprise can repurpose, leverage and monetize its data - and increase process
efficiency by analyzing and anticipating customer demands in real-time.
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.
Having the wrong SSDs in the wrong places will be like having a
skyscraper with insufficient escalators to move the workforce in and out each
business day.
If the workers in the corporate tower can't get in and out of their
offices in a reasonable time - they might as well stay at home. |
 |
If the right data can't get
to the right place exactly when it's needed it might as well not exist. And the
enterprise which depends on that data will cease to be viable. | | | |
| ..... |
| fast erase / purge MIL SSDs |
The need for fast and
secure data erase - in which vital parts of a flash SSD or its data are
destroyed in seconds - has always been a requirement in military projects.
 Although
many industrial SSD
vendors offer products with extended "rugged" operating
environment capabilities - and even notebooks SSDs come with encryption -
it's the availability of fast destructive data purge which differentiates "truly
secure" SSDs which can be deployed in sensitive applications.
Who
makes these SSDs? How do they work? And what are the characteristics and
limitations of the various methods used? Click on the link above to find out
more in my special article / directory about
fast purge SSDs. | | |
| . |
| Surviving SSD
sudden power loss |
Why should you care
what happens in an SSD when the power goes down?
This important design
feature - which barely rates a mention in most SSD datasheets and press releases
- has a strong impact on
SSD data integrity
and operational
reliability.
This article will help you understand why some
SSDs which (work perfectly well in one type of application) might fail in
others... even when the changes in the operational environment appear to be
negligible. |
|
| | |
| . |
| Where does all the money
go? - inside SSD pricing |
| SSDs are among the most
expensive (and complex) computer hardware products you will ever buy and
understanding the factors which determine SSD costs is often a confusing
and irritating process... ...which is not made any easier when market prices
for apparently identical capacity SSDs can vary more than 100x to 1!
|
 |
Why is that? There are
good reasons for these cost differences. But more expensive isn't always better
for you. To find out what goes into the price - and whether you need it - ...read the article | | | |
| . |
| How big was the
thinking in this SSD's design? |
Does size really does matter in SSD
design?
By that I mean how big was the mental map? - not how many
inches wide is the SSD.
The novel and the short story both have their
place in literature and the pages look exactly the same. But you know from
experience which works best in different situations and why.
When
it comes to SSDs - Big versus Small SSD architecture - is something which was
in the designer's mind. Even if they didn't think about it that way at the time.
|
 |
For designers, integrators,
end users and investors alike - understanding what follows from these simple
choices predicts a lot of important consequences. ...read the article | | | |
| . |
| the 3 fastest flash
PCIe SSDs - list / lists |
You know the sort of
thing I mean - where a magazine compares 10 SSDs or a blogger compares 2 SSDs
against each other. It would be nice to have a shortlist so that you don't have
to waste too much of your own valuable time testing unsuitable candidates
wouldn't it?
StorageSearch's long running
fastest SSDs directory
typically indicates 1 main product in each form factor category but those
examples may not be compatible with your own ecosystem.
If so a
new article -
the 3 fastest PCIe
SSDs list (or is it really lists?) may help you cut that Gordian
knot. Hmm... you may be thinking that StorageSearch's editor never gives easy
answers to SSD questions if more complicated ones are available.
|
 |
But in this case you'd be
wrong. (I didn't say you'd like the answers, though.) ...read the article | | | |
| . |
| |
.... |
| Who's who
in SSD? - by Zsolt
Kerekes, editor |
 |
| WhipTail, founded in 2008 and based
in Whippany, NJ, commercialized the first all-flash enterprise storage array to
address performance issues in data centers. |
|
WhipTail is 1 of more than 100 companies
in the rackmount SSD
market, and also appears in these sub-segments of the SSD market:-
iSCSI SSDs,
FC SAN SSDs and
InfiniBand SSDs.
WhipTail
- which launched its first flash SSD arrays in
February 2009
- made its debut appearance in the
Top SSD Companies List
recently (January 2012) based on search metrics in Q4 2011.
The
company recently changed the way it describes itself to suggest it was the
first company to market enterprise grade flash SSD arrays. That's bunkum of
course - because FC and NAS compatible rackmount flash arrays were being
shipped by several companies in
2007 - the
year before WhipTail was founded - and one of those companies was an early
supplier of technology to WhipTail itself.
I don't want to make a big
thing out of this particular error - because it's typical of the messy
verbiage that many high tech companies get into when they try to formulate a
summary description of themselves while still trying to preserve as many words
as possible from the Holy Writ passed down from the early text drafts of
their founders.
Eventually a kind customer or a clarity seeking
editor has to come along and say to a company - Look I'm interested in what
you do - but you really do need to rewrite this - either because it doesn't make
any sense (I can supply a list of SSD companies with profiles in the nonsense
category) or because it appears to make sense but the exact words convey a
message which undermines your credibility - or maybe the words just say nothing
useful at all.
For example -
STEC has appended the
null content phrase "the SSD company" to its logo and
SSD videos. And whereas
they might wish they were "the only (implied) SSD company" -
as their investors know only too well - many "other" SSD companies
seem to be blissfully unaware that they aren't supposed to exist.
The
problem for SSD
brand marketers is - once you start adding detailed qualifying statements
to company logos and mission statements they can start to read more like a
legal contract - and they lose their punchiness.
back to
WhipTail...
I was prompted to update my understanding of what
WhipTail is doing (in early January 2012) by some probing reader questions
which I couldn't answer adequately - as it had been more than a year since I
had last talked to the company's CTO and 5 months since they had done
anything I regarded as newsworthy.
Sometimes coincidences happen in
my job and the very next day a PR person working for WhipTail contacted me and
said would I like to talk to one of their senior managers? (This was the week
before they went on to announce their 2nd funding round.) And that was also
when I had got to the point in analyzing the search stats for Q4 2011 to
realize they would be making a debut appearance in the top SSD companies list -
which means enough of you are interested in what they do - so I should be too -
and their VCs should
be happy - for a while too,
I didn't disclose that information - and I
said I wasn't interested in a briefing about their press release - but I would
be interested shooting the breeze about the SSD market, discussing what they
were doing now and getting an update on their business. And that turned out to
be a very useful reset for some of my assumptions about WhipTail formed from
earlier contacts with the company (and looking at their web site).
redrawing
the picture of WhipTail
That's how I got to speak recently to
WhipTail's President and CFO - Cameron Pforr .
I
started by asking how they were doing with their real-time dedupe and
compression technology? - because they talked a lot about that when the company
launched and I - for one - thought of them in that context.
He said
they were no longer emphasizing that because it led to latencies which were too
long to be competitive - and instead they were focusing on performance.
WhipTail's
SSD box in 1 paragraph (and 2U)
We discussed technology and rather
than follow the track of our dialog I'll give you my own analysis and
summary of their product line which is this - WhipTail's
XLR8r is a fast-enough (250K
write IOPS
sustained / 750K IOPS peak) 2U rackmount MLC SSD with
regular RAM cache
- with an open
hardware architecture based on an array of COTS
2.5" SSDs with a
usable capacity density of 6TB per U.
WhipTail doesn't design any of
the flash SSDs in its arrays - instead it qualifies suppliers for consistency
and reliability. Endurance
isn't a worry for fast-enough (as opposed to fastest) MLC SSD arrays -
especially when there's a high ratio of capacity to user bandwidth and also a
RAM cache which helps reduce
write amplification.
Cameron said the logs from their customer systems extrapolate 8 years
operating life.
We had an interesting chat about how to develop SSD
business. Cameron had been at
Fusion-io and
Violin in the early days
of those companies trying to attract customers using (to my way of thinking)
traditional personal sales oriented techniques rather than modern scalable
marketing led methods.
He told me how many people there were in
WhipTail when he joined (about 10) and I was surprised. I said they must all
have been running and typing very fast and preoccupied with development and
sales. It explained to me why the web communications aspect of the company had
been so weak. Beefing up marketing is one of the things that the 2nd round
funding is supposed to do.
Cameron told me about the good reaction
they'd had from customers - reiterating the high percentage of customers who had
already made additional purchases. Their customers are from across the usual
spectrum of industries and applications which benefit from SSD server
acceleration - rather than biased towards 1 or 2 segments.
I've
always said that the market for general purpose "not so fast" SSD
arrays is much bigger than that for the
fastest SSDs -
because most mortals don't need ultimate speed - and slower should be cheaper.
WhipTail's
competitors?
Cameron Pforr told me he sees WhipTail's
particular competitors as being
Violin and
Texas Memory Systems.
Personally,
I'd disagree with that assessment. Those 2 companies occupy a space in user
perceptions about the market because they've sold a lot of SSD systems - and
that's a market position to aspire to - but I'd say that WhipTail's direct
competitors to beat will be the unknown masses of white box and big name
SSD RAID vendors.
Let
me explain my thinking here.
Systems based on
small SSD
architecture modules like those in WhipTail's arrays are currently at a 2 to
1 disadvantage when it comes to capacity density compared to the big
architecture controllers from Violin and TMS - and WhipTail isn't in the same
performance league either - when you look at performance per U.
That's
not a problem when you're looking at small installations - where a customer
might only use one to a handful of SSD racks - but to my way of thinking -
petabyte scale SSD
users who want to stuff all their cabinet space with SSDs are going to
get more picky about SSD metrics per rack unit.
That's where
segmentation comes in.
Some users will prefer the "open"
WhipTail approach (because the customers will feel they are less dependent on
single source hardware) others will prefer the "proprietary" Violin /
TMS approach because it uses less rackspace - while another set of users again
will choose to buy standard servers stuffed with
PCIe SSD cards. As I
discussed in an
earlier article about SSD rack trends - I think all these different
approaches will thrive despite their apparent contradictions.
In
this year of the
enterprise SSD goldrush - companies like WhipTail which have an easy to
understand system that works and high customer re-order rate - can be confident
that if they get their marketing right - they can easily sell all the SSDs they
can make.
Getting above the visibility horizon is the first step in
that process - and they've achieved that. Staying there as we know from recent
SSD history
- is much harder.
For more info about WhipTail take a look at the
links above and
WhipTail
- editor mentions on StorageSearch.com.
I currently talk to more
than 300 makers of SSDs and another 100 or so companies which are
closely enmeshed around the SSD ecosphere - which are all profiled here on
the mouse site.
I learn about new SSD companies every day, including
many in stealth mode. If you're interested in the growing
big picture of
the SSD market canvass - StorageSearch will help you along the way. Many
SSD company CEOs read our site too - and say they value our thought leading SSD
content - even when we say something that's not always comfortable to hear. I
hope you'll find it it useful too. | |
| .... |
|
|
| .. |
|
| . |
| |
.. |
| "By 2016 I expect
that upto 50% of the searches for rackmount SSD will be driven by the
need to find the lowest cost storage capacity - instead of (as today)
98% being driven by the need for faster storage performance." |
| ......from a new article about -
Rackmount SSDs | | |
| .. |
|
|
| .. |
| SSDs. the
micro and the internet |
Editor:- January 2012 - it
probably won't surprise you to learn that the subject of SSDs came up a lot with
the friends and relatives I talked to during the recent Christmas holiday.
How
do I explain the significance of the SSD market to people with diverse
backgrounds in a couple of sentences?
That's quite a challenge.
The
easiest people to discuss the SSD market with are those with a background in
electronics - particularly if they have worked in semiconductor companies.
I
also find easy to find reference points when talking to those who have worked
in the computer market. Despite that, however, the risks of potential
bottlenecks in product roadmaps and reliability subtleties and cost factors
associated with different
types of flash memory are concepts which are beyond the comprehension of
most people with database admin backgrounds.
They just have to accept
that there are important strands in chip technology which they can't
understand from first principles - and they therefore have to rely on indirect
clues and hope that the reference sources they trust are correct when it comes
to making supplier choices.
Since the flurry of acquisition and IPO
fever in the SSD market in
2011 - it's
become much easier discussing the significance of the SSD market with people
whose backgrounds are financial - like accountants and business managers with
MBAs. That's because money talks. And the SSD financials tell a clear story.
Here is a market which was till recently too small to bother learning about.
But it now such good prospects for revenue growth (100% / year in some
segments) and potential
towering revenue ceilings. These factors mean that a handful of leading
SSD companies were valued in 2011 at a total amount worth more than the
combined revenue of the entire market of several hundred SSD companies. SSDs
could be a new tech growth bubble.
The toughest people for me to
explain the context of the SSD market to - are those who have no technology
background at all - even if they have achieved senior positions in people
related markets - like law and psychology.
In those circumstances I
know that not a word I say about architecture, chip technology or market size
is going to be understood. But I can still find reference points from everyday
life. And my argument goes something like this.
Since the early 1970s
there have been 3 revolutionary disruptive influences in the electronics and
computing markets.
- the commercialization of the internet
- the transition of digital storage to solid state drives (SSDs)
I
can relate where I think we are in the SSD market at the start of 2012 to
distinct phases in those earlier revolutionary markets.
Comparison
with the microprocessor market.
The first microprocessors started
shipping in the early 1970s. By 1980 - it was clear that the micro was going to
affect a lot more than just the computer peripherals market. By that time micros
were being designed for wide deployment in factory automation and process
control systems and the new digital technologies enabled improvements in the
levels of efficiency and repeatable quality in the manufacture of everything
from foodstuffs and chemicals to cars - which had previously been impossible.
All this was still before the introduction of the Wintel PC - which as a
standard reference platform later enabled the creation of entirely new markets.
I would say that the SSD market today (despite its long
history)
is similar to the state of the microprocessor market in 1980. Some of the SSD
types and applications for SSDs are already in use - but we still haven't got to
the equivalent of the 16/32 bit micro market - because there are many
architectural improvements and reference platforms still to be developed.
Comparison
with the internet market.
The internet moved into a new higher
orbit with the introduction of commercial web sites in 1995. Before then the
primary use of the internet had been email - but as we now know - the web
eventually made it easier to find out information about almost anything and
then buy it in almost seamless real-time transactions.
I would
equate the state of the SSD market today with the state of the web in about 1998
- when you could already see a lot of the promise and the direction that the
web was going towards (the hype was so great we had the dotcom bubble) but this
was still before Google became operational and long before the economics of
digital rights management - and iTunes and the Kindle.
In the SSD
market today we can extrapolate from current business uses of SSDs and speculate
about future SSD enabled markets. But we still haven't got the pure play SSD
enabled information economies in play yet. Most of what we've got today with
Facebook, YouTube and online games is SSD accelerated versions of businesses
that already existed before.
How long before we get to the Kindle age
in the SSD market?
I expect we'll see entirely new SSD enabled markets
in the next few years - but it could be 2015 or later before it starts to be
clear who the SSD equivalents of the Wintel platform (leveraging the
microprocessor) or Amazon and Apple (leveraging the web) will be.
If
you're the CEO in a new startup and you think that your SSD enabled services
will change the world - send me an email when you're ready for our readers to
know more. | | |
| . |
| 3 things that could have
killed flash SSDs |
The
emerging size of
the flash SSD market as you see it today was by no means inevitable. It owes a
lot to 3 competing storage media competitors which failed to evolve fast enough
in the Darwinian jungle of the storage market in the
past decade.
One of these 3 contenders is definitely on the road to extinction -
but could one of the other 2 still emerge to threaten flash SSDs?
The
article -
SSD's past phantom
demons explores the latent market threats which hovered around the flash SSD
market in the past decade. They seemed real and solid enough at the time. |
 |
Getting a realistic
perspective of flash SSD's past demons (which seemed very threatening at the
time) may help you better judge the so-called "new" generation of nv
memory contenders - which are also discussed in the article. ...read the article | | | |
| . |
| Violin video re advantages
of home grown controllers |
Editor:- January 23, 2012 - I commented recently
that the top 10 SSD
companies in Q4 2011 all had one thing in common (apart from the fact they
make SSDs)...
They all have their own proprietary
SSD controller
architecture which they can use to optimize products for some applications
and markets (even if some of them also use other controllers too).
In
a
recent
video - Violin's,
CTO Software Jonathan Goldick
talks about the benefits they get from having their own controller. |
|
|
| See also:-
more SSD videos. | | | |
