 |
|
|
| leading the way to the
new storage frontier | |
| ..... |
This
page includes the
archived SSD
news from
StorageSearch.com for March 2013.
Companies
mentioned in SSD news this month included:-
Diablo Technologies,
EMC, Fusion-io,
InnoDisk,
LSI,
Nimbus,
OCZ,
Pure Storage,
QLogic,
RunCore,
Seagate,
Skyera,
SolidFire,
STEC,
Violin,
WD |
| . |
RunCore closes $10 million funding
Editor:-
March 29, 2013 - RunCore
today announced
it has closed $10 million in Series B funding led by OFC (Oriental Fortune
Capital).
"The global solid state storage market is booming, so
we believe that now is the best time to take on board strategic investors to
more rapidly achieve our globalization plans" said Jack Wu, CEO -
RunCore.
InnoDisk's upcoming 10x endurance industrial MLC SSDs
Editor:-
March 28, 2013 - InnoDisk
today
announced
it will ship industrial SATA SSDs using its
iSLCT
technology - in Q3.
iSLCT repurposes the 4 states of classic
MLC memory into 2 virtual states (with better signal integrity) effectively
emulating SLC in MLC.
This delivers 10x better endurance than MLC
(30K from "3K" MLC), faster write performance (nearly 2x as fast as
MLC and 85% of SLC speed - at competing geometries) and lower cost than using
SLC to achieve the same capacity (in current and projected market conditions).
Editor's comments:- I mentioned this technique several years
ago in a spoof SSD story - but what was once SSD fiction has become market
reality due to the divergent market
prices of different
types of flash memory.
See also:-
MLC flash lives longer in
my SSD care program,
industrial SSDs
market, hidden
aspects of the SSD capacity iceberg
See later:- why industrial
InnoDisk moved into the HPC AFA market as AccelStor
STEC names new marketers
Editor:- March 26, 2013 -
STEC - long
criticized on these pages for its extreme frugality in marketing resource
investments - today
announced
2 additions to its marketing team.
"Executing on a revamped
go-to-market strategy doesn't happen on its own; we need a highly experienced
marketing organization in place," said Ali Zadeh, CMO STEC. "Judy
and Zack, individually and collectively, bring to STEC that essential experience
in enterprise systems, along with a unique understanding of global marketing and
business development."
Nimbus pins hundreds of flash array metrics to APIs
Editor:-
March 25, 2013 - Nimbus
Data Systems today
announced
new software APIs which support its proprietary
HALO OS based family
of rackmount SSDs
- and report on hundreds of real-time and historical metrics such as:-
flash endurance, capacity utilization, latency, power consumption, deduplication
rates, and overall system health. Another new feature is that sys admins can
monitor their Nimbus
SSD arrays via new apps on Android / Apple phones and tablets.
Thomas Isakovich,
CEO and founder of Nimbus Data said the new software framework would enable
cloud architects and enterprise customers to gain greater insight into their
flash storage by viewing internal aspects of their flash storage which
mattered to them - rather than simply relying on benchmark indicators which
have been cherry picked by vendors or reviewers
QLogic enters the enterprise SSD market - with SAN IOPS caching
accelerator
Editor:- March 22, 2013 - QLogic yesterday
entered the enterprise
SSD market (in the PCI
SSD and SSD ASAPs
segments) with the
launch
its first product - the
FabricCache
10000 Series adapter (pdf) - which provides transparent sharable and
clusterable caching for FC SANs.
The 2 card set (upto 400GB flash,
and 2x 8Gbps FC ports) can deliver upto 310,000 initiator IOPS and
supports upto 2,048 concurrent logins.
QLogic says - FabricCache uses
just a single standard adapter driver per OS, the same QLogic field-proven
adapter driver stack that has shipped with more than 13 million FC ports. The
FabricCache adapter appears logically to the server as a single QLogic HBA which
integrates seamlessly into current enterprise server and infrastructure
environments.
Editor's comments:- from the business and
marketing perspective QLogic's new Mt. Rainier branded SSD is a tardy,
pragmatic and cunning response to the threats and challenges posed by SSDs
to traditional storage ecosystems vendors.
Tardy - because
the first SSD ASAP appliances - which used SSDs to automatically and
transparently accelerate access to
SAN storage first shipped
in 2009. And
the first enterprise PCIe SSDs started shipping in 2007.
Pragmatic
- for a bunch of reasons
- Pragmatic - because QLogic's new products provide a credible way for the
company to participate and get customer experience in the crowded high
value PCIe SSD market - by recycling IP from (what would otherwise soon be
downgraded to) a commodity IP base (FC SAN physical adapters).
In
my 2011 article - don't
all PCIe SSDs look pretty much the same? - SSD ASAPs (like QLogic's
FabricCache ) were discussed as one of the many options for market
differentiation.
- Pragmatic - for another reason too - because with 50 or more different
flavors of auto-caching/tiering software schemes already in the market - QLogic
has neatly side-stepped the issue of participating as yet another new
SSD software company
which user have got to learn about - and instead has cleverly positioned its
product as needing no new software. (The FabricCache adapters learn everything
they need to know from being acticated by standard FC HBA drivers.)
Cunning
- because the implied message to users here is:- "if you want to fool
around with SSD auto-accelerating your SAN storage - you can do it without
haveing to learn about new software. - All the software you need to know about
is already running your interface HBAs."
This is kind of sneaky -
because in reality - if users are investing in this product - they will soon
start to care about the internals of the software - and to ponder on the
ability of QLogic to continue delivering good
market roadmap
symmetry across upcoming new generations of back end SAN storage systems as
these SAN racks themselves change their internal make-up from hard drives to
flash.
Another consideration is that - accelerating data I/O between a
traditional server SAN stack and storage on the SAN - may give better results
than without any flash - but may not be as good an ROI as the competing
alternative of accelerating apps performance using similar flash capacity
but with an interface agnostic bunch of algorithms.
Nevertheless -
QLogic's new SSDs provide a "low perceived risk" way for users -
who don't want to plunge deeply into the mystical and changeable details of
SSD acceleration - to experiment and fool around with the benefits of SSD
SAN acceleration.
Before I get any emails from investors asking - is
this good for QLogic? or - is it bad for
Fusion-io (or
Virident)? Here are
my thoughts.
Companies in the server SAN infrastructure market have no
future without an SSD core. So having a plausible SSD product - even at this
late stage of the enterprise SSD market development game- upgrades QLogic from
a future as a mere commodity interface chip supplier to a plausible player.
I doubt if any PCIe SSD makers feel in any way threatened by QLogic's new
product.
See also:- QLogic's informative white paper -
QLogic
Mt. Rainier Integrates SSDs with SAN Connectivity (pdf)
more money for Diablo
Editor:- March 19, 2013 - It's
not unusual in the current
SSD market for
some companies to have oversubscribed
investor funding
rounds - and that was the case recently with Diablo Technologies
which today
announced
it has closed an additional $7.5 million of funding, increasing the total
equity investment of its most recent round to $36 million.
USVP joins
previously announced investors.
Editor's comments:- Diablo
describes its product as being these categories:- "soon-to-be-announced"
and "disruptive".
If you're already interested in
PCIe SSDs,
InfiniBand or SSDs
in RAM module form factors
(but which unlike the flash DIMMs from memory makers - might actually emerge
from stealth mode attached with a software model) then what Diablo does do
with its Memory Channel Storage may impact some of your future long range
plans.
Like you - I'm guessing of course. Diablo hasn't ordered any
SSD ads yet - although
that $7.5 million would come in handy.
Fusion-io acquires SCSI target IP team
Editor:-
March 18, 2013 - Fusion-io
announced
today that it has acquired another
storage software
company - ID7 - which had been
collaborating on the development of FIO's
ION data
accelerator software.
ID7 was the primary developer of the
SCST (SCSI target subsystem for
Linux) that enables replication, thin provisioning, deduplication, high
availability, and automatic backup on any Linux server or appliance.
"We
had an opportunity to work with Fusion-io on the development of the ION Data
Accelerator..." said Mark Klarzynski,
Founder and CTO of ID7 (who
blogged
today about the acquisition).. "We're excited to join the Fusion-io team...
to work together on open, software defined solutions to today's most
challenging data demands."
SSD performance characteristics and limitations
Editor:-
March 15, 2013 - published today - the new home page blog on StorageSearch.com is -
a toolkit for
understanding flash SSD performance characteristics and limitations.
It
brings together in one place many of the tools I use every day when thinking
about and assessing SSDs.
STEC's revenue dips below 4 years ago figure
Editor:-
March 14, 2013 - STEC
today
reported
that revenue for its FY ended December 31, 2012 was $168 million - having declined
over 40% from the year before figure of $308 million. Revenue in the most
recent 4th quarter was on a downward slope too - about 17% less than the 3rd
quarter.
Editor's comments:- STEC's revenue in 2012 was 26%
lower than it was 4 years earlier in
2008 ($227
million) when there were already 100 companies competing in the SSD market -
but STEC was the leading flash SSD company measured by revenue.
new LSI blog on the value of enterprise flash
Editor:-
March 14, 2013 - You won't be surprised to see me mentioning a
recently
published blog by Robert Ober,
System and Processor Architect, LSI - about the
value of PCIe SSDs in
big datacenters - which includes these statements:-
- "Work/$ is the correct metric (and not crazy expensive $/bit)."
- "when users say... $8k PCIe card in a $4k server – really? - I
am always stunned by this"
I'm guessing that the title of Robert's
blog - What are the driving forces behind going diskless? Will 100% flash
storage make sense in enterprise? - was either inspired by
SEO considerations
(stuffing the title with value-loaded words for search-engines) or was
predetermined before the blog was written.
I prefer this alternative
title - suggested by a banner graphic in the blog itself -
An $8K PCIe
card in an $4k server - huh!?!
See also:-
User Value
Propositions for buying SSDs,
SSD silos in the
enterprise
Addonics has new adapter to build 1.8" removable SSDs
Editor:-
March 13, 2013 - Addonics
today
launched a new adapter
which lets designers use mSATA or CFast flash cards as removable
1.8"
USB SSDs. MSRP
starts at $55.
WD invests in Skyera
Editor:- March 12, 2013 - WD was one of the recent
investors in Skyera
- it was
announced
today.
"We see companies like Skyera as offering a dramatic
improvement over traditional approaches to emerging storage challenges"
said Steve
Milligan, president and CEO, Western Digital.
OCZ going forward with new credit
Editor:- March
12, 2013 - OCZ
today
announced
it has secured new credit lines:- a $15 million term loan and a $15 million
revolving loan facility.
"Obtaining this new credit facility is the first step in
providing OCZ with a complete capital structure going forward. This capital will
be used to strengthen the business, fund future growth, and support emerging
enterprise opportunities," said Ralph
Schmitt, CEO of OCZ.
We're #1 in SSD revenue - says Micron
Editor:-
March 7, 2013 - Micron
sees itself as the biggest SSD company - in terms of revenue, with about 6%
market share in enterprise SSD - according to Kipp A. Bedard,
VP Investor Relations - at a recent investors conference - transcribed in
an article on SeekingAlpha.com
"In terms of SSDs, if we specifically broke out our SSD
revenues, we'd probably be the largest SSD public company today. If I had to
guess, we're probably running on a revenue basis somewhere around 80%, 85%
client, 15% to 20% enterprise"
Other interesting observations in
this presentation.
"The average smartphone includes 30GB flash."
"We believe the
client SSD market
is growing about 20% units q-over-q." ...read the article
Thanks
to Tony - a reader - who alerted me about this.
NetApp and LSI do that luvvy-duvvy thing
Editor:-
March 6, 2013 - LSI
today announced that its
Nytro
WarpDrive (PCIe SSDs)
have been validated for use with NetApp's
Flash
Accel (SSD ASAP)
software.
Editor's comments:- According to
NetApp's pdf
- "Flash Accel has the ability to keep the cache warm and coherent in
the event of disruptive operations and restart caching from the reboot/crash
point, rather than restarting from a cold cache."
But it's not as
unique in these respects as their document would have you believe - although
this suggestion is probably because of when the document was written.
LSI
says in its press release that its "advanced off-loaded
multiprocessor architecture uses up to 4x less CPU and memory resources
than competing solutions".
Now when you see that phrase - off-loaded
- in this kind of context - you can be sure that it's a dig at
Fusion-io.
The pros and cons - in architectural
efficiency and
performance -
aren't as straightforward as they appear from this subliminal value-loaded
phrasing. I discussed these issues a few years ago in an article in
FIO's product page here
on the mouse site.
The motivational reasons you might choose LSI
rather than FIO (or the other way around) probably have less to do with whether
you understand or like the way they design
SSD controllers
(which are evidence rather than motivations of what lies behind their
SSD architecture
thinking) and instead I think the reasons you might prefer one or other as a
strategic supplier would have rather more to do with whether you're
comfortable with their different
philosophies about the best routes to the
future
of enterprise storage and, in particular, whether you agree with their
speculation of what the
destination looks like.
If you're going to be in the same waggon
train for 2-3 years - bumping along comfortably together is what's
important.
9 million IOPS in a single PCIe SSD
Editor:- March
5, 2013 - Fusion-io
today
announced
it has achieved 9.6 million
IOPS (64
byte) from a single 365GB MLC
ioDrive2 (PCIe SSD).
This
performance is made possible using APIs in
Fusion-io's ioMemory
SDK (such as Auto-Commit Memory) that integrate flash into host systems,
allowing data to bypass normal bottlenecks in the operating system.
FIO
says its APIs have been embraced by dozens of industry-leading
software companies to
enhance their applications.
OCZ releases fault tolerant SSD caching software
Editor:-
March 5, 2013 - OCZ
today
announced
the general availability of
VXL
1.3 (SSD software)
- which enables PCIe
SSD flash volumes (on the company's
Z-Drive R4) to be
virtualized and synchronously mirrored, so they are continuously available to
support HA and
FT services from within the virtualized host without the need for any
back-end SAN or storage
appliance. This easy to manage approach yields no data loss and no VM downtime
even during complete server failures.
Another new feature - related to enterprise
caching- is a
'business-rule' pre-warming cache engine that adapts the flash cache to the
activity cycles in the data center to determine peak I/O performance needs at
certain times.
EMC samples XtremIO flash arrays
Editor:- March 5,
2013 - EMC today
announced
new models of PCIe
SSDs which the company claims offer nearly 60% better
TCO than (unnamed
competitors) due to new levels of
efficiency.
EMC's
XtremSF
half - height, half - length PCIe SSDs are currently available in
eMLC upto
2.2TB, while SLC models upto 1.4TB will ship in the 2nd quarter.
EMC
also said it's sampling flash
arrays which are designed and
managed
using the big
SSD controller architecture based on leveraging IP from its acquisition
of XtremIO.
Editor's
comments:- the industry has been anticipating flash SSDs which use
XtremIO's RAID busting
architecture.
Details are sketchy right now - but the
efficiency gains
from throwing away the old drive array design rulebook and starting again with
a flash foundation while at the same time having control of the complete
SSD software stack can
be impressive - as I learned last year talking to Rado Danilak
CEO of another leading company taking this approach -
Skyera.
Can
we expect EMC's flash array pricing to plunge down to Skyera levels?
That
will never happen - because EMC's business carries the legacy burden of too
many hard drives and too many old suits.
But what we could see
instead - is EMC's flash arrays coming down to a price point where the
customer pain is low enough to delay many of them from switching away to
other flash. Which means EMC could still have a future in the
solid state
storage business.
How "solid" is an SSHD? - when less than 2% of the
capacity is solid state
Editor:- March 5, 2013 - Seagate would like you
to believe that the best way to make a
consumer SSD
better (more affordable) is to put it in a
hard drive.
The
company describes this as "SSD + HDD = the best of both worlds."
Seagate's
latest offerings at the
hybrid drive altar
- Seagate
SSHDs (Solid State Hybrid Drives) - which are designed to deliver
"SSD-like
response from your favorite applications and files" are now shipping
in 2 main wrapper styles:-
- Seagate
Desktop SSHDs - are similar to the notebook drives and have upto 2TB
magnetic capacity in a higher package (26mm rather than 9.5mm).
"Seagate's
engineers have really out done themselves this time" said Scott Horn, Seagate's VP
of marketing in a
press
release today.
"Our new SSHDs serve up your favorite
content with the lightning-fast performance you have to experience to believe.
With these new drives it's like adding a turbo-charge to your PC, without having
to sacrifice capacity, at a price that's easy on your wallet. Now consumers can
create, store and consume digital content like a pro without having to
spend like one."
Editor's comments:- Hybrid drives like this are aimed at the
benchmark experience.
Seagate says they'll boot 5x faster than a
5,400
RPM HDD based notebook. But will that translate into the kind of product
which users will rave about?
Ask yourself this question.... If this
kind of flash to HDD caching ratio (125 to 1) works so well - how come the
enterprise rackmount storage market isn't dominated by racks stuffed full of
Seagate hybrids - using an enterprise-adapted version of Seagate's
Adaptive
Memory Technology?
What are all the clever people in the enterprise
storage market doing wrong? - with their different ways of doing
Auto-tuning SSD
Accelerated Pools of storage?
That's the question I asked myself
about the viability of hybrid drives on these pages back in 2005 - when the
hybrid drive market
began. And I concluded that - if as a user you want better performance - you
will generally get better results and economics by using vanilla HDDs in your
HDD+SSD mix.
That doesn't mean to say that millions of people won't
buy hybrid based PCs. The question is - would they choose to buy the same
product again? And would they recommend it to their friends?
If you
really want park bench performance in the PC experience- rather than
benchmark experience - here's 2 ways to dissect and improve the Seagate
SSHD.
- lose the SATA interface
- lose the hard drive
Violin enters the PCIe SSD market
Editor:- March 4,
2013 - Violin is
entering the market for PCIe
SSDs. Its new
Velocity
PCIe Memory Cards range have
regular RAM caches
and are available in 3 physical sizes.
- Low profile - 1.37TB raw capacity, 110K
IOPS (70:30
R/W)
- Full height, half length - upto 5.5TB raw capacity, upto 250K IOPS
- Full height - upto 11TB raw (8TB usable) capacity, upto 500K IOPS
Editor's
comments:- in October
2012 - I wrote that Violin's lack of a PCIe SSD card product line was a
serious business weakness - which limited their accessible revenue in the
enterprise SSD market.
This product gap would have been an important
scoring factor in any potential company assessing Violin's value as an
acquisition.
It was one of several significant reasons why
Texas Memory Systems
(acquired by
IBM) looked like a much
more attractive acquisition candidate in the early part of last year than
Violin - even though both companies had market-leading
big controller
SSD architectures - and despite Violin having sought acquisition much
longer.
Violin's lack of a PCIe SSD product line till now was a serious
misjudgement of the opportunities
for its technology in the enterprise SSD market and not due to any technical
defficiencies. The company's first SSD racks launched in
August 2007
(the Violin 1010 Memory
Appliance) had - in fact - been launched with PCIe interfaces.
How
will Violin's late entry into the PCIe SSD card / module market impact
competitors?
The established leaders in this market space are:-
Fusion-io,
Texas Memory Systems,
Virident and
OCZ (and another 35 or so
companies are listed on our
PCIe SSD page). One
more company in this market mix won't make any material difference to sales
forecasts - even if that newcomer is Violin. Instead it will mean that the
fuzzy edge of users' vendor shortlists will appear sharper - and companies
which shouldn't have been in these lists in the first place will drop out. (But
they wouldn't have been the ones who got the business anyway. There are a lot of
different specialized types of PCIe SSDs - and
just because they may
look the same on the outside - doesn't mean they compete equally for the same
apps slots.)
My guess is that Violin's new products will be most
attractive to companies which already like its rackmounts - and who were already
looking for a more complete single supplier solution around which to hang their
software.
So I anticipate that customers in the big web economy and
SSD dark matter users
will predominate early demand for these new products. And - for any server
companies which haven't yet acquired their own enterprise SSD IP - Violin (the
company) will now look more attractive too.
In a
press
release later today:- we learned that the final stimulus which nudged
Violin tipping into the PCIe SSD market may have been:- hints, inducements
and probably pressure from investor, memory supplier and wannabe-bigger-in-SSD
partner - Toshiba.
See
also:- my classic article -
if Fusion-io sells
more - does that mean Violin will sell less? | |
| . |
|
|
| |
|
