 |
leading the way to the
new storage frontier | |
... |
..... |
|
SSD history SSD endurance the Top SSD Companies will SSDs end
bottlenecks? consolidation
in enterprise flash arrays - forecast and analysis |
|
. |
|
"As I write this -
Diablo is in the unenviable position of being at the center of a new server
based acceleration technology which is attracting huge interest from those who
can see opportunities in the latency zone which lies between PCIe SSDs and DRAM
(the good thing) while at the same time being prevented from shipping any
further products (the bad thing) pending the outcome of legal proceedings (or a
settlement) with Netlist..." |
Zsolt Kerekes,
- editor StorageSearch.com
- in the Top SSD
Companies - 2014 Q4 | | |
|
. |
|
 |
|
. |
|
those who tweet loudest |
Editor:-
February 18, 2015 - Re the visibility seeking marketing activities of
enterprise storage companies - I found much to agree with in a recent blog -
Hybrid
Storage Array Industry Social Landscape - by Don Jennings,
Senior VP - Lois Paul & Partners
(a storage industry proven
PR).
Among
other things Don says "not many of the storage companies in our analysis
have clear content strategies to provide information and value to their
followers. This is especially true on YouTube, where these companies are rarely
posting anything other than product-usage videos. We also dont see any of them
engaging with industry media and influencers..."
The essential
output from Don's article is that he ranks 5 companies in the
hybrid storage array
market - based on the noise level and following they have achieved on
social media.
The companies (in alphabetic order) are:-
.
Setting aside for the moment any reservations you might have about the validity
of using social media as a significant enough comparative measure for
enterprise companies - Don comes up with some interesting statistics for each
company about the level of its followers, tweets etc.
And by that
measure Nimble comes out top of his list. ...read
the article
Editor's comments:- As with any measurement
- you have to ask questions like
- why has this method been chosen? Is it simply convenience?
- And how valid does such a ranking carry over into other interpretations?
etc - such as future business outcomes.
In this case - the agenda is
clear enough - Don's company LPP is in the media business - and some companies
are clearly more noisy (and better understood) than others in "editorial
like" contexts.
If your company isn't doing well enough in the
social media blare - then maybe you should change your agency.
A
devil's advocate counter argument to that might be to say that a single well
designed ad can take a company positioning message to more targeted people than
all the people who see a vendor's tweets and blogs in a year. And every day I
see companies in this industry who lack the confidence to invest in themselves
in an advertising context - preferring instead to cast their fortunes on the
winds of the media lottery newswires.
And another counter argument is
that not all important relationships and engagements are as visible as you
might think on social media. Why should they be - if there are pre-existing or
better ways in which the parties in the same mutual interest segment can
communicate?
For example - I've been talking to Don Jennings regularly
about his storage industry customers since June 2003 - but (at the time of
writing this) we aren't 1st level contacts on linkedin.
And a lot of
the people I talk to about weighty matters in the SSD market would be horrified
by the idea of others knowing what they're thinking about. I'm not saying
that one private communication is worth ten tweets - but if it's about about a
new business plan - or the order from your biggest customer - it can be worth
much more.
On the other hand. Social media may be the only independent
(non financial and non technical) way you can rank some of the companies
you're interested in. As only 1 of the 5 companies above - for example - has got
high enough in the search noise level to appear in the
Top SSD Companies.
| | |
|
. |
|
 |
|
. |
|
|
|
. |
|
I was talking to an end user whose organization has spent hundreds of
millions of dollars on EMC storage. They'd love to decouple themselves and
benefit from modern lower cost flash.
But the flash marketers in
startups aren't doing those kinds of conversations.
For many of
them a single customer like that is bigger than their whole business plan.
|
"compared
to EMC" - the unreal positioning of AFA startups | | |
|
.
.
.
.
.
.
.
. |
|
|
|
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
. |
|
It's reasonable
to ask why isn't there already a better availability of industry wide useful
enterprise software which can replace and abstract away the mish mash of
different chaotic patches, tools and feature sets which arise in the systems
products of SSD box makers? |
towards
enterprise flash array consolidation | | |
|
.
.
.
.
.
.
. |
|
 |
| |
|
For more pages like this see
storage history
month by month |
... |
Avago acquires Emulex for
$600 million
Editor:- February 25, 2015 - In 2014 - Avago Technologies - which until then
had not seemed much involved in enterprise storage - suddenly got religion.
As a heavyweight interface chip and IP maker in other markets Avago
must have asked themselves - what are the key interfaces we need to be the #1
enterprise storage connect company? - especially
as more
enterprise storage becomes solid state.
And
that's the way to interpret the acquisitions (last year) of
LSI and
PLX followed now (as
announced
today) by the acquisition of
Emulex - for
approximately $606 million.
Netlist raises $10 million through share offering
Editor:-
February 24, 2015 - Netlist
today
announced
it has closed its previously-announced underwritten public offering of 8,846,154
common shares at a price to the public of $1.30 per share. Netlist estimates
net proceeds from the offering to be approximately $10.4 million, after
deducting underwriting discounts and commissions and estimated offering
expenses. Netlist intends to use the proceeds from the offering for general
corporate purposes.
Diablo updates status of UlltraDIMM legal sanctions
Editor:-
February 24, 2015 - If - like me - you've been following with interest the
development of true SSD acceleration technologies packaged in RAM DIMMs (aka
memory channel
SSDs and similar names) then you may have been wondering - what's the
current state of the play in the
Netlist versus
Diablo and
SanDisk patent and
implied rights to IP legal wrangle?
The last furious clash of
legally related press releases - from both sides - in mid January - ended with a
lot of smoke in the air - and dire expectations regarding body count. In
particular the impression was that - until the next court session on these
matters - further shipments of SanDisk's ULLtraDIMM SSDs would be suspended.
This
is an update sent to me yesterday from a spokesperson communicating the Diablo
side of things. So "we" and "our" in the text below means
from the perspective of "Diablo".
re Preliminary
Injunction - Diablo says
- SanDisk has been granted a stay on their preliminary injunction, meaning
that they can ship their inventory to Lenovo, Supermicro, and Huawei.
- The preliminary injunction on Diablo is still in effect while we await the
standard appeal process.
- It continues to be our belief that the standard appeal process will find in
our favor.
At the center of the dispute is the idea that our technologies
compete. Our technologies do not compete. There is a long list of reasons why
they don't. Here are some of them:
- The Netlist NVvault is memory. The OS and applications see it and treat it
as DRAM, which is why no OS drivers are necessary. Ours is storage. Ours is
seen by the OS, hypervisors and applications as a block storage device and this
is why MCS does require OS drivers.
- They are used differently. For example, you typically would not put a
whole database on a DRAM NV-DIMM but you would on an MCS-based device.
- A DRAM DIMM can be used in place of DRAM, an MCS-based device cannot. An
MCS-based device, because it is storage, requires separate DRAM in the system
for execution. DRAM based devices are required to make the server run and are
complimentary to MCS-based devices.
- A DRAM NV-DIMM cannot be removed from the system and replaced with an
MCS-based device and be expected to perform the same function.
- The NVvault product is an 8GB device because it is a memory device. Since
ours does not use DRAM and instead interfaces directly to flash, it is capable
of being hundreds of gigabytes in capacity.
- JEDEC has defined a DRAM-based
NV-DIMM (NVDIMM-N) as a completely different category from an MCS-based device
(NVDIMM-F) because they operate differently and service different applications
in very different ways. There are several other companies building NVDIMM-N
devices including Netlist,
Viking and
others, while
Diablo is the only company we know of that is building an NVDIMM-F device.
- Simply because they both fit into the same slot and use a similar interface
does not mean that they compete. Most PCIe cards serve completely different
functions and do not compete, even though they use the same physical interface
(examples are graphics, audio, networking, and storage cards).
Editor's comments:- I think it's important for the SSD
industry to know whether it can count on seeing a competitive market for memory
channel SSDs being developed. For that to happen it is essential for Diablo to
establish in the courts or by agreement as soon as possible that the roadmap
for its kind of technology has a future.
If this doesn't happen quickly
- and if the whole issue is left unresolved for another year - then the window
of opportunity for this class of enterprise SSD may close. Because - as far as
I know - Netlist doesn't have a Diablo like product in a similar state of market
readiness.
So if Netlist were to succeed in preventing Diablo's
product roadmap - there isn't a similar product which architects could fall back
to. And even if Netlist chose to pursue that kind of product opportunity - which
it can't do on its own the SSD market isn't going to wait idly by for another
2 years waiting for that to happen.
Other ways of adding applications
intelligence into PCIe
SSDs - and other alternatives to RAM cached to flash are already in
development. And the software market has to judge - which new markets are most
likely to return value on their developer investment.
Sanity check
Just
to remind you - the bullet points above - came from Diablo and whether you agree
or disagree with them or not (or quibble - as for example in - there is an
industry of RAM resident databases - albeit they aren't the "typical"
HDD architected databases which are now running in flash SSDs) the reason so
many lawyers are involved now is more to do with the fact that 2 companies
(Netlist and Diablo) have a different recollection of what they once agreed in
a past collaborative project and they disagree on what rights that past
agreement confers on what they're doing now.
If I get more updates
I'll let you know.
The key things for now are:-
- if you've got a design which uses 1st generation UlltraDIMM style memory
channel SSDs - then you can still get products to fill those slots.
- But - if you've been planning around the preannounced 2nd generation
products - your projects are probably on hold.
"the most reliable 2.5 inch MLC SATA III SSD"
paves way to new budget military SSD - from Cactus
Editor:-
February 23, 2015 - Cactus
Technologies today
announced
the release of a new military 2.5" SATA SSD - the
230S
PRO series - a
military
adapted variation of the company's proven
230S
commercial grade family which Cactus describes as "the most reliable
MLC based 2.5" SATA III SSD on the market."
Describing
application roles
Joseph
Chang, VP of Engineering said - "It meets the price budget for
applications where intense writing or extreme temperatures are not prevalent."
Features
include:-
- hardware AES256 Encryption
- Jumper Triggered Write Protect
- NSA 9-12 or Quick Erase (can eliminate 512GB of data in <15 seconds)
- 64GB to 640GB MLC capacities
- Fixed
BOM
- Altitude spec of 100,000 feet
- 3,000G Shock; 20G Vibration
- Powerful Industrial ECC and Defect Management
Nimble video discusses 5 9's in 5,000 systems
Editor:-
February 21, 2015 - Nimble
Storage recently disclosed (in a
sponsored video fronted
by ESG) that its
customer deployed rackmount storage systems are achieving better than
5
9's uptime - 99.999%
availability.
This
has been attained in a field population of 5,000 arrays representing 1,750
years of system run time thanks to a combination of factors including the crowd
sourced intelligence of its
InfoSight
management system which can alert users to potential down time events so they
can take evasive action before bad things happen.
Editor's
comments:- While useful in telling us how many systems Nimble has sold it's
less useful as an indicator of availability given that the average run time
across the population is about 4 months.
It would be more impressive
if they could repeat the disclosure in a few years time and selectively extract
the up-time of systems over different run times, upto 1 year, 1 to 2 years etc.
If indeed Nimble is still in a position to do so, and if it would
still meaningful given the
consolidation
in hardware and software which lies ahead for the enterprise SSD market may
mean that vendors will be using the same hardware.
Waitan launches secure self destructible SSDs for drone and other
hostile military zone applications
Editor:-
February 19, 2015 - It's rare for me to hear about a new company in the
military SSD market (I
thought I knew them all already) - but an exception to that is Waitan which this week
launched a 2.5" SATA SSD with 4TB capacity with special security options
to protect and purge
data if the SSD gets into the wrong hands - the
StellaHunter.
"We
believe the remote controlled secure erase and self-destruction functions are
highly valuable for UAV, drone, and other remote controlled and unmanned systems
where data on the systems' storage drives is confidential, which needs to be
destroyed from afar during accidents or emergency scenarios" said James
Zheng, Waitan's CTO.
Editor's comments:- Remotely triggered
data destruction isn't a new idea in secure SSDs - but it hasn't really taken
hold in the past due to the disruptive effect of false positives - such as when
a security perimeter has been incorrectly set up or when a pacifier signal is
lost for a short time for innocent reasons.
For those reasons
Waitan's StellaHunter is triggered by 2 or more preset conditions. Users can
also choose whether the SSD should be reusable after the secure erase or whether
the SSD should have a destructive erase.
FalconStor shows why it has taken so many years to launch an
SSDcentric next software thing
Editor:-
February 19, 2015 - You might think there are enough SDS companies already -
but SSDcentric data architectures are pulling system solutions in
different
directions - so until the dust settles and the landscape looks clearer -
there are plenty of gaps for new companies to enter the market.
The
most significant this week was FalconStor - who
announced
a new SSDcentric storage pool redeployment and management platform called
FreeStor - which the
company says works across legacy, modern and virtual environments.
FalconStor
says - "The heart of FreeStor is the Intelligent Abstraction layer. It's a
virtual Rosetta Stone that allows data - in all its forms - to migrate to,
from and across all platforms, be it physical or virtual."
They've posted a good
video which describes it all.
FalconStor's natural partners are
enterprise SSD systems vendors and integrators who have good products but who
don't have a complete (user environmentally rounded) software stack.
Editor's
comments:- For 4 years FalconStor gave me the impression of a storage
software company which didn't know what it wa going to do with the SSD market -
despite having a base of thousands of customers in the enterprise storage
software market.
FalconStor's delay can now be explained. They were
studying what needed to be done - and it took a lot of work.
If you
want to understand who else is offering a product concept which is similar in
vision to FalconStor's FreeStor - I'd say
Primary Data.
Although due to a difference in ultimate scaling aspirations and markets - I
would say that FalconStor's product is lower end and currently more accessible.
Part of the reason being that FalconStor already has a customer base for pre SSD
era software - which they are hoping to convert incrementally.
$34 million funded SDS company Springpath emerges from stealth
Editor:-
February 18, 2015 - Springpath
emerged from stealth with these related
announcements.
A
server based data platform
priced from $4,000 per server per year.
A distribution agreement with
Tech Data who will offer Springpath's
software preloaded onto servers.
$34 million
funding from investors
Sequoia Capital, New Enterprise Associates (NEA), and Redpoint Ventures
Seagate and Micron collaborate on enterprise
Editor:-
February 12, 2015 - Micron
and Seagate
today
announced
a strategic multi year agreement which among other things will secure for
Seagate a supply of nand flash for the
SAS SSD market while
also providing for Micron a framework of SSD controller IP and designs with
which it can populate gaps in its own enterprise SSD range.
Editor's
comments:- Although modern
adaptive DSP
controller IP can work with any type of
flash - there are
applications in cloud
and storage arrays in which simpler controller designs - which integrate user
based code (to leverage awareness of the state of the whole array) can
provide cheaper
systems. Such SSDs can be made even more reliable - when they can leverage
knowledge about a particular trusted source of flash.
For example in
April 2012 -
SMART Storage (now
part of SanDisk)
revealed it had figured out a way to get 5x more endurance from consumer
grade flash when using old-style non-adaptive
SandForce controllers.
The technique preconditioned R/W timing parameters in the flash memory
using intelligence gained from experience with the company's (different)
adaptive controllers.
Seagate's toughest competitors in the SAS SSD
market have been SanDisk, Toshiba,
HGST and even
Samsung - so from that
perspective - there are reasons for preferring to source flash from and trust
in Micron.
Micron hasn't dipped into the enterprise
SSD acquisition pool
to the same depth as some other
big hostages of
the SSD market. I think this was partly because Micron didn't want to be
seen as competing with its "natural" historic systems customers. But
that had left Micron with an enterprise SSD product line lacking any central
theme or controller roadmap.
In that respect - Micron's new
collaboration with Seagate - will ensure a prescence for Micron's flash in large
scale arrays and systems in very cost competitive and difficult to customize
environments - in which Micron's own SSD IP would never have been regarded as a
serious alternative.
how reliable are consumer SSDs? - new data from OCZ
Editor:-
February 12, 2015 - OCZ
recently published data about the reliability
of its past generations of consumer SSDs.
OCZ says that the SSDs
it has shipping since it has been a
Toshiba group company (and
using Toshiba's flash) are about 40x more reliable than OCZ's popular
consumer SSDs were about 4 years before. And part of the story is also changes
in controller
technology.
Editor's comments:- in this paper OCZ's measure
of reliability is - returns during warranty and confirmed defects - which are
now at 0.6% and 0.3% respectively.
Another
angle of viewing consumer SSD reliability can be seen from
data recovery data.
Intel last
year
disclosed
that of the 100,000 notebooks used under its control - it encountered the need
for 1 SSD recovery per day.
The 2 data sets - from OCZ and Intel are
incomplete - and not directly comparable due to differences in sampling
periods, warranties and model mixes. But if you assume a 1 year sampling
period - for the data recovery based data - then you end up with a failure
figure which is similar to the newest SSD data from OCZ.
See
also:- consumer
SSDs, SSD
reliability papers
Hyperstone brings enterprise-class write attenuation to industrial
USB SSD controllers
Editor:-
February 11, 2015 - When I see an assertion about 100x better flash
endurance - I smile and think back to an article
my SSD care scheme is the
best - in May 2012 - which discusses this marketing idea and some of the
unerlying technologies. So why mention it again today?
A
press
release today from Hyperstone (about
their new flash management technology for
industrial SSDs)
contains this exact phrase.
"hyMap reduces
Write Amplification
by a factor of more than 100 in fragmented usage pattern and for small file
random writes. Thereby, the reduction in effectively used write-erase-cycles
results in higher performance, longer life and shorter random access response
times. As a result, in many applications hyMap together with Hyperstone
controllers and MLC flash enables higher reliability and data retention than
other controllers using SLC. hyMap does
not require
any external DRAM or SRAM."
In the same announcement - Dr. Jan Peter
Berns, Managing Director of Hyperstone - acknowledges that while these
issues have already been discussed intensively for several years in the
enterprise market. Hyperstone's new hyMap controller technology brings this
kind of improvement into smaller, low power SSDs such as SD/MMC and USB which
don't have the same kind of budgets for DRAM and CPU power as enterprise SSDs.
OCZ and Levyx aim to shrink server-counts and DRAM in
real-time big data analytics
Editor:- February 10, 2015 - OCZ and Levyx today
announced
a technological collaboration whereby the 2 companies will develop and
validate a new type of flash as DRAM solution which will be positioned as a
competitive alternative to DRAM
rich server arrays used in many big-data real-time analytics environments.
"As
demand for immediate I/O responses in Big Data environments continues to
increase, our ultra-low latency software paired with high-performance SSDs
represent a better and more cost-effective alternative to traditional scale-out
architectures that rely heavily on DRAM-constrained systems," said Dr. Reza Sadri,
CEO and co-Founder of Levyx Inc. "We are pleased to work with OCZ on this
new usage model as our technology is specifically designed to leverage the
latest in advanced SSD technologies and we'll utilize the
Z-Drive
4500 (PCIe SSD) to
deliver the enhanced performance that helps validate our technology."
Editor's
later comments:- "retiring and retiering enterprise DRAM " was one
of the big SSD
ideas which emerged in 2015.
Northwest Logic provides FPGA support for Everspin's MRAM
Editor:-
February 9, 2015 - Northwest
Logic today
announced
controller support for Everspin's
ST-MRAM - with interoperability proven on a Xilinx Virtex-7 FPGA platform.
MRAM's core IP also supports traditional volatile DDR3 SDRAM - so the
new support for MRAM will simplifiy the design of
power fail
protected low latency
caches.
Benchmarking and Performance Resources
Editor:-
February 6, 2015 - When it comes to SSDs - an SSD which is
faster in a way
that you can economically use - such as by converting faster
latency into
competitive dollars (trading banks) or by satisfying more virtual users with
less servers (nearly everyone who owns a lot of heavily used servers) is
worth looking at.
Although
performance is
not the only thing (and often is not even the most important thing) which makes
up the cost of buying
an SSD - or the
justification
to buy it - performance has been one of those parameters which - because it
has helped to sell products - even when the
numbers were unreliable
or abused - has attracted a great deal of creative literary output in the
SSD industry. Most of it fiction. Some of it fact.
I've written a lot
of articles and emails on this theme myself. So many indeed - that I sometimes
find myself in danger of writing something new - and then getting a sense of
deja vu. IOPS?
- I've got a feeling I wrote something like this before? A quick search confirms
- yup I did. - Was it yeally that long ago? Let's just update the links so it
makes sense if someone else finds it later.
It seems I am not alone
in that respect. And a recent post on linkedin suggests a much better way of
handling that.
The idea came from Greg Schulz, Founder of
StorageIO - who has recently
curated a whole bunch of articles which he's written, edited or likes into a
single resource page - which he calls - Server
and Storage I/O Benchmarking and Performance Resources
If you
have the time - Greg has many articles on this topic which will inform and
delight you.
Mobiveil supports Spansion's HyperBus NOR flash
Editor:-
February 3, 2015 - Mobiveil
today
announced
it will provide authorized controller support for Spansion's
HyperBus
flash memories.
 HyperBus
flash chips are low capacity, low pin count, faster (5x) NOR flash (BGAs)
suited for some applications in the automotive electronics market.
Mobiveil's
HyperBus flash interface
IP (pdf) delivers upto 333MB/s using this 12-pin interface.
MSS wraps 2.5" SSDs snugly for surveillance drone flights
Editor:-
February 3, 2015 - Mountain Secure Systems
today announced
it has recently shipped an order of hot swappable 2.5" SATA SSD modules
to a leading defense contractor, which will be integrated into a pod system for
the
MQ-9
Reaper Drone - for use by the U.S. military to monitor U.S. borders and
gather video surveillance intelligence.
The removable 2.5" SATA memory devices mate with a customized
docking bay and are environmentally sealed for protection against rapid
decompression, EMI, humidity, dust, salt fog, immersion and condensation.
 The
hot
swappable device (pdf) includes mini mil-circular connectors (rated for
100,000 insertion cycles), +28VDC power, EMI filters, and captive thumb screws
for docking.
"Mountain Secure Systems is proud to be a part of this important
program," said Ken Dickson,
GM of Mountain Secure Systems. "Our ruggedized data storage solutions have
been extremely dependable for both commercial and military customers."
| |
. |
 |
. |

| |
.. |
 |
..... |
remember those good old
days? we spent all our time talking about SSDs) | |
..... |
|
|
"SSDs represent a better and more cost-effective alternative to
traditional scale-out architectures that rely heavily on DRAM-constrained
systems," said Dr. Reza Sadri, CEO and co-Founder of Levyx Inc.
OCZ
and Levyx aim to shrink server-counts and DRAM (February 10, 2015)scroll
down to see this news story |
|
.
. |
|
zero seconds? or 3 seconds? How much hold up time do you need to make a 2.5"
military SSD reliable? This article examines 2 different extremes of thought as
implemented in current products. |
hold
up capacitors in 2.5" MIL SSDs | | |
|
|
|
. |
|
 |
|
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
.
. |
|
 |
|
.
.
.
.
.
.
.
..
. |
|
|
|
. |
|
| |