 |
| . |
|
see
also:-
"router"
- editor mentions on StorageSearch.com |
| . |
the need to
interconnect different storage interface devices
by Zsolt Kerekes,
editor - January 13, 2011
Back in the old days of
storage history
there were even more interfaces than there are today - because there were less
industry standards and more
proprietary ones.
So interconnecting systems was complicated and the
storage router market was fragmented as specialist firms operated in different
market niches and rarely competed head to head.
It's still complicated
today - but mostly network
storage architecture hasn't changed much in the past 10 years - since the
end of the dotcom boom which ensured that every organization had to own ethernet
compatible storage - even if internally its used a mish mash of disparate
technologies.
What has changed instead are the speeds and differing
roles of fibre-channel SANs,
GbE NAS, and
iSCSI and the
introduction of a new storage network standard called
InfiniBand which is
the only completely new transport which appeared in the decade 2000 to 2010.
Another thing which has changed in storage infrastructure is the DAS
connections. Good old parallel
SCSI has been superceded by
SATA and
SAS.
Hard drives still spin at
exactly the
same
RPM speeds as they did 10 years ago, But their capacities have got bigger.
One
thing which has changed a lot is the way
backups are done.
Tape libraries - which
dominated network backup thinking in the 1990s - have mostly given way to
disk backup. The transition
to VTLs is documented in another
article.
SSDs haven't changed the storage router market much - but
they will.
One of the earliest volume uses of embedded SSD
accelerators (outside the military
market) was the use of 3.5"
SSDs inside storage routers in 2002.
Looking ahead to the future
- I described the storage datacenter architecture circa 2016 in my article -
this way to the
Petabyte SSD.
As we progress to that point (from 2011) storage
architectures could get very messy as users leverage point products such as
PCIe SSDs and
SSD ASAPs to get
short term apps acceleration advantages while squeezing in and around the
systems they already own.
I'll be reporting on progress in that area as
usual in storage news.
A
good way to find companies currently in the storage market is to use the search
box below. |
|
| |
| . |
| this way to the Petabyte
SSD |
In 2016 there will be
just 3 types of
SSD in the datacenter.
One
of them doesn't exist yet - the bulk storage SSD.
It will replace the
last remaining strongholds of
hard drives in the
datacenter due to its unique combination of characteristics, low running costs
and operational advantages. |
 |
... |
The new model of the
datacenter - how we get from here to there - and the technical problems which
will need to be solved - are just some of the ideas explored in this
visionary article. | | | |
| ... |
| |
Notes from
SSD market
history
The product shown below, from
Imperial Technology
(which is no longer in business) is an example of a
rackmount SSD
accelerated SAN router which was
featured here on StorageSearch.com in
June 2003. |
| . |
|
| | |
| . |
| will auto
tiering SSDs change from hype to market spike? |
What were the main developments in the
SSD market last month?
You can get a detailed idea of the most
important product and business announcements in the
SSD news page. These
stories are in turn filtered and condensed down even more so you can always
see the past 6
months summary in the SSD Buyers Guide.
Most of those SSD stories
are about evolutionary changes - which are in line with what you'd
expect if you've been following
the market for some time. But once every 3 years or so - something
unexpected happens.
In August 2011 - the unexpected - was that
auto tiering SSDs / SSD
ASAPs - a subject which has had its own directory here on the mouse site
for 2 years - was the fastest climbing topic in the
top 50 SSD
articles (up 34 places to #18)!
If I look back over
storage history
- these big spikes in long established subjects (and in
SSD company searches
too) have been reliable indicators that a part of the market is moving into a
distinctly new phase. Although the historic pattern is it can take another 2
to 4 years or so before these trends are confirmed by publicly available
revenue data (via IPOs, acquisitions and quarterly results).
It's
interesting to note that the whole topic of solid state storage was itself
#18 back in the 1st quarter of 2001. It was the jump to #4 a
year later in 2002 (also reported in our news pages at the time) which alerted
me that the SSD market would not simply go on as it had done in the decades
before as a niche market - and led me to start work on my 1st (of many) SSD
market penetration models - which I discussed with industry leaders and
published in 2003.
The rest - as they say - is
SSD history.
| | |
| . |
| 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 | | | | |
|
