March 12, 2009 - by
Zsolt Kerekes,
editor
StorageSearch.com |
I'm often asked this
question...
"What do you think is going to be the next big
issue in the storage
market?"...
..."Something that's similar in market
impact to
SSDs - but which might only
start to take off after this recession?"
Yikes! - Deep breath. OK
- this is where I say - that's a very good question.
I do find that
trying to find (or invent) plausible answers to such apparently simple
questions is a challenge.
I should know the answer. I spend nearly
all my time thinking about the storage market and discussing it with people
who have the ability to change their own part of it.
I published a 7
year storage market forecast
4 years ago so I thought
I'd dust the cobwebs off the scrolls and see how that prognostication is
holding up today. |
The nature of such
long range
predictions is that most people don't know what issues they will be
grappling with the
day after tomorrow - or even if they will still have a job. So they only
get picked up by a few lonely visionaries - who like editors - have nothing
better to do than stare in their crystal balls - while someone else makes sure
that the cash register is still
ringing (and
connected).
When I enthusiastically start to expound on "Storage
Reliability" with normal people - I get the same reaction as I did when I
was talking about
SSDs in 1998,
or RISC processors
back in 1988 or microprocessors back in 1977. Their eyes glaze over - and they
say politely - "I can't understand why anyone would be interested in this."
Especially
- reliability!
"Yes, yes" they say (trying to shut me up) "I agree
it's a good thing. Much much better than unreliability. Now can we change the
subject... What more is there to say?"
I wouldn't be surprised if
most of you too - thought the same way.
After all - there are 3 more
years to go till 2012. And the
recession and
SSDs are going to dominate the
storage news pages
during most of that time. So there's no need to start worrying about reliability
- just yet. Maybe.
There are many things I could say about
Storage Reliability
- and I have collected together a lot of articles and news stories for those
who are interested.
And for the majority of you (who have better things
to be worrying about right now) I'm sure that when the time is right for you -
you'll come back to this subject.
If your own eyes are still unglazedly
focused in this direction...
One way of thinking about reliability
- is that it works like compound interest. A double digit or triple digit
percentage difference sustained over many years soon starts to mount up to a
substantial saving in resources. That's also why I said it's
green.
Although unlike
quality
- it's not free.
Post Recession Thinking -
2012 to
2013?
One
effect of the recession is that users - looking back with the benefit of
hindsight - will realize that a lot of resources (today) got wasted - and a
lot of data was
trashed - simply because of doing things the way they have always been done
- without questioning the thinking or assumptions behind any of it.
A
whole load of convenient incremental steps can take you to a place that's a
long way from a rational destination. When the spending tap closes shut - every
drip, drip starts to look more interesting and gets scrutinized more intensely.
Happy days will be
here again - but
wiser ones too. ...SSD
Reliability articles & news |
|
Later articles with a forward
looking theme include:-
SSD efficiency
Enterprise SSD market silos
adaptive R/W &
DSP in SSDs
Can you
trust SSD market data?
Where are we now
with SSD software?
How will hard drives
fare in an SSD world?
meet Ken - and the
enterprise SSD software event horizon |
. |
|
. |
| |
... |
|
SSD Backup |
The new Paranoid S3B (populated
by bulk storage archive SSDs) only dispensed lukewarm coffee to
attendant data archive admins. "Maybe we should add a heater?"
said Megabyte. | |
. |
|
. |
|
. |
|
. |
|
. |
|
. |
this way to the Petabyte
SSD |
In 2016 there will be
just 7 types of
SSD in the datacenter.
One
of them barely exists 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. | | | | |