Maybe you found the previous article a bit hypothetical and is not substantiated by facts but merely some guestimations?

To put some beef into the equation I’ll try to substantiate it with some simple calculations. Read on.

As shown in Cornell Uni’s report the expected amount of data generated will reach 1700 exabytes in 2011 with an additional 2500 in 2012. 1700 exabytes equates to 1 trillion, 700 billiard gigabytes in EU notation (say what…., look here)

So number-wise it looks like this: 1.700.000.000.000 GB

The average capacity of a disk drive in 2011 is around 1400 GB (the average of enterprise drives with high RPM of 600GB + the largest capacity wise commercially available for enterprise environments HDD of 2TB).In consumer land WD has a 6TB drive but these will not become mainstream until the end of 2011 or beginning 2012 . Maybe storage vendors will use the 3 and 4 TB versions but I do not have visibility of that currently.

1700EB / 1400GB = 1.214.285.714 disk drives are needed to store this amount of information. (Ohh, in 2012 we need 1.785.714.286 units :-))

This leads us to have a look at production capabilities and HD vendors. Currently there are two major vendors in the HDD market. Seagate (which shipped 50 million HDD in FQ3 2011) and WD shipping 49 million. (Seagate acquired HGST and WD is talking to the HDD division of Samsung) Those 4 companies combined have a production capacity of around 150 million diskdrives per quarter. This means on an annual basis a shortage of : 1.214.285.714 – 600.000.000 = 614.285.714 HDD’s
So who says the HDD business isn’t a healthy one? 🙂

OK, I agree, not everything is stored on HDD and the offload to secondary media like DVD,BlueRay,tape etc will cut a significant piece out of this pie however the instantiation of new data will primarily be done on HDD’s. Adoption of newer, larger capacity HDD is restricted for enterprise use because the access density is getting too high which equates to higher latency and lower performance which is not acceptable in these kind of environments.

This means new techniques will need to be adopted in all areas. From a performance perspective a lot can be gained with SSD’s (Solid State Drives) which have extremely good read performance but still lack somewhat in write performance as well as long term reliability. I’m sure over time this will be resolved. SSD will however not fill the capacity gap needed to accommodate the data growth.

As mentioned before my view is that this gap can and will be filled by advanced 3D optical media which provides new levels of capacity, performance, reliability and cost savings.

I’m open for constructive comments.

Cheers,
Erwin

Did you ever wonder how long this industry will rely on spinning disk? I do and I think that within 5 to 10/15 years we’ve reached the end of the abilities of disks to keep up with demand and data growth ratios. A report from Andrey V Makarenko of Cornell University estimates that around 1700 Exabytes (yes EXA-bytes) will be generated in 2011 alone with growth rates to over 2500 EXAbytes next year.

With new technologies invented and implemented in science, space exploration, health care and last but not least consumer electronics this growth ratio will increase exponentially. Although disk drive technology has kept pretty much pace with Moore’s law you can see the advances in development of this technology is declining. Rotational speed has been steady for years and the edges of perpendicular recording have almost been reached. This means that within the foreseeable future there will be a flipping point were demand will outgrow the capacity. Even if production facilities would be increased to keep up with demand, do we as society want to have these massive infrastructures which are very expensive to build and maintain as well as having a huge burden on our environment. So were does this leave us, do we have to stop generating data or generate it in a far more efficient way or should we also combine this with aggressive data life cycle management. I wrote an article earlier in this blog which shows how this could be achieved and it doesn’t take a scientist to understand it.
To go back to the subject there are talks that SSD will take over a significant amount of magnetic based drives and maybe it is so however it still lacks on reliability in one form or another. I’m sure this will be resolved in the not so distant future however will this technology be as cost effective as spinning disks have been in the last decades. I think this will take a significant amount of time to reach that point. So where do we go from here? It is my take that in addition to the uptake of SSD based drives significant advances will be made in 3D optical storage. This will not only allow for massive increase in capacity per cubic inch but also a reduction in cost, energy as well as a massive increase in performance.
Advancements in laser technology and photonic behavior as well as optical media will clear the pathway of adoption into data-centers the moment this will become commercially attractive.

There are numerous scientific studies as well as commercial entities working on this type of technology and due to market demand add significant pressure on the development of it. Check out this wikipedia article on 3D optical storage to get some more information around the technicalities.

Let me know your opinion.

Regards,
Erwin van Londen