I have been working for technology companies for 33 years now, so I don't know why I'm always surprised at the technology myths that proliferate. For example, there is a popular notion running around that Solid State Drives (SSDs) will replace Hard Disk Drives (HDDs) as the dominant storage media. So, which will win? Let me give you my answer upfront before I take you through my arguments: both win, and the market size for both continues to grow.

As I offer up this data and this perspective, I'll repeat some advice I received early in my career. A mentor once told me, when searching for the truth in business and technology "look to the economics" (maybe my version of "go to the mattresses" for you "Godfather" fans).

Here is what I read and hear on a regular basis regarding the battle of HDDs and SSDs:

• SSDs run circles around HDDs for performance
• SSDs will soon replace HDDs
• The improving density of SSDs will collapse the current cost premium to HDDs

Sound familiar? Well, as with most claims of this ilk, there are some elements of truth to them but each of these statements goes too far when viewed in light of some data.

Performance
Yes, it's true that SSDs are fundamentally faster than HDDs. This is particularly true of random I/O data reading (as with databases). With large block sequential data (i.e., rich media like video), however, this difference tends to be very small.

Replacing HDD?
Here's a claim where the data just doesn't add up. While the attractiveness of the SSD technology would lead one to believe this, the economics really don't hold up. I should probably point more specifically to NAND flash here (the "solid state" in SSDs) because another solid state technology might actually achieve this, but that appears to be years and tens of billions of dollars away.

Let's talk for a minute about the world's demand for storage. Last year approximately 2500 exabytes of data was created and/or replicated. And...this is doubling about every two years. This needs to be serviced largely by HDDs and SSDs. Last year, the NAND flash industry produced somewhere between 30 and 40 exabytes of storage; with somewhere around 3.5 exabytes finding its way into SSDs (the balance in phones, tablets, cameras, etc.). What is that, 1.4% of our total storage need? But production is ramping up... at a capital cost of about $1.5 billion per Exabyte (semiconductor fabs are expensive)! So, from an available supply perspective, SSDs replacing HDDs seems implausible.

Improving Technology Makes SSDs Cheaper
Agree. The NAND flash technology point is at 21nm line widths with plans to move to 19, then 16 nm. Storage density is further improving with the use of multi-level cell (MLC) capabilities vs single-level cell (SLC). This is bringing down the cost of solid state storage in much the same way the areal density increases seen in HDDs brought down the cost of hard drive storage.

Notice how I said "brought" down (i.e., past tense)? Because a real density growth in the hard drive industry has slowed to a crawl, the rapid erosion of cost/Gb has also slowed to a crawl. Now, the HDD industry needs to move to its next technology (HAMR?) to continue to take cost out and HAMR is a number of years away. HAMR will require significant capital investment by the HDD companies. Significant capital investment will be required anyway to keep up with storage demand (even more so with slowing areal density growth). This all spells out a flattening of HDD costs for the foreseeable future. Some would speculate that a renewed interest in improving the utilization of HDD capacity is an artifact of these economics.

Here's what's preventing the complete collapse of the price difference between the two technologies. The NAND flash suppliers have a similar problem as the HDD manufacturers... the implications of shrinking technology geometries. As the line widths shrink, the ability of flash to sustain multiple write-erase cycles declines. To make up for this deficiency, sophisticated error-correction algorithms and "brute force" overprovisioning (to allow some cells to wear out) are being used. This and the above mentioned semiconductor fab costs tend to mitigate the progress SSDs are making in closing the cost gap to HDDs.

Having made my arguments that SSDs won't take over the world, I have to say that IT solutions need this technology. I think you can see that SSDs aren't the answer to all our storage needs, but they allow us to address a crying storage requirement. At a high level, storage is called on to produce two key deliverables:

• Make data available to an application or user in an appropriate timeframe (i.e., performance) and in today's environment this need is growing.
• Store data reliably (i.e., capacity) and in today's environment this need is growing

By and large, to date, systems with hard drives have been architected to deliver both of these capabilities. It's hard to argue that hard drives haven't done a good job of delivering affordable capacity. But to deliver against the performance requirements of IT solutions, hard drives:

• Have been developed with higher speeds, but arguably little progress has been made in the last ten years
• Have been "short stroked" (a technique limiting the stroke of the actuator to improve performance)
• Have been grouped together to allow striping of data across a large number of drives to aggregate their performance.

With each of these approaches the user suffers from higher power requirements, and with the last two approaches their system has been overprovisioned (leaving stranded capacity) to deliver performance. This all adds up to significant system cost that can be avoided with new storage architectures.

Here's where SSDs come in. SSDs are proving to be a technology answer to the new generation of storage needs, both the growing performance and the growing capacity requirements. Here's the simple, logical way to think about SSDs and HDDs and their role in storage solutions. Use the right tool for the job. That is, take advantage of SSDs for performance (particularly small block, random I/O) and HDDs for capacity.

You might challenge me now and ask, "Does adding SSDs (Flash) to IT solutions make economic sense?" SSDs are expensive, but, used appropriately, SSDs can also minimize the number of HDDs required in a given solution. The secret is in optimizing the use of both, that is, avoid overprovisioning of both. Thin provisioning of capacity has become popular as a cost saver. Similarly, thin provisioning of performance is a similar cost saver. (This is a benefit of virtualized caching or tiering capabilities of newer storage solutions.)

I'll close with a few proof points. Look to the latest economically sensible storage solutions that are answering today's performance and capacity calls. The vast majority of affordable "Ultrabooks" incorporate both flash and hard drive technology, as does Apple's latest "Fusion" drive.