HDD vs SSD Storage

How do solid-state drives (SSDs) stack up to traditional hard-disk drives? Like many things in life, it depends on money and what you need. SSDs deliver greater performance than HDDs, especially faster, more predictable read times. SSD performance will only increase as vendors deploy non-volatile memory express (NVMe), a protocol designed to unleash their full potential. Familiar protocols like SCSI, SATA, and Fibre Channel were engineered for HDDs and constrain the capabilities of SSDs.

SSDs deliver higher IOPS, increased throughput, and reduced latency over HDDs. When evaluating SSDs, consider the needs of your business-critical applications. Apps that benefit from greater IOPS include virtual desktop infrastructure (VDI), server virtualization, and systems that have many concurrent users. Apps that require high throughput are those that move large files and data sets, such as data analytics, video processing, and medical imagery. Applications that are sensitive to latency typically are comprised of multiple sub-applications in a stack or across nodes, such as transactional processing systems. They also include clustered databases, streaming apps, and high-performance computing solutions.

SSDs can also improve resource utilization, supporting, for example, many more virtual machines than HDDs without performance compromises. Their speed also enables functionalities like data deduplication and compression to be performed on active storage, rather than on backups and archives.

SSDs offer additional advantages over HDDs. They need meaningfully less energy to run, which decreases power costs. They also run cooler than HDDs, lessening cooling expenses. By slashing energy requirements, AFAs operate more economically, substantially reducing ownership costs. Another consideration is density; With SSDs, you can squeeze more capacity into a rack unit, conserving space.

But before investing heavily in SSDs, there are other factors you should consider. Blazing fast SSDs might eliminate one bottleneck, but they won’t mitigate other bottlenecks in the network and elsewhere. Application and data delivery are only as fast as their slowest links.

Another is cost. Although their costs are dropping, SSDs are still more expensive to buy than tried-and-true HDDs. This is why hybrid arrays have emerged, in which SSDs handle active data while HDDs economically store inactive and backup data.

Until the costs per gigabyte of flash storage aligns with HDDs, consider SSDs for storage that demands performance and HDDs for everything else. Hybrid arrays might be your best solution. However, it is now easier than ever to justify using all-flash arrays (AFAs). It is only a matter of time when data centers are all flash and long-term storage resides on SSDs. With their many advantages, SSDs can be the smart, future-proof investment.

AFAs, hybrid arrays, and HDD arrays are each optimized to meet specific needs. Evaluate what you require, benchmark your systems, and work with vendors to determine the right solution for you. An AFA may or may not make sense for you now. However, they are in your future; it’s just a matter of when.

All-Flash Storage Arrays (AFAs)

For years, the world relied on hard disk drives (HDDs) to store digital information. These electro-magnetic devices worked well and their costs per gigabyte continually decreased. However, they had inherent performance constraints because of the time they required to read or write data on spinning metal platters with magnetic coatings. Burgeoning data troves and new generations of sophisticated applications rendered their read/write times, even when measured in milliseconds, a computing and business bottleneck.


New chip-based technologies emerged that resulted in solid-state drives (SSDs) without any moving parts. They’re much faster than HDDs and provide more predictable response times for time-critical applications, but their costs were high and their storage capacities limited relative to HDDs. They were cost effective in hybrid storage arrays. In these solutions, SSDs cached active data on tier 0 while HDDs still bore the brunt of the storage load.

The costs of SSDs are inexorably decreasing while their capacities increase. Fifteen terabyte SSDs are available and larger sizes are on the horizon. SSDs are beginning to be practical for longer-term storage and for applications that are less speed-critical. As a result, what has emerged is a new storage paradigm known as the all-flash storage array.

Initially, AFAs were too costly for all but enterprise usage, but this is changing. Moreover, AFAs are beginning to leverage the performance of their SSDs. Hybrid arrays generally rely on the same protocols that were developed for HDDs, such as SCSI, SATA, and Fibre Channel. These are incapable of supporting the blistering speeds of SSDs. The industry responded with non-volatile memory express (NVMe), a faster, more efficient protocol developed specifically for flash drives. Moreover, storage system software is becoming multi-threaded so CPU cores can cost-effectively keep pace with flash speeds.

Are all-Flash storage arrays finally practical for small- and medium-sized organizations? They’re still pricey compared to traditional HDD arrays, especially those that are designed for capacity. Yet you must consider more than acquisitions costs. In our next post on All-Flash Storage, we’ll touch upon some of the considerations and use cases to determine if AFAs make sense for you.