Storage Software Vs. Hardware: What's More Important?

A common theme from storage software vendors over the last few years has been that storage hardware is becoming commoditized and that it is the software that really matters, not the hardware. It is a fair point. Entire companies have been built on the value that the software brings to off-the-shelf hardware. However, a recent trend has been for storage hardware companies to claim that it is the software that is becoming commoditized, not the hardware.

1. What Is Storage Software?

Storage software is the software that makes a bunch of disk drives act like a system. At its most basic level the storage software provides volume management, RAID protection, and LUN masking. Vendors advanced these capabilities significantly over the years and added features like snapshots, thin provisioning, replication, and clones. Most recently they have been adding some form of SSD automation via tiering or caching.

2. How Can Storage Software Become A Commodity?

Storage software can become a commodity by becoming so commonplace that it is included automatically with the operating system, file system, or hypervisor. Look at the capabilities of the open storage software products like ZFS, GPFS, GFS, MogileFS, Lustre, Nexenta, Datacore, Glustre, and Caringo (to name a few) and compare them with some the capabilities from turnkey storage vendors and you will be surprised at the capabilities of these products.

At first glance you may think that this bolsters the argument that software solutions will make the storage hardware a commodity, until you realize that many of the above software solutions are either open source or very aggressively priced. Once something is available for free, something that will never happen to hardware, then it is by definition commoditized.

3. Does Storage Hardware Suddenly Matter?

There are three key drivers to why storage hardware suddenly matters. The first driver is being caused by flash memory. How vendors integrate flash will directly impact your experience with the system. As we discuss in our recent video "The SSD Price Problem" flash storage is not all created equally and the actual flash NAND is one small component of the overall flash solution. A more vertically integrated solution may deliver better performance and density at a better price point.

The second driver is the network. As the performance of storage systems begin to scale, the cost and complexity of the storage network become an issue. As we discuss in our article "In Open Storage The Storage Infrastructure Matters," some storage hardware vendors are pre-integrating low-cost networking options into their storage offerings so that the cost of the storage network does not become greater than the storage itself.

Finally there is reliability. We repeatedly see evidence in our labs and in talking with customers that certain vendors deliver higher levels of reliability than others. They accomplish these higher levels of reliability not only by better testing but also better design. As we discuss in our article "The Requirements for Building Reliable Storage Systems," better storage hardware designs can reduce vibration and increase air flow so that drives run cooler. Vibration and heat tend to be the top killers of hard drives.

The end result is that both storage hardware and software are being commoditized at different levels. There are plenty of systems available that are really software leveraging off-the-shelf hardware, there are systems with hardware that can leverage a variety of software, and there are systems that have commoditized everything (hardware and software).

What makes the most sense for your data center depends largely on how much time and motivation you have. The more commoditized approach you go, the more assembly that is required. It will save you money, but may cost you time.