What Matters in Storage

Posted by

The past few decades have brought a series of innovations to the storage industry, such as tiering, snapshots, deduplication, replication, iSCSI, SSD, NVMe, and a few others, but the storage service itself hasn’t changed. This might sound shocking; let me explain by first, establishing a definition of a storage service.

Storage service is the combined delivery of three interdependent services: Capacity, performance (defined by throughput, IOPS and latency), and availability or up-time. The storage service hasn’t changed; the applications’ demand for storage services has changed only in how much, but what constitutes a storage service has stayed the same. Though this definition of storage services omits most of the innovations we have touted over the past decades, it doesn’t imply that the innovations don’t matter when evaluating solutions. So, what does drive the adoption of innovation? There is only one answer: ‘cost’.

Cost of the storage service required is what has been driving storage innovation. Here are some examples:

  • Deduplication reduces the amount of actual data being stored, thus reducing capacity required to support application’s needs. If storage capacity costs $1 and deduplication reduces the need by 50%, then even if the cost of deduplication is $0.20, the overall savings of $0.30 would justify adoption. If there were no cost advantages to deduplication, would it matter whether the system had it or not?
  • Tiering is the ability to move data across media performance tiers allowing for the data to consume storage that is aligned with its performance needs. Tiering data to a lower performant-less expensive tier, where storage costs 3X less, would result in significant cost efficiencies.
  • iSCSI as an access protocol has replaced FC in many data centers. Though initially the performance of iSCSI was viewed as lower than FC, the cost of deploying an iSCSI network was significantly less expensive. Many applications were fine with iSCSI performance and the adoption of this protocol skyrocketed with extensive cost savings.
  • MLC, TLC, and QLC NAND deliver higher density with each iteration. The adoption of higher density NAND offers a lower per GB cost in capacity. Since NAND delivers better performance per GB than HDD, the cost savings are amplified with higher density.

There are many other examples where innovations in storage were targeting improvements in performance, capacity density and utilization, up-time, and access to drive down the overall cost of storage services. Evaluating these features as they affect the core storage services per unit of cost will help address the need to align total cost of ownership with business value.


Leave a Reply to André Cancel reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.