If you own a Tesla and you want to accelerate faster, corner better or – most recently, enable automated parallel parking, you can simply download a new version of the Tesla software to your car. While the hardware remains the same, your car is in many respects like a new vehicle.
The continuous improvement of the Model S over time illustrates what I think of as the “Tesla Effect”. In the same way that Tesla can extend the capabilities and performance of its current vehicles, next generation datacenter technologies like hyperconvergence are transforming how organizations buy and use storage solutions in much the same way.
The Problem with 3-Tier Infrastructure
When it comes to conventional storage infrastructure (centralized storage + storage fabric + servers), there is a lot of guesswork involved. For example, when a business purchases a storage area network (SAN), they typically try to predict the workloads they will need 3 – 5 years down the road, and then purchase an array with enough headroom to expand storage capacity to hopefully meet those requirements.
However, if the SAN-purchaser guesses wrong and under-buys, their organization faces a massive forklift upgrade that’s very expensive, complex and time-consuming. In fact, Wikibon estimates that the cost just to migrate to a new array is 54% of the cost of a new array. As a result, businesses are more inclined to buy SANs with “room to grow”. But this extra capacity requires a larger initial investment which then reduces the overall return on investment (ROI). And as shown in Table 1, this excess capacity starts depreciating on the first day it is installed.
Table 1: Depreciation Expense from Purchasing Excess Capacity Up-Front
The excess capacity also requires more rack space, power and cooling even as it sits idle. Not to mention the fact that the initially unused capacity becomes increasingly out of date when compared with new equipment once it is finally needed. This practice of purchasing storage leaves businesses vulnerable to inferior performance, less capabilities and features, and more rack space, power and cooling expenses.
Hefty upfront costs, capacity uncertainty, and financial penalties are not the only challenges associated with SANs. As organizations increasingly virtualize their datacenters, the physical limitations of traditional solutions are more apparent. SANs were built for physical, not virtual infrastructures. And while higher-performing servers can help optimize virtualization capabilities, the arrays themselves remain constrained by the transport latency between the storage and compute, which does not evolve as quickly as server technology.
The Benefits of Hyperconverged Infrastructures
In contrast to 3-tier offerings, hyperconverged infrastructure (HCI) solutions were built from the ground up to host a virtualized datacenter (“Hyper” in hyperconverged refers to “hypervisor”, not to “ultra”).
In order to end the frustrating cycle of over-buying storage capacity only to find it outdated soon after, HCI uses a software-centric architecture to tightly integrate compute, storage, networking and virtualization resources into a single offering, from a single vendor. This unity helps alleviate manufacturer finger pointing when troubleshooting and other challenges associated with virtualizing datacenters.
Through the lens of the Tesla Effect, hyperconvergence allows businesses to grow their environments seamlessly and scale out as needed – even one node at a time. The latest technology in terms of CPU, memory, disk and flash can be added to existing storage nodes at the same time new ones are added. The higher workload densities, increased capacity and updated capabilities and features help optimize the investment in the original nodes. This both enhances the ROI while reducing the risk of over-buying.
These software-redefined enhancements make HCI significantly different—and superior—to proprietary SANs. For a more in-depth analysis of hyperconvergence solutions vs. traditional infrastructure, check out the IDC report here.
Source: Wikibon, “The Cost of Storage Array Migration in 2014”http://wikibon.org/wiki/v/The_Cost_of_Storage_Array_Migration_in_2014