A massive change in enterprise data storage is underway as more companies switch to flash-based storage arrays. A recent Gartner report projects that by 2019, 20% of traditional high-end storage arrays will be replaced by dedicated solid-state arrays.
The question is, “Why?”
For one thing, flash storage uses less capacity and physical space while performing more IOPS with lower latencies. This not only boosts productivity and reduces capital expense, it helps organizations save money with lower power consumption and the ability to consolidate more applications onto fewer machines.
As a relatively new technology, flash-based media costs more per gigabyte than traditional spinning disks. As a result, flash storage is often reserved for use only with high-performance applications, or as a precious resource for a small sub-set of application data.
Dropping prices move flash into the mainstream
Rapidly dropping prices and new flash efficiency-boosting technologies are moving flash-based enterprise data storage into the mainstream. Combine these savings with increased performance and user experience benefits, and flash storage has an impressive ROI. So where is the best place to start bringing flash into your environment?
There are three ways to deploy flash storage:
Traditional Hybrid Flash Arrays:This type of storage system combines a small amount (typically less than 10%) of flash media with hard disk drives (HDDs) using block-level tiering to deliver better performance than HDDs alone with equivalent cost.
All-Flash Arrays: Using nothing but solid-state drives (SSDs), all-flash arrays give you the best performance and lowest latency possible from a storage system. Compaction technologies like deduplication and larger-capacity SSDs can bring all-flash costs close to HDD levels.
Converged Flash Arrays: This new class of storage array features a flash-first design that pegs entire applications or data volumes to flash media but also supports HDDs for greater scalability and the ability to place some data on spinning drives (e.g., as that data ages).
How do you figure out if flash is right for you, and if it is, what sort of flash array do you need? Here’s an intro to these three types of flash arrays and how they may fit in your environment.
Traditional Hybrid Flash Arrays
Available for years, the goal of this type of system design is to get the performance of flash while using premium flash-based media sparingly so you can lower total cost and also tap in to the larger capacities available on HDDs. Most disk arrays include auto-tiering capabilities to tap into solid state drives (SSDs) as premium data tier. Hybrid flash arrays offer a price per GB that is generally more than HDD-based storage arrays, but far less than all-flash storage arrays.
The challenge with some hybrid arrays is that they aren’t appropriate for all workloads because they do not deliver predictably high service levels and low latency. If data is on flash, then life is good, but if application data sits on an HDD tier, this can result in lag time for end users. This is because hybrid arrays use different algorithms for balancing data placement across flash and HDDs. How well these algorithms work often isn’t known until the array is used in production. Also, over time, the efficiency and effectiveness of data placement may vary when application workloads change or more data is added to the storage array.
One recent variation that has been deployed for arrays that support flash caching is combining auto-tiering with flash as a cache. By adding flash as a cache, some of the challenges around auto-tiering can be mitigated. This way, data in a cache can be quickly accessed by the host even if it’s in a cold tier.
When performance matters most, nothing can beat an all-flash array built on a flash-optimized architecture. All-flash storage can deliver consistent performance without compromising resiliency, scalability, or data mobility, when combined with the right data services.
Don’t get fooled by the higher initial costs of flash. As a report from IDC put it: "Solid state is a more expensive storage medium compared with hard disk drives on a raw dollar-per-gigabyte basis ($/GB) but can be significantly more cost effective on a $/IOP basis. When solid-state storage is intelligently integrated into a system with storage optimization technologies, storage vendors lower the acquisition cost and total cost of ownership (TCO)." This lower cost is referred to as the “dollar per usable gigabyte.”
There can still be a performance bottleneck depending on the system design. This is why filling traditional dual-controller arrays designed for HDDs with flash drives is not the best idea. You will overwhelm the ability of the storage controllers to keep up with the SSDs, resulting in architectural bottlenecks that throttle performance. Newer flash arrays may vary widely, not just when it comes to performance, but also in the consistency and predictability of that performance. Multi-controller, scale-out designs are popular as they provide a greater ability to keep up with performance demand.
Converged Flash Arrays
A newer concept in the flash world, the converged flash array is a category of all-flash array that can accommodate disk media as well. By utilizing a flash-first design and associated data efficiency technologies to reduce the cost of flash, organizations are putting complete applications and data volumes on flash and leaving them there. However, for secondary applications and older data, sometimes enterprises want HDDs within the same system.
The ability to deliver both in a single system offers the performance and latency of an all-flash array, the affordability of a hybrid array, the agility of a unified array (with support for block workloads, file shares, and object access), and the scale and resiliency of a high-end array when the right data services are applied.
Which of these is right for you depends on your particular needs, of course. With the above information, you should be better equipped to make the best decision for your business.