Featured Video, Video

Virtual Reality panel at Power of 4 Tech Forum

Experts examined the ways that virtual reality can be innovatively deployed to put users at the heart of the action
Don't show me again

Need for speed

HSD SSDSolid-state disk, once considered a niche technology for ruggedised, industrial and military applications, is on its way to the mainstream. This is partly because of SSD benefits, which include performance, power efficiency, ruggedness and a lightweight, compact size. But other developments have also come into play, including technology and market developments that have begun to help this technology overcome its pitfalls – namely capacity, reliability and price.

Because SSD is based on NAND flash memory chip technology, it has no moving parts, which makes it faster and less prone to mechanical failure than hard disk drives. Today, costs are shrinking faster than ever, thanks to market growth, new technology developments and vendors working overtime to accelerate their SSD development.

There are many reasons why SSDs are being adopted into enterprise servers and storage systems. “The electronically stored NAND based flash architectures permit increased durability, scalability and greater reliability and can be a boon for VDI deployments and dynamic infrastructures,” says Swapna Subramani, Senior Research Analyst, Systems and Infrastructure Solutions, IDC.

Salil Dighe, CEO, Meta Byte Technologies, adds SSDs also require far less power and produce a fraction of the heat of their spinning counterparts. “According to the Storage Networking Industry Association (SNIA), SSDs demand 92 percent less power, and operate at 38 percent lower temperatures. In addition, the absence of moving parts such as mechanical arms, motors and spinning platters enables SSDs to deliver far greater reliability and higher Mean Time Between Failure (MTBF). Parts stress analysis indicates a MTBF of almost twice as many hours for Enterprise SAS SSDs vs. HDDs. SSDs are becoming more reliable than their spinning counterparts, which essentially translates to drastically improved uptime and less costly servicing, a feature that is proving critical in some industries.”

Christian Assaf, Senior Sales Manager, Seagate, says a growing cloud ecosystem is also one of the factors behind the increase in enterprise SD adoption in the Middle East. Enterprise SSDs have enabled a faster, more efficient cloud, and as these solutions are more widely adopted, demand will continue to escalate. Faster data flows enabled by enterprise SSD deployments in the cloud will also lead to the creation of additional data to be stored, creating an advantage to solution-provider partners.”

Are SSDs poised to replace hard disks in server infrastructure? Enterprises have long struggled with the storage conundrum of high capacity vs. high performance. Hard disk and solid state drives (SSD) each offer advantages the other cannot match. Hard drives are the reigning kings of capacity, but lack the performance, ruggedness and power-saving features of SSDs. For all their advantages, SSDs are miles away from hard disk drives in delivering the capacity and cost-effectiveness required by enterprise applications.

“While enterprise SSDs have the potential to move beyond niche applications and become a viable option for certain environments, HDDs will continue to remain the mainstay of storage architectures. With data explosion occurring every year, enterprises are looking at solutions that can maintain federated data sources with de-duplication, automatic tiering, backup and archiving, disaster recovery and business continuity solutions. These solutions require high-performance disk based systems,” says Subramani.

Dighe agrees: “Given the enormity of future capacity needs, it will be impossible for CIOs and IT managers to completely replace hard drives with SSDs during the next five years in data centres. Having said that, there are far better flash based technologies, which are superior with higher addressable capacities and performance. FusionIO, one of the brands in our portfolio, is the leading storage solution provider for server infrastructure. These solutions could possibly be the best choice today for IT managers who are bothered with performance and consolidating the data centre footprint.”

These two technologies offer varied and compelling attributes and users have to consider certain factors while comparing HDDs and SSDs for their applications. “There is more than just cost per capacity or capacity density to consider when determining the type of enterprise storage to use for cloud environments. Certainly space capacity measured in gigabytes and terabytes are important characteristics to consider. However, there are other attributes that should inform purchasing decisions depending on the application, workload or usage scenario,” says Assaf.

These requirements include performance, availability, space capacity, economics and functionality. It is also critical to understand what kind of data an organisation is dealing with, as well as the environment in which the drives will be used. Different applications and data – such as active data versus inactive data – require unique storage devices.

The Storage Networking Industry Association (SNIA) has completed an in-depth analysis of the factors that need to be considered in comparing HDDs and SSDs for any given application. It concluded that assessing total cost of ownership offered the most realistic basis for comparison – assessing both the direct and indirect cost of deploying a storage system over its life cycle.

Direct costs, labour and capital costs are familiar and relatively easy to measure. However, indirect costing becomes more complex to expose. Industry studies have shown it can cost more to operate a storage device over three years than to buy it. To get a clean TCO, it is essential to objectively include all relevant data including cost for:

* Acquisition. Analysis of acquisition costs needs to include cost per drive, software licenses and differing architecture options. Consider that, in a high random I/O transaction application (i.e. Exchange email, banking transactions, etc.), a single SSD could replace an array of 10 or more HDDs, resulting in a smaller footprint, higher performance and lower costs for supporting hardware and software licensing.

* Maintenance and Repair. HDDs have an annual failure rate of 2 percent to 8 percent. So as many as one in 12 HDDs deployed will fail every year. Factor in the cost of a drive, the personnel to replace it and any system downtime to get a clear picture of the true cost of these replacements. In addition, SSDs need to be treated as a consumable with endurance dependent on multiple factors, which vary by manufacturer and design.

* Power and Cooling. In tier 0 and 1 storage systems, choosing SSDs can save more than 80 percent in total storage system energy requirements. There are many elements to this calculation. Ultimately, it is the greater power density (IOPS/Watt) of SSDs that make the difference; fewer drives can deliver the same throughput for less power, with the added benefit of requiring less space and cooling.

* RAID Configuration. It is standard practice to use RAID configurations to improve performance and reliability. Conventional RAID configurations mask the high I/O latency inherent in HDDs. New SSD-friendly RAID implementations both exploit and enhance the performance and reliability of SSDs. The tradeoffs between levels of RAID can significantly shift the performance, cost and reliability equations so the relative benefits need to be factored into a complete TCO exercise.

“Calculating a full TCO is an important discipline. But for immediate comparison between SSD types and designs, some simple metrics are useful. In the HDD era, the rule of thumb measures were cost per GB and I/O throughput. The characteristics of SSDs weaken the relevance of cost per GB and mean that tests of I/O throughput need to be appropriate to SSDs to ensure accurate real-world performance comparisons can be made between drive types,” says John Scaramuzzo, Senior VP and GM of SanDisk’s Enterprise Storage Solutions.

This leads to two new rules. One, adopt cost per terabyte written ($/TBW) as a key metric for comparison. And two, compare performance on the basis of standardised tests, suited to SSDs.
SNIA has evaluated the impact of these different factors and developed a performance test specification for enterprise solid state storage.

“Realistic comparisons between HDDs and the best performing SSDs show that for the majority of enterprise applications the performance benefits of SSDs are now available at a price that is becoming competitive with HDDs. Think TCO and ask for $/TBW and SNIA performance figures. Then simply run the numbers; they speak for themselves,” Scaramuzzo sums up.

Previous ArticleNext Article

Leave a Reply

Your email address will not be published. Required fields are marked *

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


The free newsletter covering the top industry headlines