Understanding Flash Performance

Most IT professionals are fully aware that if they have a storage performance problem that a flash based storage system is the answer for them. Flash, to some extent, makes performance a commodity. Almost any flash system can deliver more than 100,000 IOPS and many deliver 5 to 10 times that amount. In reality most data centers have a specific set of use cases that justifies a flash-based system. The problem is most flash vendors offer a single choice. It seems like, for them, all of your problems are the same as everyone else’s problems.

Determining What You Need

Once you are convinced you have a storage performance problem, the next step is to decide which flash storage system is appropriate for you. Performance has three attributes; IOPS, bandwidth and latency. IOPS is how many transactions the storage system can respond to at any given time. While the industry loves to talk about IOPS, in most cases it has very little relevance because the data center can generate only a limited number of transactions at a time. In most cases, the flash IOPS will handle more than the data center can generate. Bandwidth is how much data can move to and from the system per second. If the data center has to move large chunks of data and it needs to move those chunks quickly, bandwidth may be critical. Latency is how long it takes the storage system to respond to each individual I/O. This is an area where flash storage excels and will benefit the data center.

The IOPS Use Case is typically driven by database applications. But again there is typically a limit on how many IOPS requests these applications can generate. The installation of the right flash storage system means the data center will run out of CPU power or run into a development issue before maxing out the performance potential of the storage system.

The Bandwidth Use Case is typically the transfer of a large amount of data to or from the storage system rapidly. In many cases hard disk-based systems are suitable to meet these demands. But, of course, a flash only vendor may not tell you that. In situations where flash is justifiable over hard disk, the administrator has to configure the system to maximize that transfer.

The most common and valuable use case is latency because the flash storage system can respond to multiple I/Os quickly. A variety of flash systems can fulfill the demand, including hybrid storage systems.

There may also be a requirement for incredibly low latency, where even the performance to the storage network can factor against the performance requirements of the use case. In these situations, server side storage solutions may be more ideal to solve the problem.

Figuring out what your use case is and which solution is best for those use cases is the focus of our on demand webinar “Getting Beyond Flash 101 – Flash 102 Selecting the Right Flash Array”.


Watch On Demand

George Crump is the Chief Marketing Officer at VergeIO, the leader in Ultraconverged Infrastructure. Prior to VergeIO he was Chief Product Strategist at StorONE. Before assuming roles with innovative technology vendors, George spent almost 14 years as the founder and lead analyst at Storage Switzerland. In his spare time, he continues to write blogs on Storage Switzerland to educate IT professionals on all aspects of data center storage. He is the primary contributor to Storage Switzerland and is a heavily sought-after public speaker. With over 30 years of experience designing storage solutions for data centers across the US, he has seen the birth of such technologies as RAID, NAS, SAN, Virtualization, Cloud, and Enterprise Flash. Before founding Storage Switzerland, he was CTO at one of the nation's largest storage integrators, where he was in charge of technology testing, integration, and product selection.

Tagged with: , , , , , , ,
Posted in Blog

Enter your email address to follow this blog and receive notifications of new posts by email.

Join 25,514 other subscribers
Blog Stats
%d bloggers like this: