One of the fundamental truths about storage performance is that there is a predictable curve that relates IOPS to latency. At first, latency rises gently, sometimes even imperceptibly, as IOPS rise. At some inflection point, this changes, and suddenly every incremental unit of IOPS that a system takes on results in an exponential increase in latency.
Remote Tech Group (RTG) is the most advanced Act! hosting provider in the U.S. Running on IBM infrastructure, the team at RTG recognizes that while Act! runs on the .NET platform, customers are accustomed to the performance afforded by newer technologies like JSON and REST. With that in mind, they sought a solution to provide better performance.
Their evaluation of Infinio was a success, first with a RAM-only deployment, then even more so when they added SSDs. they found most of their I/O requests to be cacheable, which of offloaded work the aging storage, while delivering the enterprise-class response time their customers have come to expect.
“With tiering between DRAM and SSDs, Infinio gave us a 10X ROI on our hardware investment."
As I talk to customers and prospects, I get asked a lot of questions not just about our product, but also about the industry. The question I've been asked most often lately is blunt: "Are price drops in SSDs friend or foe for companies like yours?"
We're excited to announce the general availability of Infinio Accelerator version 3.4 today! <Humble brag> With this release, we're the first caching vendor with VMware Ready certification on vSphere 6.7 for VMFS, NFS, vSAN, and VVols. </Humble brag>
We're a caching company, so it will probably come as no surprise that we think the flash in your servers (SSDs, PCIe cards, NVMe devices, and flash cards) are best deployed as a cache, rather than exposed as a raw storage device.
Did you blink? You may have missed the introduction of two important flash technologies into our industry. Here's a quick primer on them:
A few months ago we surveyed over 1,000 IT decision makers about what experience they've had with server-side storage; that is, hyper-converged infrastructure, vSAN, software-defined storage, and server-side cache. We've compiled the results into a short presentation you can download.
Earlier this week, our VP of Engineering, Tom Linnell, presented a webinar entitled "Redefining Storage Performance in an All-Flash World."
All of our customers run VMware vSphere - every one of them. So we are very familiar with how vSphere gets deployed, how it is managed, and how critical it is to the organizations that use it.
We've written previously about Intel's Optane cards - why to consider them, what workloads they're suited for, and how to get the most out of them with VMware. Today we'll share some initial results from our lab testing with Optane.