At IBM’s Edge 2013 conference last week the company not only extolled the values of flash, as does anyone who has had a flash experience, but it also showed how flash could be made even faster than it already is.
You’re probably already thinking: “Flash is about 1,000 times as fast as HDD – how do you make it even faster?”
The answer is actually pretty simple: compress the data. If there is a limit to how much bandwidth you have going into and out of a piece of storage, you can speed it up if you can reduce the size of the data that consumes that bandwidth.
Of course, that’s not always easy. Compression often slows data access down, even for HDDs, and it could cause a dramatically more significant slowdown when using flash. IBM’s answer is to use a fast enough compression-decompression engine to make these delays invisible even to flash-based storage. That’s a pretty tall order, given that the PCIe SSDs that IBM sells through its acquisition of Texas Memory Systems (TMS) can deliver as many as one million IOPS.
IBM claims to be the only storage vendor that can do real-time compression without a penalty. That’s a pretty strong statement given the numerous storage start-ups (like SolidFire, Pure Storage, and Skyera) who sell boxes that combine compression with flash. (Even the SandForce SSD controllers sold by LSI use internal real-time compression.)
The net result is faster flash, though, and this should help IBM differentiate its products in two ways: The flash will be faster, and you can use less of it to save on costs.
IBM is executing fully on last April’s Flash Ahead Initiative in which the company committed to heavily promote flash. Readers who would like to learn more about flash use in the enterprise can purchase Objective Analysis‘ report: The Enterprise SSD: Technologies and Markets, which can be purchased for immediate download on the Objective Analysis website.