Diskeeper Corporation has announced a new software optimizer for squeaking the most speeds out of your solid-state device. The technology’s called HyperFast, and we’ll let Diskeeper speak for itself as to what it actually does: “HyperFast creates and maintains optimized free space, increasing the controller’s ability to write sequentially and thereby enormously increasing the peak speed and life of the SSD.”
What does that mean? We crawled through Diskeeper’s white papers to find out, but still couldn’t figure out exactly how this new process speeds up a solid-state drive. The company claims that it’s trying to reduce an SSD’s free space fragmentation levels—but the “benefits” of solid-state defragmentation are nebulous at best. An SSD’s firmware uses wear-leveling functionality to assign different locations for the data you push to the drive. Defragmenting the SSD would only jumble the data around more, for a “sequential” file as seen by a software defragmenter doesn’t correspond to a sequential series of pages on an SSD block.
According to Diskeeper, its HyperFast technology makes sure that files are written to solid-state drives in a sequential order. This reduces the overall number of write/erase routines that need to run and should lead to higher performance metrics and a greater lifespan. The company boasts reads that are 5.9 times faster and writes that are 19.5 times faster on the benchmarks it’s showing off. We remain skeptical. Forum members over at OCZ Technology ran benchmarks on HyperFast-enabled drives, and they claimed to see no performance improvement whatsoever. In fact, their numbers suggest that a HyperFast-enabled SSD will actually perform slower than one without the attached service.
How does HyperFast integrate with an SSD’s built-in wear-leveling? Does HyperFast defragment the drive by ordering pages and their corresponding files sequentially, or is it just mashing up a giant chunk of “write” data against a giant chunk of “free” space? Is the program caching write operations until it can process a large number as a sequential batch? These answers are completely unclear at this point. What is clear, however, is that there’s some Internet-fueled discrepancy over Diskeeper’s new SSD optimizer. And if the program is truly performing some kind of defragmentation process on the SSD, it’s doubtful that you’ll see any benefit. Until more information about the technology emerges, you’re better off taking a look at Microsoft’s SteadyState utility or Easy Computing Company’s Managed Flash Technology if you want to squeak the most performance out of your solid-state drives.
I may be able to understand their research, but it will require that the operating systems API will need to be optimized to take real advantage of the controllers wear leveling algorithm, and these algorithm vary by controller and product family. There are no 'standards' yet, as this is an emerging technology used in many different applications.
My research is to link the operating system file management to the controller and better the access and wear performance. New technologies in NAND are emerging as well (cache, stripping, multiple die and channel, etc). I read an article that Windows 7 has worked on this.
Defragmenting a SSD, SD, MMC device so larger transfers of data can be written without causing the wear leveling algorithms to internally move data sectors around (and erase blocks) requires insight into the controller's algorithm, which directly would affect write performance. A 'generic' method may be difficult to show any performance between various devices, which is probably why no significant performance was observed using a traditional file system approach with this product.
Anyway, I believe that will happen is that the controllers and NAND technology coupled with the new embedded commands to link the file system API to the hardware will leap frog the performance in the very near future. This is only my opinion; hopefully, my Thesis results will show this promise.