- FTL-free SSD concept streams data sequentially with addresses assigned to devices
- StreamFast claims a thousand-fold reduction in memory requirements for large SSDs
- Design targets cooler drives, lower power consumption and simpler high-capacity storage
Hammerspace founder David Flynn is introducing a new SSD architecture that removes the Flash translation layer and DRAM from its controller, replacing them both with a file system-centric design called StreamFast.
According to Blocks and filesthe concept is being developed as part of a new StreamFast business in collaboration with the Open Flash Platform group, while Hammerspace itself will continue to focus on its system-level software.
Flynn says the current SSD model consumes memory and power because the controllers rely on an FTL stored in DRAM to track the location of the data.
The DRAM crisis
“You need one byte of RAM for every kilobyte of flash on the SSD,” Flynn explained. Blocks and files. “Think about it. If you want to have a petabyte of flash on an SSD, that means you have to have a terabyte of DRAM with it.”
He connects this to the broader DRAM crisis, where manufacturers are shifting capacity toward high-bandwidth memory for GPUs from companies like Nvidia and AMD.
The proposal is to remove FTL entirely and let the filesystem interact directly with flash.
“We need to get rid of the block abstraction and move to something more native than Flash,” says Flynn.
StreamFast instead uses sequential addresses assigned to the device. The SSD writes incoming data streams one after the other and then returns these addresses to the host file system.
“The magic is that the device assigns sequential addresses to arbitrary strings of data that are transmitted to the device,” Flynn said.
Because writes are sequential, the host can reread the stream after a failure, rather than tracking each address in memory.
“With the StreamFast file system, that’s one byte of RAM for every megabyte of flash,” he said.
That’s a thousand-to-one improvement over the usual ratio. According to Flynn’s calculations, a 1PB SSD would need about 1GB of host memory instead of 1TB inside the drive.
Removing FTL also reduces write amplification and reduces heat, because the controller’s DRAM is often the thermal hot spot.
“This simplifies the construction of the SSD to the point where it is much more reliable,” Flynn said.
The company works with partners across the Flash ecosystem, although when Blocks and files mentioned SK Hynix, Flynn was suspicious.
“I can’t talk about the details of our partnerships yet, but stay tuned. And I was in Korea just a few weeks ago,” he said.
Flynn also says that cooler, simpler drives could adapt to power-constrained environments, including sealed or even orbital data centers.
Follow TechRadar on Google News And add us as your favorite source to get our news, reviews and expert opinions in your feeds. Make sure to click the Follow button!
And of course you can too follow TechRadar on TikTok for news, reviews, unboxings in video form and receive regular updates from us on WhatsApp Also.
