Smarter NAND for Better SSDs

NAND part of one of the diagrams below.Micron presented something really interesting during the company’s Investor Day Conference last week, but it didn’t seem to get any press coverage.  The company naturally repeated its plan to become a more important supplier of data center SSDs, but what The SSD Guy was most interested in were a few comments they gave for choosing to make vertically-integrated SSDs.  Micron now makes not only the NAND and the DRAM internal to its SSDs, but also the controller.

Why would a company Continue reading “Smarter NAND for Better SSDs”

An SSD You Can’t Wear Out

Infinity symbol overlaid on a Nimbus ExaDrive DC SSD photoThere’s something really odd about Nimbus Data’s colossal 100 terabyte ExaDrive DC SSDs, and it’s not their sheer capacity (although that’s pretty remarkable by itself!)  The strange thing is that they can’t be worn out.  It’s physically impossible.

At first glance that may seem wrong-headed.  NAND flash wears out, and that was the cause of a lot of Continue reading “An SSD You Can’t Wear Out”

Whatever Happened to “Hero” SSDs?

Bodybuilder with the insides of an SSD superimposedIt seems not so long ago that there were frequent press releases, and showings at trade shows, of “Hero” SSDs.  These demonstration models (which weren’t always released as products) always had some unique and impressive attribute.  They may have had a higher capacity than any SSD known to humankind, or perhaps they had phenomenal endurance.  Some broke the IOPS barrier.

The SSD Guy doesn’t remember anyone Continue reading “Whatever Happened to “Hero” SSDs?”

Using 176-Layer NAND for High-Capacity Data Center SSDs

Chart with a line that goes pretty flat from 1.5 to 2ms latency 0 to 350K IOPSMicron recently briefed The SSD Guy on its new 7450 SSD series, a range of high-capacity data center SSDs offered in an impressive number of capacities and form factors spanning M.2, U.3 and E1.S. The 7450 is a mainstream drive targeted at a wide variety of data center applications, including common, mixed, and random workloads.

The 7450 series is an evolution of Micron’s 7400 series which was first introduced at 96 layers and was based on Continue reading “Using 176-Layer NAND for High-Capacity Data Center SSDs”

Using AI to Manage Internal SSD Parameters

Old wise man with a disk symbol coming out of his headFor a long time The SSD Guy has meant to write something about the budding use of AI in SSDs.  It’s an interesting approach whose time has come.

If you’re not conversant with AI, and maybe find the whole subject to be daunting, don’t worry.  AI comes in many forms, and some are very simple.  When major Internet firms like Google and Facebook use AI to Continue reading “Using AI to Manage Internal SSD Parameters”

Computational Storage Hits the Mainstream

Chart showing two lines on a graph of performance vs number of SSDs. With "Scale In" the performance is proportional to the number of SSDs. With a standard server the performance diesn't change. With 16 SSDs the performance is 4 timeas as much, and with 32 SSDs it's 8 times as much.There’s an idea that has been kicking around for a number of years, and it seems now to be gaining traction.  The idea is to use the inherent smarts and high available bandwidth within an SSD to perform functions that would normally be done by a server’s processor thereby reducing the load on the processor while minimizing the amount of data that needed to make a round trip from the SSD to the processor and back for some trivial function.

Such data movement is said to consume a very Continue reading “Computational Storage Hits the Mainstream”

What’s Software-Enabled Flash?

abstract eye-catching imageThere have been numerous changes to SSDs since they moved into the mainstream 15 years ago, with controllers providing increasing, then decreasing endurance levels, and offering greater, then lesser levels of autonomy.  What has been missing is any ability for the system to determine the level of performance that the SSD provides.

Recently Kioxia, the company formerly known as Toshiba Memory, announced Continue reading “What’s Software-Enabled Flash?”

Start-Up Fadu Launches New SSD Controller

Fadu, a startup out of Korea, made a big  splash at the Flash Memory Summit to announce its new NVMe SSD controllers that don’t compromise speed to achieve low-power operation.

The company’s products are focused on quality of service (QOS) in enterprise-style 24/7 workloads with the aim of enabling the transition to NVMe in Enterprise and Hyperscale data centers, the fastest-growing segments in the SSD market.  Some readers may recall that Fadu won the 2018 FMS Best-of-Show award in the “Most Innovative Flash Memory Technology” category for an earlier generation of products.

The company’s founding team comes from Samsung and Hynix with a CEO (Jihyo Lee) from Bain Capital.  Lee gave a keynote address at the Flash Memory Summit simply titled: “Enterprise SSD: The Future”

The new SSD controller, Annapurna, is a Continue reading “Start-Up Fadu Launches New SSD Controller”

What is an SSD Trim Command?

TrimmerAlthough the Trim command has been defined for nearly a decade, for some reason I have never written a post to explain it.  It’s time for that to change.

Trim is something that was never required for HDDs, so it was a new command that was defined once SSDs became prevalent.  The command is required because of one of those awkward encumbrances that NAND users must accommodate: Erase before write.

NAND flash bits cannot be altered the same way as an HDD.  In an HDD a bit that’s currently set to a “1” can be re-written to a “0” and vice versa.  Writing a bit either way takes the same amount of time.  In NAND flash a 1 can be written to a zero, but the opposite is not the case.  Instead, the entire block (4-16k bytes) must be erased at once, after which all bits are set to a 1.  Once that has been done then zeros can be written into that block to store data.  An erase is an excruciatingly slow operation, taking up to a half second to perform.  Writes are faster, but they’re still slow.

Let’s say that a program needs to Continue reading “What is an SSD Trim Command?”

SSDs Need Controllers with More, NO! Less Power

More Power-Less PowerThe Storage Developer Conference in September gave a rare glimpse into two very different directions that SSD architectures are pursuing.  While some of the conference’s presentations touted SSDs with increasing processing power (Eideticom, NGD, Samsung, and ScaleFlux) other presentations advocated moving processing power out of the SSD and into the host server (Alibaba, CNEX, and Western Digital).

Why would either of these make sense?

A standard SSD has a very high internal bandwidth that encounters a bottleneck as data is forced through a narrower interface.  It’s easy to see that an SSD with 20+ NAND chips, each with an 8-bit interface, could access all 160 bits simultaneously.  Since there’s already a processor inside the  SSD, why not open it to external programming so that it can perform certain tasks within the SSD itself and harness all of that bandwidth?

Example tasks would include Continue reading “SSDs Need Controllers with More, NO! Less Power”