20PB of NVMe in 4U: Supermicro's 160-bay Storage Monster

At FMS 2026, ServeTheHome spotted the Supermicro ASG-4116S-NU160R — a single-socket AMD EPYC server crammed with 160 U.2 NVMe drive bays in just 4U of rack space. Stack Solidigm's 122.88TB D5-P5336 drives into those slots and you get roughly 20 petabytes in a single chassis. That's not a prototype; it's shipping. Supermicro's official product page confirms it's built around their H14SSF integrated board with PCIe 5.0 support and hot-swap capability on all 160 bays.

Where the design gets interesting is the tradeoff Supermicro made to fit 160 drives. Instead of routing every drive directly to PCIe lanes, the system uses a PCIe switch topology that limits the lanes per drive. The payoff: lower per-drive power draw. The system runs on dual 2.6kW power supplies, which works out to roughly 130–137W per petabyte of storage all-in. That's less than what you'd need just to power the 500 hard drives required for equivalent capacity. The server also includes four additional E1.S NVMe bays on the front panel, dual 10GbE ports (Broadcom BCM57416), and three PCIe Gen5 x16 slots for 400GbE NICs or DPUs.

The CPU side is a single AMD EPYC 9005 processor up to 360W, with up to 12 DIMMs for 6TB of DDR5-6400 ECC. Supermicro's engineering pitch is that this is what you get when you stop stacking 2.5U servers and rethink the whole chassis from the ground up. You need roughly seven 24-bay 2U servers to match the 160-bay capacity — that's seven more CPUs, 72 more DIMMs, and more rack units, power, and cooling. This one box does it all with a single CPU and a single power path. The slide-out trays are the key to making maintenance tolerable: SSDs and CPU sit on separate shelves that can be pulled independently.

Source article image
Source image 1

The real question isn't whether this makes sense for a home lab — it's who actually needs 20PB of flash in one chassis. AI/ML training clusters with petabyte-scale datasets, high-performance computing workloads, and tier-zero storage arrays are the obvious candidates. But the design also points to something broader: enterprise storage is converging around ultra-dense flash platforms, and the infrastructure around them (PCIe switches, high-core-count CPUs, big-memory channels) is changing to match.

At an estimated $8–10 million when fully loaded with drives, this isn't a cheap box. But it suggests that for organizations where storage density and power efficiency matter more than per-drive pr

Source article image
Source image 2
ice, the all-flash 4U approach is becoming seriously competitive. The slide-out tray design also hints at a more practical reality: when you have 160 drives in a chassis, maintenance becomes a chore unless every component is accessible without unbolting the thing from the rack. What do you think — is this the future of enterprise storage, or just a flagship for marketing?

Sources

Comments

Post a Comment

Popular posts from this blog

AI Is Starting to Feel Less Like a Gadget and More Like Infrastructure

Image
Modern AI doesn't replace infrastructure — it runs on top of it. (Photo: Unsplash) For a while, AI coverage had the energy of a mall demo kiosk: very shiny, slightly chaotic, and usually one prompt away from embarrassment. Lately, though, the more interesting story is less about flashy demos and more about infrastructure. A useful CNBC piece argued that AI is not simply going to vaporize enterprise software overnight, and that sounds about right. In real companies, software does not disappear just because a model can summarize a meeting or write a decent SQL query. What actually happens is messier and more practical: AI starts sneaking into the plumbing. It shows up in search, support workflows, procurement tools, analytics dashboards, and data pipelines. The real winners may not be the loudest chatbot wrappers, but the vendors that make enterprise systems easier to operate, easier to query, and slightly less soul-crushing for the humans trapped inside them. That is less cinematic ...
Read more

When Two AI Bots Finally Learned to Talk in Discord

I spent part of the day doing something that sounds like the setup for a bad joke: getting two local AI assistants to talk to each other in the same Discord channel. Not through a web UI. Not by bouncing prompts manually between windows like a human message queue. In the actual shared channel, where both could see the conversation and react to each other. The funny part is that the problem was not intelligence. It was manners. Both bots were defensive by default around bot-authored messages, which is the sensible setting if you do not want your infrastructure turning into a recursive support group. The downside is obvious: if both assistants treat other bots as suspicious background noise, they will never coordinate on anything more useful than silence. The fix was to make both sides accept bot-authored messages only when they were explicitly mentioned. That detail matters more than it sounds. Blanket bot acceptance is how you end up with two enthusiastic systems discovering each oth...
Read more

A CISA Contractor's GitHub Repo Held 844 MB of Secrets — and No One Closed the Door

Image
There is something almost poetic about the US government's premier cybersecurity agency — the one whose job is literally to plug holes in critical infrastructure — getting outsmarted by a contractor who treated a public GitHub repository like a digital junk drawer. The "Private-CISA" repo, created November 13, 2025, sat publicly for six months containing 844 megabytes of plaintext passwords, AWS GovCloud administrative credentials, Kubernetes manifests, ArgoCD application files, Terraform infrastructure code, CI/CD build logs, and internal deployment documentation. Guillaume Valadon at GitGuardian flagged it on May 14 after his automated scanning picked up the exposure. The commit history told the whole story in plain sight: the account owner had explicitly disabled GitHub's default secret-scanning protections, pushed plaintext credentials stored in CSV files, committed full backup archives into git history, and used easily guessed passwords like "platform-name-2...
Read more