Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Framework's 10G Ethernet module exposes USB-C's complexity

jeffgeerling.com

Post reply on HN
Print view View original

91–100 of 197 posts

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#91

Post by adrian_b »

Unlike "5 Gb/s" USB, which in reality is 4 Gb/s USB, so a 5 Gb/s Ethernet interface cannot reach its maximum speed on a 5 Gb/s USB, the "10 Gb/s" USB is really 10 Gb/s, i.e. the difference between its real speed and 10 Gb/s is small enough to be negligible.

The same is true for 10 Gb/s Ethernet, whose speed is not exactly 10 Gb/s, but the difference from 10 Gb/s is also negligible.

Therefore, you do not need a 20 Gb/s USB to reach the maximum speed with a 10 Gb/s Ethernet interface, a 10 Gb/s USB port is good enough.

The overhead of data framing on USB is slightly higher than on Ethernet, so the maximum throughput on an USB 10 Gb/s Ethernet interface is a little lower than for a PCIe Ethernet NIC, but the difference is small enough to not matter. Usually other factors, like bad device drivers or inefficient programs, can cause much greater variations in Ethernet throughput.

The 9.4 Gb/s throughput obtained in TFA is perfectly reasonable when taking into account the packet overheads, which make impossible to reach 10 Gb/s for user data, regardless of hardware. A 20 Gb/s USB interface could not provide any serious improvement over that.

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#92

Post by PunchyHamster »

ChuckMcM wrote: post #57

I chuckled at 10G wired ethernet on a laptop. I mean in a docking station? Sure that seems reasonable. But fun none the less. I appreciate the USB-C nature of the Framework's expansion ports, it does make real the entire reason that USB was created in the first place, hot plug slots. Still, I (and others) pointed out to Intel early on that using Ethernet with a specific packet type would be cheaper and just as fast (…

I wish they would just have direct PCIe lanes. For most of the cards doing those speeds USB is just unnecessary overhead

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#93

Post by arghwhat »

Well, this is about USB 3.2 Gen 2x2, which is a mess created by USB IF for good old, blue USB A connectors. Not USB-C complexity.

USB 3.2 Gen 2x2 is the very rarely supported 20Gb/s variant of USB 3, and making devices now that require that for full performance is a weird decision, with high-speed capable ports generally having wider support for either USB4 or Thunderbolt3+. I imagine the reason would be that some chip with an otherwise poor market fit got cheap...

Throwing this into the mix definitely doesn't improve the USB-C "what does this port support" conundrum, but this specific one predates USB-C and is not at all something you'd normally hit.

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#94

Post by raverbashing »

Sounds like the dual problem of "I want the thinnest" is the "I want the most powerful" on miniature equipment, and of course you run into an unbalanced situation

Honestly I don't see much of an use for 10Gbps in a notebook that can't be solved by a dongle when you actually need it

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#95

Post by adrian_b »

arghwhat wrote: post #93

Well, this is about USB 3.2 Gen 2x2, which is a mess created by USB IF for good old, blue USB A connectors. Not USB-C complexity. USB 3.2 Gen 2x2 is the very rarely supported 20Gb/s variant of USB 3, and making devices now that require that for full performance is a weird decision, with high-speed capable ports generally having wider support for either USB4 or Thunderbolt3+. I imagine the reason would be that some ch…

10 Gb/s Ethernet interfaces do not require 20 Gb/s USB ports for reaching maximum performance, they already reach that on 10 Gb/s USB ports, despite of what the writer of TFA believes.

The main application of 20 Gb/s USB ports is to connect external NVMe SSDs, when faster USB 4 or Thunderbolt ports and SSDs are not available.

For an external NVMe SSD on USB, a 20 Gb/s USB port will double the throughput, unlike for a 10 Gb/s Ethernet interface where any improvements are completely negligible.

I do not think that 20 Gb/s USB Type C ports are "very rarely supported". Every mini-PC or desktop motherboard that I have bought during the last 10 years had at least one such USB port.

Such ports appear to be rare only on laptops, because most laptops have very few USB ports.

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#96

Post by bartvk »

jfb wrote: post #7
RachelF wrote: post #6

Every PCIe 10G ethernet card I've seen has a heatsink on it, sometimes covering the entire card or even have little fans on the heatsink. Expecting it to work full time in a laptop is a bit of a stretch of the heat dissipation budget. Also, the laptop he is working has the AMD FP8 chipset - depending on how the ports are setup, he might only get 10G USB, if the ports are allocated to video instead.

Yeah, 10Gb ethernet runs hot . I just rewired the house with 10Gb (we have 8Gb FTTP) and it's kind of upsetting how hot my Thunderbolt dock gets.

Which dock (brand/model) did you get?

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#98

Post by retired »

adrian_b wrote: post #95
arghwhat wrote: post #93

Well, this is about USB 3.2 Gen 2x2, which is a mess created by USB IF for good old, blue USB A connectors. Not USB-C complexity. USB 3.2 Gen 2x2 is the very rarely supported 20Gb/s variant of USB 3, and making devices now that require that for full performance is a weird decision, with high-speed capable ports generally having wider support for either USB4 or Thunderbolt3+. I imagine the reason would be that some ch…

10 Gb/s Ethernet interfaces do not require 20 Gb/s USB ports for reaching maximum performance, they already reach that on 10 Gb/s USB ports, despite of what the writer of TFA believes. The main application of 20 Gb/s USB ports is to connect external NVMe SSDs, when faster USB 4 or Thunderbolt ports and SSDs are not available. For an external NVMe SSD on USB, a 20 Gb/s USB port will double the throughput, unlike for a…

What about overhead? Can you truly do 10Gb/s networking on a 10Gb/s USB port? Would having such NIC on a 20Gb/s USB port not result in higher speeds?

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#99

Post by retired »

ChuckMcM wrote: post #57

I chuckled at 10G wired ethernet on a laptop. I mean in a docking station? Sure that seems reasonable. But fun none the less. I appreciate the USB-C nature of the Framework's expansion ports, it does make real the entire reason that USB was created in the first place, hot plug slots. Still, I (and others) pointed out to Intel early on that using Ethernet with a specific packet type would be cheaper and just as fast (…

Future proofing. Websites nowadays load tens of megabytes for a simple news page. I wouldn’t be surprised if in the future a website consumes 500+ megabytes on the initial page load. That will take 40 seconds on a 100 megabit link and 400 milliseconds on a 10 gigabit link.

Try to load any modern website on dial-up. The connection will likely timeout before a full page load.

Re: Framework's 10G Ethernet module exposes USB-C's complexity

#100

Post by Tade0 »

PunchyHamster wrote: post #92
ChuckMcM wrote: post #57

I chuckled at 10G wired ethernet on a laptop. I mean in a docking station? Sure that seems reasonable. But fun none the less. I appreciate the USB-C nature of the Framework's expansion ports, it does make real the entire reason that USB was created in the first place, hot plug slots. Still, I (and others) pointed out to Intel early on that using Ethernet with a specific packet type would be cheaper and just as fast (…

I wish they would just have direct PCIe lanes. For most of the cards doing those speeds USB is just unnecessary overhead

They sort of do in the 16 with the dual M.2 adapter:

https://frame.work/pl/en/products/dual-m-2-adapter

People have been making custom OCuLink adapters and recently Framework developed its own:

https://frame.work/pl/en/products/framework-oculink-dev-kit

Post reply on HN