There are L1 crosspoint "switches" in the 2-5ns range depending on port density and similar modes in some Ethernet silicon. These are not Ethernet switches in any normal sense though. They only replicate the signal 1:1 or 1:n and do not dynamically switch the destination based on anything in the packet. The fastest L3 Ethernet switches on the market are ~90ns.
They're more like digital patch panels. You can connect any pair of ports together in both directions (TX/RX), just like moving a patch cable around. You can also connect an incoming RX lane to multiple TX lanes (think optical splitter but electrical). You cannot merge signals together. Some products have FPGAs that add L2+ or multiplexing functionality with packet buffers, but that's not part of the 2-5ns path.
So, if I know the destination addresses on each port in advance I can program it to behave like an L2 switch (with proper multicast even), and I can use code to reprogram it whenever the traffic pattern changes?
The L1 path can't do any address matching and you can't overlap sources - like Ghostbusters, no crossing the streams. You can source port 1 to ports 2-4 (multicast, but static and unidirectional) and you can change a bidir connection between pairs of ports. The signal gets replicated regardless of what's in the frame. It wouldn't be practical to make it behave quite like an L2 switch.
When I was at a small IT consulting shop ~15 years ago, this is roughly how it worked. We'd get paid 24x7 for a week on-call at minimum wage + 1.5x normal wage for any hours we had to log in.
Hollow core fiber (HCF) is designed to substantially reduce the latency of normal fiber while maintaining equivalent bandwidth. It's been deployed quite a bit for low latency trading applications within a metro area, but might find more uses in reducing long-haul interconnect latency.
Timestamps and other types of in-band network telemetry are sometimes inserted in the frame as a trailer (with a new FCS). If an application isn't looking for the L2 data, it's just ignored by the Linux IP stack.
They claimed that they had correctly interpreted the documents as presented. The issue was that my condo (in a 2 unit condo building) hadn't been correctly deeded one of the 2 parking spaces, even though the building was designed and used that way for decades.
They claimed that the seller misrepresented the property by claiming it came with a parking spot.
The more time they spend in a truck, the higher the risk of "transportation sickness," which is basically animals being stressed out from being in a weird truck going down the highway and being more susceptible to a bunch of stuff. Interesting aside, that's part of what made Roosevelt's ranch more successful, he was supposedly one of the first ranchers to stop transporting live cattle to Chicago for sale, and instead slaughtered on-site and made use of the newly invented refrigerated boxcar.
There's money in direct sales, of course, but you have to a) be inspected for general sales and b) use a butcher who is inspected and licensed for i) in-state and ii) out-of-state sales. If you ever buy a "share" of an animal and pay to have it butchered, you may notice the meat comes in packaging with prominent NOT FOR RESALE markings -- that's why, it's a local butcher not USDA licensed for general public sales.
Buying "shares" is a skirt around the law, but most people don't want to deal with the amount of meat from even 1/4 a carcass, and they're usually hard customers for local butchers ("Your butcher is robbing us! They wouldn't give us
T-bones and NY Strip!"). Supposedly if you're found to be doing too much of it, or "automating" it too much for the "shareholders," the USDA will come down on you for it (IMO rightly).
You also then have to market the meat. My wife and I had offered to help set up a canned site to help with it, but my parents were too concerned about the licensing requirements and that it'd be throwing more money into the hole that is subsistence farming!
A bonus based on risk-adjusted outcomes would put pay in alignment with patient care. This would require much better outcome analysis and reporting though (also a good thing).
Adding this sort of friction would increase spreads. Market makers are a net positive for markets (who buys/sells when no one else wants to?), and I don't see any downside to allowing them to manage risk and trade quickly. I think the way to increase fairness is to change the way orders are matched.
The best solution I've seen is to do batch auctions every millisecond or so, and randomize matches within that window (for market orders or limit orders at the same price). You could use a longer window to include slower players in the market.
