points by srcreigh 1 day ago

Nice post. Unsatisfying conclusion - did you ever figure out why the original adapter was throttled when plugged into the monitor, and not when plugged into the computer?

cibyr 1 day ago

The additional latency from going through the monitor made the bandwidth-delay product exceed the amount of data the adapter was able to send before receiving an ack. I thought that was fairly clear from the explanation, but now I notice that he didn't mention the latency without the monitor.

  • nh2 1 day ago

    That doesn't seem to be described by the article at all.

    The latency added in the monitor is described as around 8 us, completely negligible compared to any Internet connection's latency.

    So the latency without the monitor should be completely irrelevant.

    • db48x 23 hours ago

      Negligible compared to the RTT, sure. But they’re talking about the latency between when the network adaptor signals that a packet has arrived and when the CPU actually services the interrupt to tell the card to send the packet(s) to main memory. The NIC’s buffer could only hold 4 packets, so by the time the NIC got a DMA buffer to copy the packets into a fifth or sixth packet had arrived and been dropped.

      • nh2 22 hours ago

        I see now, indeed. What cibyr posted is entirely correct.

        I thought their "latency without the monitor" had referred to the overall end-to-end connection to the other IP endpoint, but they were talking about `NIC <-USB-> laptop`.

    • toast0 22 hours ago

      > The reason is that if you add up the average time it takes to get the go-ahead through my monitor’s hub, which is around 7.6 µs, to the average time it takes to send 4 KB, around 8.2 µs, you can find what the maximum speed is.

      This part is saying the NIC with this monitor can transfer 4 KB to the host through the USB hub every 15.8 us. You can do the math and it's about 2gbps.

      Remove the hub, and reduce the delay solves the problem.

      Increase the burst size would work: 8 KB per 24.0 us would be sufficient for 2.5 gbps.

      Increase the burst size and the transfer rate as done with the 5 gbps adapter, and that should work out, although that one is probably going to be insufficient for full rate 5 gbps as well.

      • nh2 22 hours ago

        Yes, that is correct. I had misunderstood which connection cibyr was referring to, see sibling post.

      • hinkley 13 hours ago

        That may be a thing where those of us who understand how TCP/IP or Ethernet works understood this paragraph but others didn’t follow.

nh2 1 day ago

The article answers this

"if the speed of the drain from my adapter to my Mac is half a gig slower than the speed of the input, then you can imagine the buffer getting filled more and more until it overflows. Those are dropped packets, which result in a hard backoff when the router resends them, so you drop loads in speed. And that’s the reason for all of this."

With diagram https://blog.tymscar.com/studio-display-ethernet/bottleneck....

The monitor decides to send the adapter's packets on at only 2 Gbit/s, which leads to buffer overflow, thus packet loss, thus e.g. TCP congestion-control backoff.

The only thing we don't know is _why_ the monitor chooses to limit the bandwidth to those 2.07 Gbit/s (computed as the 41 KiB blocks per (7.6+8.2) µs). If it sent e.g. 81 KiB blocks, doubling the bandwidth, the problem wouldn't happen.

That'd be between Apple and the monitor.

  • db48x 23 hours ago

    No, you’ve misunderstood. Any time the NIC signals that one or more packets have arrived the CPU must reply back to the NIC to give it a DMA buffer to copy the packet(s) into. By the time that reply arrived at the NIC it was already too late. The NIC could only buffer four packets and the fifth or even sixth packet had already arrived and been dropped. The NIC then sent the four packets it had to the DMA buffer and started over.

    The monitor was not really at fault. All USB hubs must read USB packets on all of their ports and copy them over to the upstream port. Those packets must all go into a buffer first so they the hub can send them individually even when they arrive simultaneously. That introduced just enough delay to allow the NIC’s internal buffer to fill up. Any hub would have caused the same problem. The solution was to buy a NIC designed for a higher speed because it has a bigger internal buffer. That new NIC will probably have the same problem with USB hubs, but at 5Gbps instead of 2.5Gbps.

    • brigade 22 hours ago

      Not all hubs and computers are equal here. Having experienced this with RTL8153, the combination of the Studio Display and ARM MacBooks is especially bad. Using an Intel MacBook with the display, or a different USB hub instead of the display, gets the full NIC bandwidth.

      • db48x 22 hours ago

        Fair enough, but I still wouldn’t say that he monitor is at fault. It’s probably not operating outside the USB specification in any way, even if it takes longer to forward messages than other hubs. It may even be multiple hubs, internally.

        It’s really the NIC’s fault because its buffer is too small to handle a little extra latency.

    • nh2 21 hours ago

      > The NIC could only buffer four packets

      Where does the "4" come from? The article's diagram suggests that the NIC's buffer is "~35 KB", though I don't know where that number comes from either (I supposed measuring how long it takes until frames are dropped). "4" seems to be the number of 1 KB packets (the 3+1 from "packet size 1024 bMaxBurst 3"), so a transmission size (protocol-level "window size"), not a buffer size. I guess if you are referring to that as a different "buffer", that makes sense, but it doesn't seem to be the buffer the article is talking about.

      But you are right with your main point regarding latency. My statement

      > The monitor decides to send the adapter's packets on at only 2 Gbit/s

      isn't really right: It's not that the monitor "decided" to only send 41 KiB instead of larger sizes; the 41 KiB is the maximum that the NIC can send because its `bMaxBurst = 3`, and the latency added by the monitor being a USB hub then limits the bandwidth to the mentioned ~2 Gbit/s.

      I guess the key point not said anywhere is that `bMaxBurst = 3` and `wMaxPacketSize = 1024 B` are fixed protocol-level parameters that hubs like the monitor have no control over. So the 4 KiB windows are fixed from the NIC through the monitor to the Mac; the monitor cannot e.g. decide to buffer some of those to compensate for the latency it adds.

      • db48x 14 hours ago

        > the monitor cannot e.g. decide to buffer some of those to compensate for the latency it adds.

        Correct. The NIC buffers the Ethernet packets, the USB hub in the monitor can only forward what the NIC sends. If the NIC drops an Ethernet packet, no amount of buffering in the USB hub can help; it’s already been dropped.

        > Where does the "4" come from?

        It was set by whoever designed the RTL8156B chip. They looked at the delay product of the USB link and calculated that a buffer holding four packets would be enough to maintain 2.5Gbps. And they’re right, assuming the latency of the USB link stays low.

        Notice that when it came time to make the RTL8157 chip that supports 5Gbps they doubled the buffer size to 8. That also works only if you assume that the latency of the USB link is low, or if you have Ethernet packets arriving at 2.5Gbps instead. They probably double it again in the chip that supports 10Gbps.

        Realtek are just being cheap. It would only have cost pennies to double the buffer sizes in both products, and the result would be a more reliable product. This is an example of why engineers specify Intel NICs and only consumers end up with Realtek NICs.

  • nh2 22 hours ago

    Hm, HN garbled my syntax involving asterisks. I meant to write

        computed as the 4*1 KiB blocks per (7.6+8.2) µs). If it sent e.g. 8*1 KiB blocks
    

    not

        computed as the 41 KiB blocks per (7.6+8.2) µs). If it sent e.g. 81 KiB blocks
archerx 1 day ago

I’m guessing it’s a USB bandwidth issue. I learned about these kind of limitations when I tried to have 3 kinects running at the same time on the same USB bus.

  • KeplerBoy 1 day ago

    He states that high speed SSDs through the monitor are fine though.

  • swiftcoder 1 day ago

    > I’m guessing it’s a USB bandwidth issue

    It's explicitly not a bandwidth issue (that would also affect the SSD). It's a latency issue - the chip doesn't have a big enough buffer to keep sufficient packets in flight at once.

    • nh2 1 day ago

      > It's explicitly not a bandwidth issue

      That's explicitly the opposite of what the author says.

      "the speed of packets coming into the adapter is 2.5 Gbps. That’s what the router pushes in. The speed going out is around 2 Gbps."

      Of course latency is always on the denominator side in the "bandwidth = data / time" equation, but it seems wrong to claim it's latency when it could also be improved by fixing the numerator; it's the entire fraction that's insufficient, thus bandwidth. As written:

      "The reason is that if you add up the average time it takes to get the go-ahead through my monitor’s hub, which is around 7.6 µs, to the average time it takes to send 4 KB, around 8.2 µs, you can find what the maximum speed is"

      And later, increasing the numerator is exactly what fixes it with the other hardware: "I can see that instead of sending 4 1 KB packets per burst, it would send 8!"

      > the chip doesn't have a big enough buffer to keep sufficient packets in flight at once

      How does this make sense? Even if his buffer was 100x larger, if the fill bandwidth exceeds the drain bandwidth, it'll eventually fill up. The article says that explicitly:

      "Well, if the speed of the drain from my adapter to my Mac is half a gig slower than the speed of the input, then you can imagine the buffer getting filled more and more until it overflows."

      • swiftcoder 1 day ago

        > Even if his buffer was 100x larger

        "buffer" was perhaps a poor choice of words on my part, because "buffer" is ambiguous. In this case I am referring to the notional "transmit buffer", which is 4 in the non-working case and raised to 8 in the working adapter.

        > "I can see that instead of sending 4 1 KB packets per burst, it would send 8!"

        Increasing the number of packets in flight does not change the bandwidth, it only improves latency sensitivity (i.e. you can fire more data before requiring an ACK).

        > it seems wrong to claim it's latency when it could also be improved by fixing the numerator.

        Increasing the bandwidth without increasing the transmit buffer would not fix this issue. The adapter he ends up buying does both (allow 2x the packets in flight, and 2x the bandwidth).

        The bottom line here is that the original adapter handles full duplex 2.5g when plugged into the laptop directly, and the SSD gets full duplex bandwidth in excess of 2.5g through the same intermediate link (i.e. the display), so both the adapter and the display have sufficient bandwidth. The added hop of latency however makes the short transmit buffer insufficient to cover the latency.

        • nh2 21 hours ago

          > In this case I am referring to the notional "transmit buffer", which is 4 in the non-working case

          Then I agree with what you were saying. Those 4 * 1 KiB are a protocol-level size (similar to the TCP window size), not an actual "buffer".

          > Increasing the number of packets in flight does not change the bandwidth, it only improves latency sensitivity (i.e. you can fire more data before requiring an ACK).

          That I don't fully follow. To me, the measured bandwidth includes all the effects of ACKs etc. If the the protocol demands that you can have at max 4 * 1 KiB unACKed in flight so you're waiting around for ACKs and not snding data, then increasing the number of packets in flight to 8 would 2x the bandwidth.

          > The added hop of latency however makes [it] insufficient to cover the latency.

          I agree with that, see also my newer reply https://news.ycombinator.com/item?id=50592931

          I this context, I also agree with your original statement; I misunderstood what you referring to with "buffer" (meaning the window, not actual storage), and "bandwidth" (where I think you're referring to the 5 Gbit/s nominal bandwidth of the bus, irrespective of the fact that the effective bandwidth of data sent is much lower due to requiring ACKs for small data).

    • hinkley 13 hours ago

      You’re using an ancient definition of bandwidth. Bandwidth in packet switching networks is not the layer 1 signaling rate, it is packets per unit time times the payload size of the packets.

  • prepend 1 day ago

    Uploads were fine.