Cheap Desktop 400GbE Switch MikroTik CRS804-4DDQ-HRM Review

(servethehome.com)

42 points | by speckx 15 hours ago ago

27 comments

  • wrs 13 hours ago ago

    I haven’t been directly involved in networking for a while, so it was funny to tune back in and see that now not only is 10Gbps apparently no big deal, they even put it on the management interface!

    • buckle8017 13 hours ago ago

      Noting actually says those ports have to be for management.

      Most people probably would use them for something else.

      • wmf 12 hours ago ago

        They're not connected to the ASIC so anything on those ports is taking the slow path.

  • nubinetwork 10 hours ago ago

    > The exciting part of this is that there are four 400GbE QSFP56-DD ports for a total of 1.6Tbps of network bandwidth.

    That I can't break down to 10gbit or 1gbit without another switch...

    > The list price is $1295, but these often sell at a street price of $1100 or so, making this under $0.70/Gbps

    It doesn't work that way...

    I like mikrotik, but who is this switch really made for?

  • iso1631 14 hours ago ago

    > While $1100 is not a low number

    It really is when you're talking 400G.

    OK there's very few ports on this, but in general if you're looking at 400g interfaces. $1100 won't even get you a genuine Arista 400G passive DAC.

    • bobdvb 12 hours ago ago

      On their video Patrick points out that this is now lower than $1 per Gbps, cheaper than any of the cheapest AliExpress switches.

    • iscoelho 11 hours ago ago

      Power usage is also very reasonable! 400GE switches and routers pull a ridiculous amount of power.

  • avidiax 14 hours ago ago

    Is there an actual use for this in a homelab? Isn't 25gbps enough that no SSD will saturate it?

    • wtallis 13 hours ago ago

      Please be careful with units. There are high-end consumer SSDs that will deliver data at 14+GB/s, which is much higher than 25Gb/s.

    • MarkSweep 14 hours ago ago

      The second sentence of the article:

      > We have a number of these now and have been running our RDMA network backend for the 8x NVIDIA GB10 cluster for several months now, using one.

      I have a friend who uses something similar for his 4 NVIDIA GDX Spark cluster.

      • avidiax 14 hours ago ago

        I see, so only if you are running an AI cluster. And what is it transferring between the nodes? Partial computations?

        • ericd 14 hours ago ago

          Essentially, yes. The DGX Sparks, at 128 gigs for ~$4700 are one of the cheapest ways to get enough high-ish speed memory cobbled together to run one of the more capable open weight models to run at home/for a small biz. This switch lets you combine the memory of 2-4 of them.

          • bitbckt 13 hours ago ago

            4-8 of them. 2 Sparks can operate without a switch.

            • ericd 9 hours ago ago

              Well, this one only has 4 ports, would you daisy chain them somehow to get to 8? Or bridge three of these switches?

              • dgl 6 hours ago ago

                They are QSFP56-DD which can be split using breakout cables. So it's 4 x 400GbE ports, which could in theory be split into as many as 32 x 50GbE ports. (Although whether that then ends up being an economical thing to do is a different matter.)

                • ericd 5 hours ago ago

                  Ahh yeah, I've seen people using those. I was thinking you'd ideally want to connect them full speed, but it looks like they're 200gbps ports anyway, and I guess even if they were 400gpbs, you don't really need that much for cross-GPU traffic for MoE models doing tensor parallel.

      • nubinetwork 10 hours ago ago

        Oh I'm sorry, just let me casually spend 30k...

        • MarkSweep 4 hours ago ago

          I'm not defending the use of money; I think it's questionable. It's still a home lab by my definition: it's computer stuff that costs less than a sports car in your home.

    • toast0 13 hours ago ago

      I purchased my SSD based on price and I have a AM4 APU so I'm limited to pci-e 3, but a quick check with crystaldiskmark says I'm hitting about 3.6 GB/s on sequential reads in seq1m q8t1 ... That would saturate 25gbps (assuming you have the right access patterns). seq1m q1t1 does 2.3 GB/s on my system, close enough to 25 gbps.

      By my math, pci-e 5.0 should do 4x the throughput, so if you had 4 pci-e ssds you wanted to serve over the network and you had the pci-e lanes, you could saturate 400 gbps.

      I'm pretty happy with my little baby network with a handful of 10G and 2.5G ports, and I'm cheap so if I made a big upgrade it'd probably be something used that has more 10g ports plus a 40G I could DAC to the adjacent home server ... but my home servers are barely powerful enough to push 10g anyway. (Something like a DCS-7050TX-48 goes for ~ $100 and would be a big upgrade in capacity I don't use over the S3300-28X I currently run)

    • hgoel 13 hours ago ago

      DGX Sparks have 200Gbps interlinks for clustering. Apparently switches are the only practical way to scale such clusters beyond 2 nodes even though each Spark has 2 such ports.

      • FireBeyond 12 hours ago ago

        Well, the problem is that you want each node to be able to directly connect to each other, so you run into a mesh situation. https://www.youtube.com/watch?v=QJqKqxQR36Y shows 8 running at 100gbps and clustered.

        • hgoel 11 hours ago ago

          I understand that part, what I don't quite get is why we can't divide the layers such that each node only needs to talk to at most 2 nodes. I assume I'm misunderstanding how work is distributed between them, but haven't looked into the details yet.

          • wtallis 9 hours ago ago

            I think this is the distinction between pipeline parallelism (first N layers on machine 1, next N layers on machine 2, etc.) vs tensor parallelism where all machines contribute to the same matrix multiplication operation within the same layer. Pipeline parallelism doesn't need exotic high speed networking, but also doesn't deliver the kind of speed increase that tensor parallelism provides.

    • FireBeyond 12 hours ago ago

      Yes, AI... this video does a good job walking through: https://www.youtube.com/watch?v=QJqKqxQR36Y

      (tl;dw - guy connects first four DGX and then another 4 "DGX-alikes". Uses 400gbps breakout cables (you can split interfaces, TIL) so he has 2 ports on the first switch, and then gets this one, I believe. You can buy cables that are 1x400 to 4x100gig, etc.

    • corvad 14 hours ago ago

      I mean at lot of what a homelab is experimenting. For example I have an absurd amount of communication 56GbE Mellanox switches but never really saturate it.

      • bobdvb 12 hours ago ago

        Yup, I have a pair of CRS504, so I can learn MLAG and my three node cluster doesn't really tickle the sides of that.

  • pyrolistical 13 hours ago ago

    Nic needs pcie5 x16 slot, so on am5, take out your gpu