News for hackers. Stuff that matters.
Re:Loxilb: eBPF based cloud-native service load-balancer by betaby on Wednesday February 22, 2023 @09:55PM (#34906143)
> only the first two packets in a VM->LB->VM flow will traverse the LB. Subsequent packets are direct from VM-to-VM and are rewritten in the host NICs to merely appear to go via the LB address

Do you have more details how that's done?

Re:Loxilb: eBPF based cloud-native service load-balancer by fnordpiglet on Wednesday February 22, 2023 @10:28PM (#34906373)
Generally you can do this if the network is software defined. The boundaries between networks aren’t actually real, which means you can load balance by simply determining if the packets should be able to route then letting them route for the rest of the flow.
Re:Loxilb: eBPF based cloud-native service load-balancer by baq on Thursday February 23, 2023 @05:03AM (#34908728)
So, basically magic, just as I expected. Got it.
Re:Loxilb: eBPF based cloud-native service load-balancer by jvans on Thursday February 23, 2023 @03:18AM (#34908154)
+1 would be great for more detailed explanation or links out to reading material.

I assume there are some limitations if you actually skip the LB? How do the host NICs rewrite the LB address, does this imply there is hardware support for this kind of bypass routing?