@@ -422,8 +422,8 @@ The latest network control structures are utilising low level kernel features.
While the Berkeley Packet Filter has been the stable base for Linux Netfilter stack, the extended version of it (eBPF) moves the computational decision making to the kernel.
While the previous OS user level tools are now rendered useless, the packet routing decision is done before the packet is introduced to the host OS.
Decision, which was previously segregated to different OSI-model or TCP/IP-stack layers, is now solved in a single process.
The eBPF can provide answers to all of the requests by partially resolving the Session layer and fully implementing the control of Transport-, Network-, Data link- and Physical-layers.
Decision, which was previously segregated to different OSI-model or TCP/IP-stack layers, can be now solved in a single context.
The eBPF can provide answers to all of the requests by implementing the control of Transport-, and Internet-layers partially stepping into Application layer.
In a highly interconnected cluster, where multiple sites are used to host the workloads, this can mean that the virtual or physical port definition is made available only in the machine where the corresponding workload is located at.
