On 03/23/2019 06:14 PM, Lawrence Brakmo wrote: > There was no eBPF at that time. We like the flexibility we get by programing > the algorithms in eBPF. eBPF being there does not mean we can adopt whatever research work, we want evaluations of the costs and benefits. > > These are not intrusive changes, they simply extend the current limited return > values form cgroup skb egress BPF programs to be more in line with qdiscs. They are quite intrusive changes to IP layer, we can not deny this.
- [PATCH bpf-next 6/7] bpf: Add cn support to hbm_out_ker... brakmo
- [PATCH bpf-next 5/7] bpf: sysctl for probe_on_drop brakmo
- [PATCH bpf-next 4/7] bpf: Update BPF_CGROUP_RUN_PROG_IN... brakmo
- [PATCH bpf-next 7/7] bpf: Add more stats to HBM brakmo
- Re: [PATCH bpf-next 0/7] bpf: Propagate cn to TCP Eric Dumazet
- Re: [PATCH bpf-next 0/7] bpf: Propagate cn to TCP Alexei Starovoitov
- Re: [PATCH bpf-next 0/7] bpf: Propagate cn to ... Eric Dumazet
- Re: [PATCH bpf-next 0/7] bpf: Propagate cn... Alexei Starovoitov
- Re: [PATCH bpf-next 0/7] bpf: Propagate cn to ... Eric Dumazet
- Re: [PATCH bpf-next 0/7] bpf: Propagate cn to TCP Lawrence Brakmo
- Re: [PATCH bpf-next 0/7] bpf: Propagate cn to ... Eric Dumazet