On 4/9/19 16:43, Templin (US), Fred L wrote: [...] > >> albeit that the tunnel tail now has to reassemble. At speeds typically >> much higher than a typical end host. > > Using iperf3, I can show fragmentation and reassembly at near line-rate on > 10Gbps > Ethernet gear. That seems pretty good to me. Which shows that implementers > have taken IP fragmentation seriously and put in the hard work necessary to > optimize the performance.
Have you ever checked the number of CVEs related to fragmentation? -- Fernando Gont SI6 Networks e-mail: [email protected] PGP Fingerprint: 6666 31C6 D484 63B2 8FB1 E3C4 AE25 0D55 1D4E 7492 _______________________________________________ Int-area mailing list [email protected] https://www.ietf.org/mailman/listinfo/int-area
