Hans Petter Selasky wrote this message on Fri, Mar 20, 2015 at 19:56 +0100: > On 03/20/15 19:02, Adrian Chadd wrote: > > On 20 March 2015 at 10:58, Hans Petter Selasky <h...@selasky.org> wrote: > >> On 03/20/15 14:31, Emeric POUPON wrote: > >>> > >>> - in the ip_newid macro, we do "htons(V_ip_id++))" if we do not use > >>> randomized id. > >> > >>> In multi core systems, we may emit successive packets with the same id. > >> > >> Will using a mutex or an atomic macro fix this issue when incrementing the > >> V_ip_id ? > > > > It will, but it'll ping-pong between multiple cores and slow things > > down at high pps. > > Maybe we can have the V_ip_id per CPU and use the lower 8-bits as random > CPU core number?
ip id's only need to be unique for fragments to a specific source address/destination address/protocol tuple... so, using different id buckets per above hash would be best... Take a look at: https://tools.ietf.org/html/rfc6864 Which is a good read for addressing this issue... -- John-Mark Gurney Voice: +1 415 225 5579 "All that I will do, has been done, All that I have, has not." _______________________________________________ freebsd-net@freebsd.org mailing list http://lists.freebsd.org/mailman/listinfo/freebsd-net To unsubscribe, send any mail to "freebsd-net-unsubscr...@freebsd.org"
