On 10/31/2018 08:50 PM, Christoph Paasch wrote: > What we had here is that we wanted to let a server initiate more than 64K > connections *while* binding also to a source-IP. > With TCP the bind() would then pick a source-port and we ended up hitting the > 64K limit. If we could do an atomic "bind + connect", source-port selection > could ensure that the 4-tuple is unique. > > Or has something changed in recent times that allows to use the 4-tuple > matching when doing this with TCP? Well, yes, although it is not really recent (this came with linux-4.2) You can now bind to an address only, and let the sport being automatically chosen at connect() https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=90c337da1524863838658078ec34241f45d8394d
- [RFC 0/2] Delayed binding of UDP sockets for Quic per-con... Christoph Paasch
- [RFC 1/2] net: Add new socket-option SO_DELAYED_BIND Christoph Paasch
- [RFC 2/2] udp: Support SO_DELAYED_BIND Christoph Paasch
- Re: [RFC 0/2] Delayed binding of UDP sockets for Qui... Eric Dumazet
- Re: [RFC 0/2] Delayed binding of UDP sockets for... Christoph Paasch
- Re: [RFC 0/2] Delayed binding of UDP sockets... Eric Dumazet
- Re: [RFC 0/2] Delayed binding of UDP soc... Christoph Paasch
- Re: [RFC 0/2] Delayed binding of UDP sockets... Eric Dumazet
- Re: [RFC 0/2] Delayed binding of UDP soc... Eric Dumazet
- Re: [RFC 0/2] Delayed binding of UDP sockets for... Leif Hedstrom
- Re: [RFC 0/2] Delayed binding of UDP sockets... Eric Dumazet
- Re: [RFC 0/2] Delayed binding of UDP sockets for Qui... Willem de Bruijn
- Re: [RFC 0/2] Delayed binding of UDP sockets for... Christoph Paasch
- Re: [RFC 0/2] Delayed binding of UDP sockets... Eric Dumazet