Date: Fri, 19 Apr 2019 19:18:04 +0200 (CEST) From: Wojciech Puchar <wojtek@puchar.net> To: Kurt Lidl <lidl@FreeBSD.org> Cc: freebsd-hackers@freebsd.org Subject: Re: openvpn and system overhead Message-ID: <alpine.BSF.2.20.1904191916230.52982@puchar.net> In-Reply-To: <8e238882-1779-41ed-92fd-33abf2667d18@FreeBSD.org> References: <alpine.BSF.2.20.1904171707030.87502@puchar.net> <0cc6e0ac-a9a6-a462-3a1e-bfccfd41e138@grosbein.net> <ACE6415A-549E-4349-BB70-E4C1ECA08BCB@netgate.com> <alpine.BSF.2.20.1904191842140.44949@puchar.net> <8e238882-1779-41ed-92fd-33abf2667d18@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
>> from/to tun device, as well as send/recv would have multipacket version - >> it would mean speeding it up at least 4 times. > > Well, FreeBSD does have sendmmsg()/recvmmsg(), which allows for > sending/receiving multiple packets per system call. I do not know if > the "tun" device allows for send/recv type processing, or just > read/write. > i will have a look at openvpn code next weekend. tun doesn't have this but this would bit still a bit speedup. > Don't get me wrong -- having in-kernel processing, like ipsec does, is far > superior to doing it as a userland daemon, IMHO. Just pointing out Having everything in kernel isn't superior. Having low overhead system call interface would be. Sad to say but system call overhead in FreeBSD is high.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?alpine.BSF.2.20.1904191916230.52982>