Date: Fri, 29 Jul 2005 11:52:07 +0200 From: Jeremie Le Hen <jeremie@le-hen.org> To: Julian Elischer <julian@elischer.org> Cc: Daniel O'Connor <doconnor@gsoft.com.au>, freebsd-net@freebsd.org Subject: Re: AltQ + ng_iface Message-ID: <20050729095207.GL68965@obiwan.tataz.chchile.org> In-Reply-To: <42E99CFD.6070803@elischer.org> References: <200507290834.10268.doconnor@gsoft.com.au> <200507291035.46770.doconnor@gsoft.com.au> <42E98725.1020600@mac.com> <200507291115.06612.doconnor@gsoft.com.au> <42E99868.1080306@mac.com> <42E99CFD.6070803@elischer.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Hi Daniel, Chunk, Julian and all, > >slow things down. So you want to send dataless ACKs at a higher > >priority than generic big packets full of data, maybe via the "iplen" > >keyword with "established", look for packets smaller than ~100 bytes? > > [...] > > I sometimes actually prioitise ALL small packets allowing interactive > stuff to > bypass ftps etc. and sometimes I do it on both ends. I personnaly use the following rules on egress of my external interface to "prioritize" (although that's not Dummynet do) some packets. This works very well, I can make two parallel uploads at full upstream bandwidth without my SSH session or my download being impacted : ACKs: tcp from any to any iplen 40-60 tcpflags ack Interactive SSH: tcp from any to any 22 iptos lowdelay tcp from any 22 to any iptos lowdelay DNS requests: udp from any to any 53 Small PONG: icmp from any to any icmptype 8 iplen 1-200 HTTP(S), FTP: tcp from any to any 21,80,443 Regards, -- Jeremie Le Hen < jeremie at le-hen dot org >< ttz at chchile dot org >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050729095207.GL68965>