Date: Thu, 5 Jul 2012 13:00:48 -0400 From: Jason Hellenthal <jhellenthal@dataix.net> To: Vyacheslav Kulikovskyy <coolsysop@gmail.com> Cc: freebsd-net@freebsd.org, Eugene Grosbein <egrosbein@rdtc.ru> Subject: Re: lagg speed trouble Message-ID: <20120705170048.GC35340@DataIX.net> In-Reply-To: <CABj7HZ_2q70FGFOD_QB7ATVpZ68n0ZQroi0OV8xkpSxajqeE1A@mail.gmail.com> References: <CABj7HZ8dnbpwhgpQ9pE=M2xJh_LFp2oYdPqvXke0GF%2B4rt7sgg@mail.gmail.com> <4FF5329E.1000007@rdtc.ru> <CABj7HZ_2q70FGFOD_QB7ATVpZ68n0ZQroi0OV8xkpSxajqeE1A@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
--wRRV7LY7NUeQGEoC Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Thu, Jul 05, 2012 at 12:00:07PM +0300, Vyacheslav Kulikovskyy wrote: > 2012/7/5 Eugene Grosbein <egrosbein@rdtc.ru> >=20 > > 04.07.2012 18:30, Vyacheslav Kulikovskyy =D0=BF=D0=B8=D1=88=D0=B5=D1=82: > > > i have sever with two 1G links (em) aggregated by lagg0 > > > > > > after 1700Megabits i have collisions/errors on lagg0 port, but not on= em0 > > > or em1 > > > > > > I'm using nginx in own CDN. and server don't limited my mbufs, irq, or > > > anything else.. only lagg0 errors ( > > > > lagg0 by default uses way too small output FIFO queue, 50 slots. > > You definitely want to increase this to sum of your em intefaces > > txd buffers at least. So, if you use hw.em.txd=3D4096, you should > > use 8192 for lagg or more. I prefer 10K, in /boot/loader.conf: > > > > net.link.ifqmaxlen=3D10240 > > > > Reboot is required. > > > > Eugene Grosbein > > >=20 > This is solution don't help me > hw.em.txd: 4096 > net.link.ifqmaxlen: 10240 >=20 > # netstat -w 1 -I lagg0 > input (lagg0) output > packets errs idrops bytes packets errs bytes colls > 77600 0 0 4771508 71175 70 208916199 0 > 79747 0 0 4885070 73101 242 218847447 0 > 84956 0 0 5262540 74504 455 213752515 0 > 81333 0 0 4998499 73836 229 215808086 0 >=20 > and no errors on em0,em1 >=20 > more info: FreeBSD 9.0-STABLE #0: AMD64 >=20 > ps after small test i'll try patch from Andrew Thompson Would you be able to produce a tcpdump capture of the traffic causing this on all three interfaces ? tcpdump -s 112 -w em0.pcap -p -c 5000 -i em0 tcpdump -s 112 -w em1.pcap -p -c 5000 -i em1 tcpdump -s 112 -w lagg0.pcap -p -c 5000 -i lagg0 Tar em up and put them somewhere in a http or ftp you know about but noone else does and email appropriate person with the link. --=20 - (2^(N-1)) --wRRV7LY7NUeQGEoC Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- iQEcBAEBAgAGBQJP9cg/AAoJEBSh2Dr1DU7WnusH/3hnDnAPKryEJNPwSi8NFm13 GV8lHwSHi7PrLQrdcmeOCUf8Wyt32W2t3f8+fizHvojKDqa8oqbUcaW3DQTRlkod julIZOc7xAZG02/PiVoErNRS8bBABSrO9HukA+MLkwWFcZ8PxoVqlEexuBak+tsF MOs8QTLuBr4WqicJx0yTgz7pFYpHX9fuuxegX9mbifLJdBDacwaITcjoIz0IL7um O/GluBlHJKjF9bD6dwvHY2DyyHUXLhJunsP3lnuJ1Ibbh92WBLF1NRcw/Ank7Wzu mnuExqq+y6gzfabCaiN2F/zETQlEuPv6HQAmvzXMMORsH89QkuRrl1TZ1NpH5Kw= =4bdk -----END PGP SIGNATURE----- --wRRV7LY7NUeQGEoC--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20120705170048.GC35340>