Date: Sun, 21 Jul 2013 09:23:41 -0700 (PDT) From: Barney Cordoba <barney_cordoba@yahoo.com> To: Adrian Chadd <adrian@freebsd.org> Cc: "freebsd-net@freebsd.org" <freebsd-net@freebsd.org> Subject: Re: LACP LAGG device problems Message-ID: <1374423821.78377.YahooMailNeo@web121604.mail.ne1.yahoo.com> In-Reply-To: <CAJ-VmonzT1o=AkWnZVmh5qTUA68RP2vpn=%2BtNyoeYqgS5xjV2w@mail.gmail.com> References: <53315.1374329071.4500971523820617728@ffe15.ukr.net> <1374411800.11157.YahooMailBasic@web121604.mail.ne1.yahoo.com> <CAJ-VmonzT1o=AkWnZVmh5qTUA68RP2vpn=%2BtNyoeYqgS5xjV2w@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
I wasn't referring to science projects. Nor did I say it wasn't useful.=0AO=
nly that 10g is cheap now and quite a bit better. LAGG isn't perfect.=0A=0A=
=0A----- Original Message -----=0AFrom: Adrian Chadd <adrian@freebsd.org>=
=0ATo: Barney Cordoba <barney_cordoba@yahoo.com>=0ACc: freebsd-net@freebsd.=
org; isp <mline@ukr.net>=0ASent: Sunday, July 21, 2013 9:49 AM=0ASubject: R=
e: LACP LAGG device problems=0A=0AHah!=0A=0AI'm pushing 20GE out using lagg=
right now (and fixing the er, amusing=0Abehaviour of doing so.) I'm aiming=
to hit 40 once I get hardware that=0Adoesn't get upset pushing that many b=
its. The netops people at ${JOB}=0Aalso point out that even today switches =
occasionally get confused and=0A"crash" a switchport. Ew.=0A=0ASo yes, ther=
e are people using lagg, both for failover and throughput reasons.=0A=0AI'm=
working on debugging/statistics right now as part of general "why=0Aare th=
ings behaving crappy" debugging. I'll see about improving some=0Aof the pee=
r reporting at the same time.=0A=0A=0A=0A-adrian=0A=0AOn 21 July 2013 06:03=
, Barney Cordoba <barney_cordoba@yahoo.com> wrote:=0A>=0A> ----------------=
----------------------------=0A> On Sat, 7/20/13, isp <mline@ukr.net> wrote=
:=0A>=0A>=A0 Subject: LACP LAGG device problems=0A>=A0 To: freebsd-net@free=
bsd.org=0A>=A0 Date: Saturday, July 20, 2013, 10:04 AM=0A>=0A>=0A>=0A>=0A>=
=A0 Hi! Can anybody tell me, is there any plans to improve=0A>=A0 LAGG(802.=
3ad)=0A>=A0 device driver in FreeBSD?=0A>=A0 It will be greate to have a po=
ssibility to set LACP mode=0A>=A0 (active/passive)=0A>=A0 and system priori=
ty.=0A>=A0 Also there is no way to set hashing algorithm and master=0A>=A0 =
interface=0A>=A0 (port).=0A>=A0 And we can't see any information about our =
neighbor.=0A>=A0 The same function in Linux is named Bonding and it is much=
=0A>=A0 more better.=0A>=A0 I realy can donate some money to those who can =
make this=0A>=A0 improvements.=0A>=A0 Best regards.=0A>=0A>=A0 >=0A>=A0 ___=
____________________________________________=0A>=0A> Why are you using LAGG=
when 10g cards are like $350? It's not=0A> a peering protocol nor it is PT=
P; can you see your "peer" info on=0A> an ethernet?=0A>=0A> Bonding is a la=
te 90s concept designed to connect 2 slow links to=0A> get higher speeds, b=
ack in the day when 100Mb/s was ambitious.=0A> The point of LAGG is that it=
's transparent; you can load balance=0A> traffic to multiple hosts or creat=
e a redundant link without having=0A> to have equipment running some specia=
l applications, or any special=0A> logic above the LAGG device.=0A>=0A> Des=
cribing how you are using LAGG (and why) might be better=0A> than just aski=
ng for "improvements".=0A>=0A> BC=0A>=0A> _________________________________=
______________=0A> freebsd-net@freebsd.org mailing list=0A> http://lists.fr=
eebsd.org/mailman/listinfo/freebsd-net=0A> To unsubscribe, send any mail to=
"freebsd-net-unsubscribe@freebsd.org"=0A
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?1374423821.78377.YahooMailNeo>