Date: Thu, 12 Oct 2006 16:14:00 -0400 From: Mike Tancsa <mike@sentex.net> To: Danny Braniss <danny@cs.huji.ac.il> Cc: freebsd-net@freebsd.org, feebsd-hackers@freebsd.org Subject: Re: em blues Message-ID: <7.0.1.0.0.20061012160920.12a780d8@sentex.net> In-Reply-To: <E1GY1e4-000AFI-2T@cs1.cs.huji.ac.il> References: <E1GY1e4-000AFI-2T@cs1.cs.huji.ac.il>
next in thread | previous in thread | raw e-mail | index | archive | help
At 10:34 AM 10/12/2006, Danny Braniss wrote:
> > >short version:
> > >the point im trying to make, is that the same setup, where I only change
> > >the release, is going downhill - with this particular MB.
> >
> > But its not the same necessarily. Some of the settings are different.
> > For example, disable net.inet.tcp.inflight.enable on 6.x if you want
> > it to be the same setting as on 4. This kicks in when the hosts are
> > not directly connected and can hamper performance.
>
>I assume that by directly connected you mean not connected via WAN,
>and so, yes these hosts are on the same vlan, and no,
> net.inet.tcp.inflight.enable=1/0
>make no difference
By directly connected, I mean on the same subnet. Whether the
underlying transport is over a WAN doesnt matter, as long as the two
devices are on the same subnet is what counts. Just to rule out
issues like duplex setting bugs, I would try the two boxes back to
back and make sure its the same subpar performance.
---Mike
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?7.0.1.0.0.20061012160920.12a780d8>