Date: Fri, 20 Sep 2002 20:06:49 -0700 (PDT) From: Julian Elischer <julian@elischer.org> To: Barney Wolff <barney@tp.databus.com> Cc: net@FreeBSD.ORG Subject: Re: Tcp question. Message-ID: <Pine.BSF.4.21.0209201945490.21069-100000@InterJet.elischer.org> In-Reply-To: <20020921023043.GA90973@tp.databus.com>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 20 Sep 2002, Barney Wolff wrote: > I think you need to separate out tcp behavior from ssh behavior. > A & C are clearly not the same tcp/ssh implementation, and I'm > not even sure B is consistent between the two runs - for example, > B's window size is different, as is the amount of data it sends > before setting the P bit. The problem is not that the far end is slow to respond, but that B, the freebsd box, doesn't send more data immediatly when the ACKs arrive for data it's already sent. It waits around for another 3mSecs before sending more data. > > With ssh doing compression & encryption, cpu power becomes visible > at lan speeds. The 1380 mss from C may also indicate extra proto > layers we're not seeing. And are you sure there's not a 10 mbit > link somewhere between B and C? It's a 100Mb link on both sides of the Cisco PIX firewall between B and C The link that gets 7MB/sec goes through 2 routers including firewall, but they are FreeBSD boxes. > > On Fri, Sep 20, 2002 at 05:53:49PM -0700, Julian Elischer wrote: > > > > OK so I have 3 machines: > > > > > > A------router--------B-------router--------C > > > > > > if I send data from B to A I see 7MB/sec. > > if I send data from B to C I see 700KB/sec > > -- > Barney Wolff > I'm available by contract or FT: http://www.databus.com/bwresume.pdf > To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-net" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSF.4.21.0209201945490.21069-100000>