[45926] in North American Network Operators' Group
Re: Satellite latency
daemon@ATHENA.MIT.EDU (Clayton Fiske)
Thu Feb 28 12:42:17 2002
Date: Thu, 28 Feb 2002 09:41:38 -0800
From: Clayton Fiske <clay@bloomcounty.org>
To: nanog@merit.edu
Message-ID: <20020228094138.A59327@bloomcounty.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
In-Reply-To: <200202280401.XAA23506@lawyers.grc.nasa.gov>; from mallman@grc.nasa.gov on Wed, Feb 27, 2002 at 11:01:04PM -0500
Errors-To: owner-nanog-outgoing@merit.edu
On Wed, Feb 27, 2002 at 11:01:04PM -0500, Mark Allman wrote:
> > The receiver is the one that informs the sender how large of a
> > window it can accept, so it can be practical for a subscriber
> > installation. It wouldn't be a good idea to park a bunch of
> > servers behind one of these links, but any receiving node that set
> > its TCP receive window to 2x the byte/sec capacity of the link
> > should see decent throughput.
>
> No, you need to set things on both sides. The sender has to buffer
> data until it is ACKed in case it needs to retransmit. So, its
> buffer needs to be as big as the advertised window or the sender
> buffer will effectivly limit the advertised window.
What do you need to set on the send side? If the receiver tells the
sender "my acceptable window is 512k", the sender knows how much it
has to buffer.
-c
