Re: revision RFC 2001 (draft-ietf-tcpimpl-cong-control-00.txt)

[Andi Kleen <[e-mail]>]

In article <Roam.SIMCSD.2.0.4.902950136.15924.kcpoon@jurassic>,
Kacheong Poon <[e-mail]> writes:
>> Yes you can.  In the receiver, you implement a local state variable that
>> keeps track of the largest packet ever received from the peer, and use
>> that in determining how many full size packets you have received, instead
>> of the sending MSS.  I implemented this in UNICOS years ago, and it worked
>> fine for most cases.

> This issue was discussed about a week ago in the Linux networking list.  I
> think they implement something similar, which they called "adaptive receive
> MSS."  So I guess Linux, beside UNICOS, is also conformant to the RFC.
> Anyone from the Linux networking community can confirm this?


All released versions (Linux 2.0, official 2.1) do not conform.

The implementation of adaptive receive MSS will appear shortly in 2.1 
snapshots, and will be included in the upcoming 2.2 release.

Most BSD implementation (at least Free/NetBSD) don't have the problem, 
because they simply send an ACK every second packet, no matter how big
the packets were (this means BSD will send more acks than linux in some
situations)


-Andi