Re: [lwip-users] Incorrect Nagle implimentation

[Kieran Mansley]

On Thu, 2005-11-24 at 14:00 +0000, Bob Grice wrote:
> While investigating the tcp throughput on my LWIP implimentation, I noticed
> a distinct stop & restart occurring at a regular 200ms interval. Furthur
> investigation led me to LWIP's implimentation of Nagle's algorithm in
> function do_write( ).
>  
> The code currently delays transmission until the timer expires whenever
> there is outstanding acks (unless TF_NODELAY), whereas Nagle requires
> transmission only to be delayed if there is outstanding acks and you can't
> send a MSS sized segment.

I agree with your interpretation of the Nagle algorithm, and wonder why
we don't currently implement it correctly - I haven't got the lwIP
source to hand, so can't really comment on that at the moment.  However,
I can't see any glaring problem with your suggested fix, so don't see
why someone shouldn't test it and see if it works as advertised.  Any
volunteers?

Kieran