lwip-users
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [lwip-users] Microblaze and lwIP


From: Caglar Akyuz
Subject: Re: [lwip-users] Microblaze and lwIP
Date: Tue, 08 May 2007 22:17:15 +0300
User-agent: Thunderbird 1.5.0.8 (X11/20060911)

Kieran Mansley wrote:
> On Tue, 2007-05-08 at 15:06 +0100, Kieran Mansley wrote:
> 
>> Unfortunately, this is just a property of TCP, rather than either lwIP
>> or windows having a bug.  I think linux has some clever stuff in it to
>> notice when the delayed ACK protocol would harm performance and so is
>> able to turn it off in cases like this.
> 
> A colleague has pointed out that you may be able to avoid this problem,
> if you're using the sockets API, by setting the TCP_NODELAY socket
> option.  This won't solve the issue in all cases, but may be good enough
> for your needs.

I have run into a similar problem and I solved the problem on LwIP side
forcing packets to be sent immediately using tcp_output(). On the PC
side(both Windows and Linux hosts) I tried setting TCP_NODELAY as you
have pointed, i.e. I disabled Naggle's algorithm. After a few months of
test, I realized that I'm facing some lost packets issue on the PC side.
When I removed disabling Naggle's algorithm part, I was able to manage
recovering packet loss rate a little bit. I'm not sure if it's true or
not, but I guess Windows and Linux stacks can show this kind of behavior.

Somebody please correct me if I'm wrong, as this problem really disturbs me.




reply via email to

[Prev in Thread] Current Thread [Next in Thread]