[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [lwip-users] performance in sending / receiving
From: |
Kieran Mansley |
Subject: |
Re: [lwip-users] performance in sending / receiving |
Date: |
Thu, 15 Feb 2007 15:08:09 +0000 |
On Thu, 2007-02-15 at 16:03 +0100, Robert Goeffringmann wrote:
> Is there anything like a suggested model for those thread priorities?
Not from me, but someone else might have a suggestion.
> I also wrote a checksum routine in assembly, but no matter if I use that one
> or lwip's most basic one doesn't have any difference at all on either
> sending- or receiving speed. So I suppose I can assume that cpu power is not
> the bottleneck... right?
It's an indicator rather than proof, but does suggest that CPU isn't
exhausted (assuming that your assembler checksum routine is any good of
course!)
If you can measure the latency of the network (e.g. using ping) then
that combined with the tcp window size will give a theoretical max TCP
bandwidth. It might be that you are just limited by this.
Kieran
- [lwip-users] performance in sending / receiving, Robert Goeffringmann, 2007/02/13
- Re: [lwip-users] performance in sending / receiving, Kieran Mansley, 2007/02/14
- Re: [lwip-users] performance in sending / receiving, Kieran Mansley, 2007/02/14
- Re: [lwip-users] performance in sending / receiving, Robert Goeffringmann, 2007/02/15
- Re: [lwip-users] performance in sending / receiving,
Kieran Mansley <=
- RE: [lwip-users] performance in sending / receiving + tcp_tmr, Taranowski, Thomas \(SWCOE\), 2007/02/15
- Re: [lwip-users] performance in sending / receiving + tcp_tmr, Robert Goeffringmann, 2007/02/16
- RE: [lwip-users] performance in sending / receiving + tcp_tmr, Taranowski, Thomas \(SWCOE\), 2007/02/16
- RE: [lwip-users] performance in sending / receiving, Goldschmidt Simon, 2007/02/16
RE: [lwip-users] performance in sending / receiving, Taranowski, Thomas \(SWCOE\), 2007/02/14