[Top][All Lists]
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
RE: [lwip-users] p->payload == iphdr failed...
From: |
bill |
Subject: |
RE: [lwip-users] p->payload == iphdr failed... |
Date: |
Mon, 10 Nov 2008 09:14:20 -0500 |
> Bill,
> Unless I misunderstand what you're suggesting (quite likely), using
> the PBUF_RAW/PBUF_POOL combination requires that I do the memcpy
> transfer
> from my incoming packet buffer to the pbuf space. That's what I was
> originally doing (and it worked, but seemed inefficient), and
> am now trying to avoid ( see earlier messages on this thread ).
> Am I confused?
I used a mixture. If the pbuf has no chained pbufs (pbuf->next == NULL) I
don't do the copy and use the pointer directly. If there are chains, I do
the memcpy. My Ethernet controller supports multiple output buffers for one
packet transmission but I was unable to get it going and it wasn't a
priority to do so. In my application, the normal mode is there are no
chains in transmit. 99% of my effort has been on optimizing receive
throughput not transmit throughput.
Bill
- Re: [lwip-users] p->payload == iphdr failed..., (continued)
- Re: [lwip-users] p->payload == iphdr failed..., address@hidden, 2008/11/08
- Re: [lwip-users] p->payload == iphdr failed..., Jonathan Larmour, 2008/11/08
- Re: [lwip-users] p->payload == iphdr failed..., Ed Sutter, 2008/11/08
- Re: [lwip-users] p->payload == iphdr failed..., address@hidden, 2008/11/08
- Re: [lwip-users] p->payload == iphdr failed..., Jonathan Larmour, 2008/11/09
- Re: [lwip-users] p->payload == iphdr failed..., Simon Goldschmidt, 2008/11/10
- Re: [lwip-users] p->payload == iphdr failed..., Jonathan Larmour, 2008/11/10
- Re: [lwip-users] p->payload == iphdr failed..., Ed Sutter, 2008/11/08
RE: [lwip-users] p->payload == iphdr failed..., bill, 2008/11/07