|
From: | Taranowski, Thomas (SWCOE) |
Subject: | RE: [lwip-users] LWIP Delay between Consecutive Packets |
Date: | Fri, 3 Oct 2008 15:09:52 -0400 |
This sounds to me like the driver isn’t
sending out packets right away. I’m not specifically familiar with the Xilinx board,
but Ethernet MACs are all pretty similar in design. I’d review the driver to
ensure that the bit to mark the send buffer ready to send (Ready, Own, etc.) is
set correctly when a packet is enqueued in the send queue, and that the
hardware isn’t pending on something to be done. From:
address@hidden
[mailto:address@hidden On Behalf Of Gary Olson Hi
Kieran and Bill,
I thought I had setup checksum offloading but I found that the software
settings had to be set up as well as the hardware. This did improve my
bandwidth about 20 percent but still To
slow for my needs. Still have delays between my UDP packets around 400
us. My bandwidth for TCP transfers are around 70 – 80 Megabits per
second. I
am using RAW API and a ML505 Xilinx Board with a Microblaze processor running
at 100 Mhz and PLB 125 Mhz I can send 3 Picture Frames in .8 seconds
one frame being 2 Million Bytes or 16 million bits. 3 *
16 Million bits = 54 million bits in .8 seconds = 67.5 million bits per
second using TCP. Here
is my settings: BEGIN LIBRARY PARAMETER LIBRARY_NAME
= lwip PARAMETER LIBRARY_VER
= 3.00.a PARAMETER
PROC_INSTANCE = microblaze_0 PARAMETER tcp_mss =
4560 PARAMETER
ip_frag_max_mtu = 5500 PARAMETER
ip_reass_bufsize = 9000 PARAMETER mem_size =
1000000 PARAMETER
pbuf_pool_bufsize = 4600 PARAMETER tcp_wnd =
5560 PARAMETER tcp_snd_buf
= 25000 PARAMETER
tcp_tx_checksum_offload = true PARAMETER
tcp_rx_checksum_offload = true PARAMETER
pbuf_pool_size = 550 PARAMETER memp_n_pbuf =
32 END I have been using LWIP I think Version 3,
-llwip4 is my link against library command. Additionally I played with tcp_wnd and tried raising
it all the way to 60000 it might have helped some but brought it back down
because Some one said I should have the FIFO size for it in
my hardware MAC. I did notice that when I brought the tcp_wnd that the
GAP started to Vary from shorter to longer in a serial type of
sequence. Thank You, Gary Olson |
[Prev in Thread] | Current Thread | [Next in Thread] |