Kieran, I've looked through a log file captured without using DHCP, and the problem is present there as well. In this case the MAC address for a few segments is changed to 00:00:00:00:d5:06. Interestingly, in both log files all the incorrect MAC addresses have the same last two bytes as the correct address.
Regards, Paul Development Engineer Vtech Engineering Corporation 978-974-9944 ----- Original Message ----- From: "Paul Butler" <[EMAIL PROTECTED]> To: "Mailing list for lwIP users" <[email protected]> Sent: March 29, 2007 1:02 PM Subject: Re: Fw: [lwip-users] Dropped Packets on PC receiver withlwip1.1.0Transmitter > Kieran, > > I've had it pointed out to me this morning that the ignored packets in the > log file I sent you have the wrong MAC address! You can confirm this by > looking at segments 49 and 50: note that although the destination IP is > still 192.168.16.36 (which is correct), the MAC address changes from > 00:06:1b:c5:d5:06 (correct) to 00:10:24:28:d5:06 (incorrect). Presumably, > the receiver looks at the MAC address and discards the segment. In this > case, the transmitter retransmits at segment 55 using the correct MAC > address and the system recovers. Later in the same file, segments 133 and > 134 are sent to the same incorrect MAC address, but the retransmissions at > segments 151, 153, 155, and 157 are sent to a new incorrect MAC address > (00:11:43:ea:d5:06). This explains several of the symptoms I have been > seeing. > > Can you think of a reason the destination MAC address would be getting > corrupted? There are ARP segments in the logfile, and presumably more > before I started capturing, but none immediately preceding the corrupted > packets. Given that several identical segments are sent, I have a hard time > believing this is introduced on the wire. > > Regards, > Paul > > ----- Original Message ----- > From: "Kieran Mansley" <[EMAIL PROTECTED]> > To: <[email protected]> > Sent: March 29, 2007 10:22 AM > Subject: Re: Fw: [lwip-users] Dropped Packets on PC receiver with > lwip1.1.0Transmitter > > > > On Thu, 2007-03-29 at 11:00 -0500, Paul Butler wrote: > > > > > I've attached the complete log in wireshark (ethereal) pcap format, > please > > > let me know if you see anything interesting. If you think can get it to > > > post to the list and get some more eyes on it, I'd appreciate it. > > > > I've had a quick look and can't see anything wrong with the packets that > > are getting ignored. > > > > However, if Window's thought they had a bad checksum, it would not send > > an ACK as it wouldn't trust the packet enough to work out where to send > > the ACK to. However ethereal things these packets checksum OK, and > > given that you've captured this at the Window's end of the connection, > > the scope for it going wrong from this point is small. > > > > If you were using linux at this point I'd suggest looking at the network > > stack statistics using "netstat -s" while these packets are coming in - > > it should tell you why it is rejecting them. I'm not sure how to > > achieve something similar on windows, but I guess it probably does keep > > track of how many packets were dropped due to bad checksums etc, and you > > could watch those counters to find out why it's dropping them. > > > > Kieran > > > > > > > > _______________________________________________ > > lwip-users mailing list > > [email protected] > > http://lists.nongnu.org/mailman/listinfo/lwip-users > > > > > > > _______________________________________________ > lwip-users mailing list > [email protected] > http://lists.nongnu.org/mailman/listinfo/lwip-users > _______________________________________________ lwip-users mailing list [email protected] http://lists.nongnu.org/mailman/listinfo/lwip-users
