Date: Mon, 03 Mar 1997 11:36:34 +0500 From: A JOSEPH KOSHY <koshy@india.hp.com> To: Michael Smith <msmith@atrad.adelaide.edu.au> Cc: hackers@FreeBSD.org, jrb@cs.pdx.edu Subject: Re: [driver testing] Odd network behaviour? Message-ID: <199703030636.AA123670994@fakir.india.hp.com> In-Reply-To: Your message of "Mon, 03 Mar 1997 00:53:40 %2B1030." <199703021423.AAA20864@genesis.atrad.adelaide.edu.au>
next in thread | previous in thread | raw e-mail | index | archive | help
>>>> "Michael Smith" <msmith@atrad.adelaide.edu.au> writes Hi Mike, > wl2 is the 'fast' host sending, and 'wl1' is the slow host receiving; the > trace is taken on wl2. > > To my eyes, this looks like the packet 302957:304417 was lost somehow by > the receiver, and was eventually resent. But why the long silence > before the retransmit? Hiccups usually seem to occur after three or > four back-to-back packets from the 'fast' system (but not always), so > I guess there's some overrun happening somewhere. > use, and it's got me stumped. Any ideas would be greatly appreciated. I've seen similar behaviour on NE2000 compatible cards too. Turning on BPF and running tcpdump at the recieving end shows that the retransmitted packet had actually been accepted from the interface earlier. It somehow hadn't made it to the higher network layers. So whatever the bug is, its probably not 82586 specific. How to repeat: take a tcpdump of incoming traffic (say an FTP GET) on a busy ethernet, look for retransmits for packets that had been already read in. Koshy <koshy@india.hp.com> My Personal Opinions Only
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199703030636.AA123670994>