On Sun, Jul 29, 2007 at 06:59:26AM +0100, Darryl L. Miles wrote: > The problems start around time index 09:21:39.860302 when the CLIENT issues > a TCP packet with SACK option set (seemingly for a data segment which has > already been seen) from that point on the connection hangs.
I'd say most likely scenario is the SERVER is behind a Cisco Pix firewall, which has known bugs in handling packets with sack option. By default the Cisco has sequence number randomization enabled, but it's a half-assed implementation which doesn't bother adjusting the sequence numbers inside sack options. This has been reported to Cisco, and they don't seem to care. As a workaround, you can do this: echo 0 > /proc/sys/net/ipv4/tcp_sack and it will probably fix it up. It'd be really nice, however, to have a per-route option for sack, similar to how we can clamp window scaling per route. Something like the below ip r a <host> <gw> <nosack> Phil - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to [EMAIL PROTECTED] More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/