Wanted to update this thread to confirm, as Jack suspected, the issue
we where seeing was something much more ingrained that a driver issue.
It turned out this problem in the tcp reassembly code which is likely
due to insufficient size of net.inet.tcp.reass.maxsegments.
The result is even with just 2 decent sized tcp streams a single lost
packet can cause an unrecoverable situation resulting in the session
stalling and eventually ~60 seconds later being reset by the sender.
Increasing nmbclusters which in turn increases maxsegments eliminated
the problem e.g.
sysctl kern.ipc.nmbclusters=262144
kern.ipc.nmbclusters: 25600 -> 262144
For more information see the thread:-
tcp failing to recover from a packet loss under 8.2-RELEASE?
http://lists.freebsd.org/pipermail/freebsd-net/2011-August/029491.html
Regards
Steve
================================================
This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it.
In the event of misdirection, illegible or incomplete transmission please
telephone +44 845 868 1337
or return the E.mail to [email protected].
_______________________________________________
[email protected] mailing list
http://lists.freebsd.org/mailman/listinfo/freebsd-net
To unsubscribe, send any mail to "[email protected]"
