9.2 ixgbe tx queue hang

Wed Mar 19 19:41:41 UTC 2014

(Sorry for the formatting on that last message, that was weird)

Today I wanted to test the assertion that this is a NFS issue, since we all
seem to be running NFS.

I shut down my NFS daemon in rc.conf, configured the FreeBSD10 iSCSI ctld,
rebooted, and then ran all my tests exclusively from the iSCSI connection
to my FreeBSD-10 box.

 The only other thing I had active on the FreeBSD-10 box was a flood-ping
so I could see if/when the problem occurred.

I still had the problem. It triggered around 40 min into my iometer
benchmark. Continued sporadically for a while, then settled down and didn't
give me problems.

That error behaviour isn't abnormal - I really need to push the SAN to put
it's network into a 'dead and not coming back' mode.

Any thoughts?