I have been trying to do some performance reporting using two different sets of hardware built with the latest ISO.
One the NIC goes off line under load, kernel log shows a problem. BarryG advises there is an issue with the current driver.
I would provide the log entries, but that period of testing in now full of *, wrong UTM. Will need to bring the other UTM up to extract the log entries.
I changed the the NIC for another of the same type and model and got the same results.
Ian
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] e1000e 0000:00:19.0 eth0: Detected Hardware Unit Hang:
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] TDH
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] TDT
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] next_to_use
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] next_to_clean
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] buffer_info[next_to_clean]:
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] time_stamp
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] next_to_watch
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] jiffies
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] next_to_watch.status
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] MAC Status
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] PHY Status
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] PHY 1000BASE-T Status
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] PHY Extended Status
2014:02:08-14:37:56 Cats-speed kernel: [ 2178.936536] PCI Status
2014:02:08-14:37:57 Cats-speed kernel: [ 2179.944779] e1000e 0000:00:19.0 eth0: Reset adapter unexpectedly
2014:02:08-14:38:00 Cats-speed kernel: [ 2183.235199] e1000e: eth0 NIC Link is Up 1000 Mbps Full Duplex, Flow Control: Rx/Tx