Re: e1000 TX unit hang

Phil Oester wrote:

I saw this error (once) in 2.6.13 a few weeks ago:

Jun 23 15:19:01 X kernel: e1000: eth0: e1000_clean_tx_irq: Detected Tx Unit Hang
Jun 23 15:19:01 X kernel:   TDH                  <7e>
Jun 23 15:19:01 X kernel:   TDT                  <7f>
Jun 23 15:19:01 X kernel:   next_to_use          <7f>
Jun 23 15:19:01 X kernel:   next_to_clean        <7e>
Jun 23 15:19:01 X kernel: buffer_info[next_to_clean]
Jun 23 15:19:01 X kernel:   dma                  <16ef9012>
Jun 23 15:19:01 X kernel:   time_stamp           <423845db>
Jun 23 15:19:01 X kernel:   next_to_watch        <7e>
Jun 23 15:19:01 X kernel:   jiffies              <423845db>
Jun 23 15:19:01 X kernel:   next_to_watch.status <0>

so upgraded to 2.6.17 and got a slew of them today - shown below.
E1000 maintainers: any ideas?

The issue is known and worked on, unfortunately no more information yet.

We're tracking the issue and stuff (debug patches, etc) over here (at 
e1000.sf.net):

http://sourceforge.net/tracker/index.php?func=detail&aid=1463045&group_id=42302&atid=447449

For now, try to see if turning off tso using ethtool helps.


Cheers,

Auke