[tulip] stall on tulip card

Donald Becker becker@scyld.com
Mon, 8 Jan 2001 03:57:34 -0500 (EST)


On Sun, 7 Jan 2001, Hank Barta wrote:

>     well until I started running 'setiathome' on this box. Since
>     then, I've had three lockups of the tulip card Here is all of
>     the information I can think of that seems to be pertinent:

> 	I could find no indication of problems in the logs.

What was happing with the counts in /proc/net/dev?

>     This last time, I recorded the results of 'tulip-diag' before
>     and after I restarted the network:
...
>   The transmit threshold is 256.
..
>   The transmit threshold is 128.

The only difference is with the transmit threshold, which was increased in
the error case.  There was a report that manipulating Tx threshold was
causing a problem with the Centaur, but I was unable to reproduce the
problem.  If this really is the problem, we will have to figure out if the
hang is caused by the initial underrun, or the attempt to increase the Tx
threshold value.

See the state with  'tulip-diag -aa' might be useful.

Thanks for the good report.

Donald Becker				becker@scyld.com
Scyld Computing Corporation		http://www.scyld.com
410 Severn Ave. Suite 210		Second Generation Beowulf Clusters
Annapolis MD 21403			410-990-9993