Cry for help!

Corbett J. Klempay cklempay@acm.jhu.edu
Fri Dec 11 01:01:14 1998


Hey all...I *need* to know if anyone out there has been having similar
problems...I have an 8 node cluster up as just 8 separate PC's right now
since our master keeps flaking out...it is:

PII-350
384 MB
2 x 9.1GB IBM Thresher (10K USCSI)
Promise USCSI card (NCR 875-based)
2 Netgear 310's...both are Lite-Ons

The machine works ok if just one card is installed...but if both are in,
it gives these whack CSR messages like:

eth0: The Transmitter stopped! CSR5 is 2678016, CSR6 is 816e2002
eth1: The Transmitter stopped! CSR5 is 2678016, CSR6 is 812e2202

The networking dies under any kind of load (like ping floods or any kind
of heavier network activity)...it can be restarted to get it to work
again, but it just dies again when it gets heavy traffic.

Another note: when we tried putting 1 Lite-On Netgear and 1 Tulip Netgear
in the same machine, we got the whole machine to die with a "Divide Error:
0000" error every time...

We are using 0.90 of the driver.

*ANY* help or clues or anything would be greatly appreciated...we're short
on time here to tinker with things much (middle of finals).  Thanks :)

------------------------------------------------------------------------------
Corbett J. Klempay			         Quote of the Week:
http://www2.acm.jhu.edu/~cklempay  "Advice is what we ask for when we
				    already know the answer but wish we
				    didn't." 

PGP Fingerprint: 7DA2 DB6E 7F5E 8973 A8E7  347B 2429 7728 76C2 BEA1
------------------------------------------------------------------------------