Kernel panic with Netgear Lite-On PNIC and v0.91

[Joe Robertson]

Is this true for all 2.2.5 kernels? We are running the RedHat updated
release 6.0(kernel 2.2.5-22).. I've noticed that we freeze up a
bit(although ifconfig reports low collisions/no lost packets) during heavy
load, but I dont know if this is due to the network itself, tulip, kernel,
pci architecture, or what.. We are using a NetGear F310TX Rev D-1 100/10
running at 100BaseTx at half-duplex, tulip.c v0.89K(modified to support
the F310TX), RedHat 6.0, kernel 2.2.5-22.
Also, is there an easy-to-use page anywhere on tulip.c tweaks? I want to
configure tulip for get maximum thoroughput, and I'm not sure what ring
buffers and interrupt events and such mean..

Thanks! :)

Joe

On Tue, 15 Jun 1999, Mark Hahn wrote:

> > We have experienced a number of freezes under very heavy
> > load which led me to switch our cluster running kernel 2.2.5 
> 
> 2.2.5 was _horrible_ under load; the nic is not relevant.
> there's a reason we're up to 2.2.10...
>