Re: [Xen-devel] help with horrible network failures

[Rob Gardner <rob.gardner@xxxxxx>]

Jon Mason wrote:
> On Wednesday 02 March 2005 04:52 pm, Rob Gardner wrote:
>
> > Nivedita Singhvi wrote:
> >
> > > Rob Gardner wrote:
> > >
> > > > The machine with the problem:
> > > > Intel e100 nic
> > > > 1.7 Ghz Xeon
> > > Yep, practically all instances of this problem were
> > > with the e100. Unfortunately, the current version
> > > of the driver no longer has NAPI as a dynamically
> > > tunable parameter via ethtool. It can be disabled
> > > via a kernel config parameter (CONFIG_E100_NAPI).
> > > You could recompile and see if the problem disappears.
> > > (Not a real fix).
> > My current configuration has:
> > # CONFIG_E100_NAPI is not set
> >
> > Isn't that the same as it being disabled? Or should I change it to:
> > CONFIG_E100_NAPI=n
>
> Yes, that is disabled, but from my previous statement that does nothing in 
> e100 (as it is enabled regardless of that compile flag).  I think there have 
> been a few driver fixes that were dropped in the newly released 2.6.11.  If 
> you can't change the adapter, it might be worth trying.  
So... the answer is to try linux kernel 2.6.11? The latest xen-unstable 
still looks like it's using 2.6.10, and so does xen-2.04. So I don't 
understand what exactly  I should try next.
> NAPI is a compile time option, not a runtime option.  so, it must be enabled 
> during kernel compilation.  
But you just said that it does nothing in e100. Or do you mean I need to 
modify the e100 driver directly?

Rob






-------------------------------------------------------
SF email is sponsored by - The IT Product Guide
Read honest & candid reviews on hundreds of IT Products from real users.
Discover which products truly live up to the hype. Start reading now.
http://ads.osdn.com/?ad_id=6595&alloc_id=14396&op=click
_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxxx
https://lists.sourceforge.net/lists/listinfo/xen-devel