Re: heavy nfs[4]] causes fs badness Was: 2.6.20-rc4: known unfixed regressions (v2)

[florin@iucha.net (Florin Iucha)]

On Sun, Jan 14, 2007 at 11:11:13PM -0300, Horst H. von Brand wrote:
> Florin Iucha <florin@iucha.net> wrote:
> 
> [...]
> 
> > Based on this info, I think we can rule out any USB.  I will try
> > testing with NFS3 to see if the problem persists.  Unfortunately there
> > is no oops or anything in "dmesg".
> 
> Take a look at bz #7796, a NFS bug + fix. But my feelin is that this is
> older.

The reported had and oops?  Luxury!  I get nothing ;)

I am testing again, this time on 2.6.20-rc5 compiled with extra debug
and I got a couple dozens of:

   "eth0: too many iterations (6) in nv_nic_irq."

in the kernel log.

florin

-- 
Bruce Schneier expects the Spanish Inquisition.
      http://geekz.co.uk/schneierfacts/fact/163

Attachment: signature.asc
Description: Digital signature