Re: 2.6.15.1: persistent nasty hang in sync_page killing NFS (ne2k-pci / DP83815-related?), i686/PIII

[Nix <nix@esperi.org.uk>]

On Sun, 29 Jan 2006, nix@esperi.org.uk whispered secretively:
> On Sat, 28 Jan 2006, Trond Myklebust stipulated:
>> http://blogs.sun.com/roller/page/shepler?entry=port_623_or_the_mount
> 
> That's specific to one port. As the capture (from the server side this
> time) shows, the NFS client is using all sorts of ports on the client,
> and port 2049 on the server; acks are not required, this being UDP.
> 
> I'm going to rebuild with NFS-over-TCP support and see if that changes
> anything next. A bit pointless on a clean switched network, but it's
> hardly going to be noticeable...

Further info, possibly in support of your suggestion, possibly not: the
problem does *not* occur with NFS-over-TCP. So it's specific to UDP,
this hardware (perhaps motherboard or network card, see the .config
diff), *and* NFS. Other UDP stuff (e.g. DNS) gets through fine in both
directions; NFS works with TCP; and the whole lot worked before the
hardware was changed.

At this point though I'd say that it's really rather unlikely to be
purely hardware at fault.

> I'll get another network card on Monday and swap out the DP83815, and
> see if *that* changes anything.

No need now, I can make it appear and disappear on demand.

-- 
`I won't make a secret of the fact that your statement/question
 sent a wave of shock and horror through us.' --- David Anderson