bge watchdog timeouts still happening

Paul Mather paul at gromit.dlib.vt.edu
Fri Sep 15 12:55:34 PDT 2006


On Fri, 2006-09-15 at 12:33 -0700, Kent Stewart wrote:
> On Friday 15 September 2006 09:28, Herve Boulouis wrote:
> > Le 15/09/2006  18:05, Gleb Smirnoff a écrit:
> > > H> bge0: <Broadcom BCM5700 B2, ASIC rev. 0x7102> mem
> > > 0xfeb00000-0xfeb0ffff irq 17 at device 8.0 on pci1 H> miibus0: <MII
> > > bus> on bge0
> > > H> brgphy0: <BCM5401 10/100/1000baseTX PHY> on miibus0
> > > H> brgphy0:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX,
> > > 1000baseTX, 1000baseTX-FDX, auto H> bge0: Ethernet address:
> > > 00:06:5b:1a:7f:4a
> > >
> > > Is it integrated or not? I've got exactly the same NIC and I can
> > > try to reproduce the problem if you describe the workload.
> >
> > Yes, it's the onboard bge. Workload is 10-25 Mbit/s of web hosting.
> 
> It seems to be at the top of the tree somewhere because people are also 
> seeing the watchdog timeouts on em and I get them on the gigabit re's.
> 
> I got them downloading the kde-3.5.4 distfiles on a 768kb DSL line. I 
> had setiathome running, which keeps the cpu useage close to 100%.

FWIW, I get repeated "watchdog timeout" errors on 6-STABLE with a
dc-based Cardus NIC (Netgear FA511).  The worst behaviour I observed was
under heavy NFS load, with the link being unavailable for extended
periods of time.  Mostly, though, the problem manifests itself when the
card is inserted and the interface is trying to be brought up via DHCP
using dhclient, as if the NIC is not being initialised properly,
perhaps.

I don't know if this is the same problem, but I thought I'd mention it.

Cheers,

Paul.
-- 
e-mail: paul at gromit.dlib.vt.edu

"Without music to decorate it, time is just a bunch of boring production
 deadlines or dates by which bills must be paid."
        --- Frank Vincent Zappa


More information about the freebsd-stable mailing list