Would the same solution apply to a 3COM 905B NIC? I have been experiencing
the same problems.
> -----Original Message-----
> From: tom minchin [mailto:tom@interact.net.au]
> Sent: Tuesday, July 27, 1999 1:30 AM
> To: Patrick Kormann
> Cc: 'squid-users@ircache.net'
> Subject: Re: Ethernet Problem
>
>
> On Tue, Jul 27, 1999 at 09:24:03AM +0200, Patrick Kormann wrote:
> > Hi!
> >
> > I guess this doesn't strictly belong to the squid mailinglist.
> On the other
> > hand, this only happens on each of our 4 linux proxies, not on any other
> > linux machine.
> > Regurarly, out of blue sky, we get the following problem:
> > Jul 27 04:09:29 proxy1 kernel: eth0: Transmit timed out: status
> 0050 0080
> > at 175049833/175049848 command 000c0000.
> > Jul 27 04:09:29 proxy1 kernel: eth0: Trying to restart the
> transmitter...
> > Jul 27 04:09:34 proxy1 kernel: eth0: Transmit timed out: status
> 0050 0090
> > at 175049833/175049848 command 000c0000.
> > Jul 27 04:09:34 proxy1 kernel: eth0: Trying to restart the
> transmitter...
> > Jul 27 04:09:39 proxy1 kernel: eth0: Transmit timed out: status
> 0050 0090
> > at 175049833/175049848 command 000c0000.
> > Jul 27 04:09:39 proxy1 kernel: eth0: Trying to restart the
> transmitter...
> > Jul 27 04:09:44 proxy1 kernel: eth0: Transmit timed out: status
> 0050 0090
> > at 175049833/175049848 command 000c0000.
> > Jul 27 04:09:44 proxy1 kernel: eth0: Trying to restart the
> transmitter...
> >
>
> You have intel eepro100s? Their driver/hardware is buggy under Linux and
> high load (eg lots of UDP), I found that the latest kernel 2.2.10 and
> sticking this in conf.modules fixed it most of the time:
>
> alias eth0 eepro100
> options eepro100 multicast_filter_limit=3
>
> The only other thing left to you is to have a logger that detects that
> kind of error in the logs and reboots. Or replace the intel cards with
> something else.
>
> tom@interact.net.au
>
>
Received on Wed Jul 28 1999 - 12:08:06 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:47:36 MST