"Transmit timed out" with EtherExpress Pro100B

[Osma Ahvenlampi]

"Robert G. Brown" <rgb@phy.duke.edu> writes:
> Oooo, brutal!  I have to say that I use the eepro100 in (16) Dell
> poweredge 2300's and just benchmarked them full duplex through a switch
> at 95.6 Mbps (data only) or 98.5% of wire speed, accounting for the

Interesting. I benchmarked the machine against another with a 3c905
using a crossover wire, with the result of 94 Mbps. I agree there's
nothing wrong with the speed of the card (actually, I was surprised
the 3com was that fast).

> headers.  This is going both ways at once, so the aggregate bandwidth
> was 191 Mbps.  The network is stable enough that several of the systems
> were up for months diskless (while awaiting a functioning aic7xxx).

In a network that has multicast traffic?

> The difficulties experienced on a poweredge 2300 could easily come from
> a mixture of a kernel swap/mmap bug, the aic7xxx 7890 driver (which is
> still pre-release, after all) and the eepro100.  I don't deny that there

This is true. Since I can't boot the machine without the aic7xxx
pre-release driver (which is in its last beta before the real release,
so if there is a bug in it, it should be pointed out ASAP), it's
difficult for me to eliminate that variable. PowerEdge has the eepro
and the aic7xxx on different interrupts, though..

Anyway, I just patched the eepro100 driver to
multicast_filter_limit=0, re-enabled appletalk, and put two machines
pinging the pe2300 constantly. If I don't see the problem within one
hour, I would consider it pretty clear what's broken. With only
surface knowledge of Linux internals and absolutely no knowledge of
the Intel Speedo3 chip, I can't do anything about a fix, though.

> are likely some problems in the driver and I'm sure Donald is aware of
> them, but most of the problems that are left very likely multiple layers
> of the system, and not just the drivers themselves.  You also have to be

If the other poster is right, and this problem can be demonstrated
simply by running gated, that doesn't leave THAT many layers. Pretty
much the minimum layers for a functioning IP stack, in fact.

While I would personally like to see this work, and do something to
reach that goal, I simply can not justify the hours spent in internal
hacking instead of business. It's cheaper for us to buy a new card for
the machine. I'm just afraid that next time I'm configuring a server,
I'll have the same problem in front of me.

-- 
Chemistry professors never die, they just smell that way!
Osma Ahvenlampi <oa@spray.fi>