[vortex] 3C905CX, 2.2.18, Dell Dimension 4100 (P933) ReceiveFailure Fix / Inquiry

Joe Rouvier joe@netli.com
Wed, 17 Jan 2001 02:03:02 -0800


Donald Becker wrote:
> 
> On Tue, 16 Jan 2001, Samuel Madden wrote:
> 
[...]
> You misunderstand the loops.  They are not software timing loops.  They
> are PCI transaction counts.  PCI transactions are often the most
> appropriate measure.
>
> > I'm wondering:
> > 1) why isn't some more precise timing mechanism being used here?
> 
> Most of the operations should take zero apparent time.  I check the loop
> count for all operations when I write a driver, and it's rare that a
> chip actually requires more than one loop iteration.

If it's rare for a device to take more than one PCI transaction to do
something, do you think the ~30000 transaction count for RxReset on the
3c905cx means the current driver doesn't init the card correctly?  Or is
the new chip just slow on that command?

> The loop counts exist to make certain the driver doesn't hang on broken
> or missing hardware.
>
> > 2) what are the performance implications of making the rx timeouts
> >       significantly higher?
> 
> Bad.  The kernel is sitting in a very long timing loop.  In some cases
> this occurs with many interrupts blocked due to rotating interrupt
> priority.

But the longer loop is only used on TxReset, RxReset, TotalReset,
DownStall and RxDiscard.  Aren't these commands sent very rarely?
(referring specifically to the 2.2.19-pre2 driver with Adam M's
wait_for_completion() changes)

> The patches that increase the timing loop counts are for experimental
> and verification purposes only.  Please do not submit them for
> inclusion in a main-line kernel!
>
> > 3) does anyone have suggestions for what optimal values might be here?  i've
> >       increased them quite a lot and am not really interesting in trying
> >       all the permuations manually.
> 
> Not for the CX board -- some aspect of the design appears to have
> changed dramatically from the earlier chips.

I recently purchased 6 of the Dells with this card.  We will be writing
networking software on 'em.  This tends to make having a reliable NIC
kind of nice.  Should I yank the cards and get something else?  If so,
any recommendations?

I don't suppose anyone has heard anything from 3com?

-----
"Computer games don't affect kids, I mean if pac man affected us as
kids, we'd all be running around in darkened rooms, munching pills
and listening to repetitive music."  --Unknown