Ok, it might simply be that my setup (and that of a few others
I talked to) isn't optimal, and that the numbers I am seeing
are simply too low. It's been a while since I tested a wide
variety of gig-e hardware.

Btw, with a faster/wider PCI bus, I meant faster than
32/33 which is still the default in most boards, although
that's changing now.

I'm interested in seeing performance numbers for NetBSD on
exactly the same hardware.

> That'd be interesting, esp. if I can collar enough machines to run
> some head-to-head tests.

Ok, I'll put up a tarfile.

> Also, there are some bug workarounds we should get into the driver.
> Do you have access to broadcom docs? Or workarounds for the various
> hardware bugs (checksum offload, 5701 DMA bugs, or the patch for 5701
> firmware, as uploaded by various Linux drivers?)

My version has been tested on sparc64, being a big-endian, 64bit
platform with some DMA constraints, it is a good testcase for
a properly ported/written driver.

I have seen comments on the hw checksum problem (it's disabled
for receiving in the driver), I haven't heard about the other
ones. If you have some pointers to those, I'll look into that.

- Frank

-- 
Frank van der Linden                           fvdl@wasabisystems.com
======================================================================
Quality NetBSD CDs, Support & Service.   http://www.wasabisystems.com/