Packet corruption in re0 (and em0 too)

[Raul]

First of all, it's my first post here ...

Thanks to everybody that made FreeBSD possible.

Christoph Schug escribió:

> I am having the very same problem on a rented Hetzner DS8000 root

Sorry to say, I think that 'me too'

My re0 comes with the motherboard, a Gigabyte GA-MA69G-S3H (AMD 690G 
chipset).

I've tried yesterday with RELENG_7_0 (RC3) and RELENG_7, same behavior 
on both. I've returned to RELENG_7_0 and plug an em0 but, in my case, 
the same behavior happens. I left the box by night compiling CURRENT and 
this morning I've run my 'stress tests' (once again with re0) ... the 
box break to gdb as far I remember (too sleepy, sorry). Well, at least 
no garbage over the link BD.

The fastest method I found to reproduce the problem is receive a 
compresed tar (with good compression ratio) over the network (using nc, 
100 Mbps fdx), pipe through tar that decompress and write it on disk (a 
lot of MB/s and tps looking at 'systat -vm'). The source tar file is 
about 5Gb and link always fails before EOF :|.

The em0 is brand new so no idea if it works right. It would be the first 
one that fail to me (great stuff intel ;) ... I'm pretty confident about 
the switch and allow setting flow control, duplex negotiation, dot1q and 
so on.

I'll be glad to test whatever you suggest on that box.

Regards,
Raul