Re: [gentoo-amd64] Re: Anybody having trouble with the via-velocity driver on 2.6.29?

[Kyle Liddell]

IRQ processing smells like the problem - trouble pops up with NFS/ftp/ping/whatever, but only when I saturate the link.  Back to .28 until that "minor" bug is fixed.

Thanks.

On Wed, Apr 01, 2009 at 12:15:43PM +0000, Duncan wrote:
> Kyle Liddell <kyle@××××××××××××××××.net> posted
> 20090401060645.GA4182@athlon, excerpted below, on  Wed, 01 Apr 2009
> 02:06:45 -0400:
>
> > After upgrading the kernel from 2.6.28-gentoo-r3 to 2.6.29, I'm having a
> > weird problem: If I make "light" use of the network (ssh, email, http,
> > etc), no trouble.  But, if I make "heavy" use of the network (say,
> > copying a few GB from a local NFS server to /dev/null), the network
> > interface stops working almost immediately.  ifconfig, mii-tool, the
> > NIC's led, and the switch's LED all say that the link is still up.  But,
> > all my connections time out, ping gets no replies, etc. (I'm using the
> > via-velocity driver for my motherboard's built-in 1GB NIC.)
>
> I'm unsure if your hardware is affected, but there's a known NAPI and
> interrupt related regression in 2.6.29.  It was due to a commit trying to
> fix another bug just a few hours before release, and the discovery and
> subsequent bug trace was one of two subthreads quickly attached to Linus'
> 2.6.29 official announcement.  (FWIW, the other subthread was even more
> fallout from the earlier ext4 data loss over improper shutdown, where
> ext3 was fine.  That has and continues to generate HUGE subthreads all
> over the place, from the Ubuntu bug filing that was one of the first
> reports of it to LKML to /. to LWN.  ext4 may have had the dev- removed
> from the name, but it's not exactly stable as this demonstrates, and
> what's worse, many people including Ted Tso seem to think the problem
> really is NOTABUG.)
>