Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 6 Jun 2002 05:58:25 -0700
From:      Greg Rumple <grumple@zaphon.llamas.net>
To:        Bryce <bryce@burnip.net>
Cc:        Paul Dlug <paul@nerdlabs.com>, freebsd-stable@freebsd.org
Subject:   Re: fxp0 timeout errors
Message-ID:  <20020606125825.GD55256@zaphon.llamas.net>
In-Reply-To: <002401c20d1f$a3931d70$8000000a@Bryce>
References:  <200205271231.29155.paul@nerdlabs.com> <002401c20d1f$a3931d70$8000000a@Bryce>

next in thread | previous in thread | raw e-mail | index | archive | help
I have a stack of dual port intel 10/100 cards that this happens on time
and time again.  I after spending weeks trying to solve this problem (it
does not happen under Linux btw) gave up finally, and purchased a
different card for the machines that run FreeBSD.  The circumstances to
make this happen purely involve doing heavy volumes of ethernet traffic
(a ping -f or a nice large rsync suffice).  It will immediately happen,
and sometimes it will recover and work again after 2-3 minutes,
sometimes it'll stay dead forever.  It purely seems limited to this
stack of cards, as I have other cards that do not suffer from the same
problem (single port cards).  If anyone has any clues, I would be glad
to assist in helping track this down as well.

Greg

* Bryce (bryce@burnip.net) [020605 23:02]:
> I've ran into the same problem, on IBM X series servers.  (x340s, x342s)
> 
> With IBM supplied nics mind you.  Other older cards work great.
> 
> The first time I ran into this problem, I swapped out the "new" cards for
> older working ones, in a hope the problem would get resolved...
> 
> I'm also more than willing to help debug this.  At the moment, I've
> encountered the problem with 4.5 Stable.  (I have yet to make the jump to
> 4.6.)
> 
> Currently running an SMP kernel, Mylex Acceleraid controller, and IBM disks.
> 
> Bryce
> 
> 
> ---
> bryce@burnip.net
> 
> Computers let you make more mistakes faster than any other invention in
> human history, with the possible exception of handguns and tequila. - Mitch
> Radcliffe
> 
> 
> ----- Original Message -----
> From: "Paul Dlug" <paul@nerdlabs.com>
> To: <freebsd-stable@freebsd.org>
> Sent: Monday, May 27, 2002 5:31 AM
> Subject: fxp0 timeout errors
> 
> 
> > I posted this a while back but didn't get much of an answer beyond (use a
> 3com
> > card instead). I have a bunch of Dell 1550's with on board Intel NIC's. I
> > received the following messages on the console (below), any attempt to
> ping
> > results in the message "No buffer space available."
> >
> > May 14 16:03:12 web5 /kernel: fxp0: DMA timeout
> > May 14 16:03:12 web5 /kernel: fxp0: DMA timeout
> > May 14 16:03:12 web5 /kernel: fxp0: SCB timeout: 0x10 0x0 0x80 0x0
> > May 14 16:03:12 web5 /kernel: fxp0: DMA timeout
> >
> > The first box this happened on I chalked it up to a bad NIC or PCI bridge
> and
> > had Dell replace the motherboard, the problem hasn't occured since. A week
> > after the same thing happend on another box. This, combined with a number
> of
> > other posts about these fxp problems makes me suspect this is an OS level
> > problem rather than hardware. This occured under a cvsup'd version of
> > 4.5-STABLE, I then upgraded to 4.6-PRERELEASE as of a few days ago and the
> > problem persisted. The box will be up anywhere from 15min to an hour
> before
> > the above messages appear and send it out of service.
> >
> > pciconf -l:
> > chip0@pci0:0:0: class=0x060000 card=0x00000000 chip=0x00081166 rev=0x23
> > hdr=0x00
> > chip1@pci0:0:1: class=0x060000 card=0x00000000 chip=0x00081166 rev=0x01
> > hdr=0x00
> > chip2@pci0:0:2: class=0x060000 card=0x00000000 chip=0x00061166 rev=0x01
> > hdr=0x00
> > chip3@pci0:0:3: class=0x060000 card=0x00000000 chip=0x00061166 rev=0x01
> > hdr=0x00
> > fxp0@pci0:1:0:  class=0x020000 card=0x00da1028 chip=0x12298086 rev=0x08
> > hdr=0x00
> > fxp1@pci0:2:0:  class=0x020000 card=0x00da1028 chip=0x12298086 rev=0x08
> > hdr=0x00
> > none0@pci0:3:0: class=0x030000 card=0x00df1028 chip=0x47521002 rev=0x27
> > hdr=0x00
> > isab0@pci0:15:0:        class=0x060100 card=0x02001166 chip=0x02001166
> > rev=0x50 hdr=0x00
> > atapci0@pci0:15:1:      class=0x01018a card=0x00000000 chip=0x02111166
> > rev=0x00 hdr=0x00
> > ahc0@pci2:5:0:  class=0x010000 card=0x00df1028 chip=0x00cf9005 rev=0x01
> > hdr=0x00
> > ahc1@pci2:5:1:  class=0x010000 card=0x00df1028 chip=0x00cf9005 rev=0x01
> > hdr=0x00
> >
> >
> > It looks like quite a few people are having similiar problems with the fxp
> > cards, is anyone close to a fix? Please let me know if there's anything I
> can
> > do to assist in debugging this issue.
> >
> > Thanks,
> > Paul
> >
> > P.S. The motherboard is SMP capable but only has one processor installed,
> SMP
> > is turned off in the kernel configuration. Disks are on an adaptec aic7899
> > SCSI controller. Server is an NFS client using TCP mounts. Network is
> > 100mbps, switched, fxp0 properly autonegiotates to 100mbps/full duplex.
> >
> >
> > To Unsubscribe: send mail to majordomo@FreeBSD.org
> > with "unsubscribe freebsd-stable" in the body of the message
> >
> 
> 
> To Unsubscribe: send mail to majordomo@FreeBSD.org
> with "unsubscribe freebsd-stable" in the body of the message
> 

-- 
Greg Rumple
grumple@zaphon.llamas.net

To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20020606125825.GD55256>