Any way to solve "watchdog timeout" on network-IF?

KAWAGUTI Ginga ginga-freebsd at
Wed Jan 10 09:11:47 UTC 2007


I'm using FreeBSD/i386 6-stable on HP DL360G5 server,
and getting "Watchdog timeout" & "link state changed to DOWN/UP"
messages shown below.

bce0: /usr/src/sys/dev/bce/if_bce.c(5000): Watchdog timeout occurred, resetting!
bce0: link state changed to DOWN
bce0: link state changed to UP

[System I'm using:]

  * CPU Xeon 51xx, 
  * Intel 5000X chipset
  * NIC:  bce ( 2006/10/24)
     bce0: <Broadcom NetXtreme II BCM5708 1000Base-T (B1), v0.9.6> 
           mem 0xf8000000-0xf9ffffff irq 16 at device 0.0 on pci3
     bce0: ASIC ID 0x57081010; Revision (B1); PCI-X 64-bit 133MHz
     miibus0: <MII bus> on bce0
     brgphy0: <BCM5708C 10/100/1000baseTX PHY> on miibus0
     brgphy0:  10baseT, 10baseT-FDX, 100baseTX, 100baseTX-FDX, 1000baseTX, 1000baseTX-FDX, auto
     bce0: Ethernet address: 00:18:71:73:c5:5a

Give UDP generating load (ports/net/rude was used).

  Test configuration:
  [FreeBSD]-(bce)--- 100BaseTX-switch ---(em)[FreeBSD]
   packet genarator   -------------->    packet receiver
   70Mbps UDP, 1400Byte packet * 6000pps.

Then, the above "Watchdog timeout" message occurs _SOMETIMES_.
Maybe once a week, sometimes 10times/day.
I've tested with 3 hardware(all HP DL3x0 server with BCM5708 chip),
and all of them seems to suffer with this.

I've suspected new bce-NIC, and tried with bge cards
(also with FreeBSD 6-stable).
However, similar message also happens with bge(other network IFs also).
Next, I've tried with other cable, other ether-switch, but 
they still seems to happen _sometimes_.

Are these "Watchdog timeout" events common and happening everywhere else?
Or am I doing something wrong?

Searching the -stable archive, there seems some other people
suffering with this:

2006.11.29 [Re: Dell PE 1950 bce NICs revisited]
2006.12.14 [em watchdog timeout]

Thank you.

More information about the freebsd-stable mailing list