[Bug 131737] Re: network device (nVidia MCP55, forcedeth) stops sending packets

Paul Weaver paul.weaver.uk at gmail.com
Fri Jul 11 16:43:18 UTC 2008


I've had a similar issue with an MCP55 ethernet driver, on a different
motherboard (a generic PC one) in a more recent kernel -- after about
250 days of uptime, receiving about 70-80GBytes/day, transmitting about
90-100GBytes per day the network just fell off, not even responding to
pings

ifdown eth1 worked, but ifup eth1 hung, a reboot brought the machine
back.

Jul 11 12:52:00 newsjtcfs99 -- MARK --
Jul 11 13:12:01 newsjtcfs99 -- MARK --
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289006] NETDEV WATCHDOG: eth1: transmit timed out
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289012] eth1: Got tx_timeout. irq: 00000036
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289014] eth1: Ring at 7bfa2000
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289015] eth1: Dumping tx registers
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289020]   0: 00002036 000000ff 00000003 030903ca 00000000 00000000 00000000 00000000
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289025]  20: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
...
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289422] eth1: Dumping tx ring
Jul 11 13:25:42 newsjtcfs99 kernel: [1482177.289426] 000: 00000000 3661494a 00000000 // 00000000 217a3b40 20000117 // 00000000 387ab8da 20000040 // 00000000 73dbf8ce 20000046


Attached lshw, lspci -vvv, and var/log/messages

I'm also running the x86_64 version, but a later kernel (7.10's)

Linux newsjtcfs99 2.6.22-14-generic #1 SMP Sun Oct 14 21:45:15 GMT 2007
x86_64 GNU/Linux

Network is full duplex 1gbit plugged into a cisco 6513.

** Attachment added: "fs99crash.txt.gz"
   http://launchpadlibrarian.net/15965368/fs99crash.txt.gz

-- 
network device (nVidia MCP55, forcedeth) stops sending packets
https://bugs.launchpad.net/bugs/131737
You received this bug notification because you are a member of Kernel
Bugs, which is subscribed to linux-source-2.6.15 in ubuntu.




More information about the kernel-bugs mailing list