forcedeth is dead in large data transport
 

Hi, I am using forcedeth nic to transport data, but when the data is huge, nic cannot work, the dmesg give me such message:
+++++++++++++++++++++++++++++
NETDEV WATCHDOG: eth0: transmit timed out
eth0: Got tx_timeout. irq: 00000000
eth0: Ring at 100140bf800: get 100140bf8f0 put 100140bf8f0
eth0: Dumping tx registers
0: 00000000 000000ff 00000003 033503ca 00000000 00000000 00000000 00000000
20: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
40: 0420e20e 0000a855 00002e20 00000000 00000000 00000000 00000000 00000000
60: 00000000 00000000 00000000 0000ffff 0000ffff 0000ffff 0000ffff 00000000
80: 003b0f3c 40044001 00000000 007f0020 0000061c 00000001 00000000 00007f66
a0: 0014050f 00000016 7a483000 0000803f 005e0001 00000100 ffffffff 0000ffff
c0: 10000002 00000001 00000001 00000001 00000001 00000001 00000001 00000001
e0: 00000001 00000001 00000001 00000001 00000001 00000001 00000001 00000001
100: 140bf800 140bf000 007f003f 00008000 00010032 00000000 00000004 140bf8f0
120: 140bf540 f2fec680 a000ffcf c5472010 8000061c 140bf8fc 140bf470 0fe08000
140: 00304120 80c02600 00000000 00000000 00000001 00000000 00000001 00000000
160: 00000000 00000000 00000000 00000000 01ff0080 0000c000 00000000 00000000
180: 00000006 00000008 0294796d 00008103 0000004a 00003c00 00000080 0000bd83
1a0: 00000006 00000008 0294796d 00008103 0000004a 00003c00 00000080 0000bd83
1c0: 00000006 00000008 0294796d 00008103 0000004a 00003c00 00000080 0000bd83
1e0: 00000006 00000008 0294796d 00008103 0000004a 00003c00 00000080 0000bd83
200: 00000000 00000001 00000000 00000000 00000000 00000000 00000000 00000000
220: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
240: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
260: 00000000 00000000 fe027001 00000100 00000011 000000a3 fe027011 000001a3
280: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
2a0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
2c0: 00000000 00000000 00000000 00000000 0000000e 00000000 00000000 00000808
2e0: 00000000 00000000 00000000 00000000 00000000 00000001 00000001 00000001
300: 80212000 00000000 00000000 00000000 00000000 00002000 00000000 00000000
320: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
340: 00000000 00000000 00000000 00000000 00000000 00000020 1b3b29e2 00000000
360: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
380: 00000000 00000000 00000000 00000000 00000000 00000000 00000002 00000000
3a0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
3c0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
3e0: 06255300 00701365 00000000 00000000 00000000 00000000 00000000 00000000
400: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
420: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
440: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
460: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
480: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
4a0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
4c0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
4e0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
500: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
520: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
540: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
560: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
580: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
5a0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
5c0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
5e0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
600: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
eth0: Dumping tx ring
000: 00000001 fb14e000 200005ee // 00000002 1bedbe9e 00000000 // 00000001 fb14e460 200005ee // 00000002 1e97b89e 00000000
004: 00000001 fb14ea08 200005ee // 00000002 1e97b69e 00000000 // 00000001 fb14efb0 00000000 // 00000001 d8a39000 200005ee
008: 00000002 1e97be9e 00000000 // 00000001 d8a39558 200005ee // 00000002 1e97ba9e 00000000 // 00000001 d8a39b00 00000000
00c: 00000001 f2fec000 200005ee // 00000001 f751089e 00000000 // 00000001 f2fec0a8 200005ee // 00000002 1c46389e 00000000
010: 00000001 ea28dd98 00000000 // 00000001 f7cd7000 200005ee // 00000001 d273ce9e 00000000 // 00000001 f7cd7340 200005ee
014: 00000001 d273c69e 00000000 // 00000001 f7cd78e8 200005ee // 00000001 d273c49e 00000000 // 00000001 f7cd7e90 00000000
018: 00000001 f7cd6000 200005ee // 00000001 d273ca9e 00000000 // 00000001 f7cd6438 200005ee // 00000001 d273c09e 00000000
01c: 00000001 f7cd69e0 200005ee // 00000001 d273c29e 00000000 // 00000001 f7cd6f88 00000000 // 00000001 f74e2000 200005ee
020: 00000001 dcf5889e 00000000 // 00000001 f74e2530 200005ee // 00000001 dcf5849e 00000000 // 00000001 f74e2ad8 00000000
024: 00000001 f74e3000 200005ee // 00000001 dcf5809e 00000000 // 00000001 f74e3080 200005ee // 00000001 dcf58c9e 00000000
028: 00000001 f74e3628 200005ee // 00000001 dcf58e9e 00000000 // 00000001 f74e3bd0 00000000 // 00000001 d851a000 200005ee
02c: 00000002 1bc5229e 00000000 // 00000001 d851a178 200005ee // 00000001 ef2a129e 00000000 // 00000001 d851a720 200005ee
030: 00000001 dcf5829e 00000000 // 00000001 d851acc8 00000000 // 00000001 daf4c000 200005ee // 00000001 dcf58a9e 00000000
034: 00000001 daf4c270 200005ee // 00000002 1c8bf49e 00000000 // 00000001 daf4c818 200005ee // 00000002 1c8bf29e 00000000
038: 00000001 daf4cdc0 00000000 // 00000001 bfa17000 200005ee // 00000002 1c8bf89e 00000000 // 00000001 bfa17368 200005ee
03c: 00000002 1c8e649e 00000000 // 00000001 bfa17910 200005ee // 00000002 1bedb09e 00000000 // 00000001 bfa17eb8 00000000
++++++++++++++++++++++++++++++++++
This is my lspci:
+++++++++++
00:00.0 RAM memory: nVidia Corporation: Unknown device 0369 (rev a2)
00:01.0 ISA bridge: nVidia Corporation: Unknown device 0364 (rev a3)
00:01.1 SMBus: nVidia Corporation: Unknown device 0368 (rev a3)
00:01.2 RAM memory: nVidia Corporation: Unknown device 036a (rev a3)
00:02.0 USB Controller: nVidia Corporation: Unknown device 036c (rev a1)
00:02.1 USB Controller: nVidia Corporation: Unknown device 036d (rev a2)
00:04.0 IDE interface: nVidia Corporation: Unknown device 036e (rev a1)
00:05.0 IDE interface: nVidia Corporation: Unknown device 037f (rev a3)
00:05.1 IDE interface: nVidia Corporation: Unknown device 037f (rev a3)
00:05.2 IDE interface: nVidia Corporation: Unknown device 037f (rev a3)
00:06.0 PCI bridge: nVidia Corporation: Unknown device 0370 (rev a2)
00:08.0 Ethernet controller: nVidia Corporation: Unknown device 0373 (rev a3)
00:09.0 Ethernet controller: nVidia Corporation: Unknown device 0373 (rev a3)
00:0a.0 PCI bridge: nVidia Corporation: Unknown device 0376 (rev a3)
00:0b.0 PCI bridge: nVidia Corporation: Unknown device 0374 (rev a3)
00:0c.0 PCI bridge: nVidia Corporation: Unknown device 0374 (rev a3)
00:0d.0 PCI bridge: nVidia Corporation: Unknown device 0378 (rev a3)
00:0e.0 PCI bridge: nVidia Corporation: Unknown device 0375 (rev a3)
00:0f.0 PCI bridge: nVidia Corporation: Unknown device 0377 (rev a3)
00:18.0 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] HyperTransport Technology Configuration
00:18.1 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Address Map
00:18.2 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] DRAM Controller
00:18.3 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Miscellaneous Control
00:19.0 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] HyperTransport Technology Configuration
00:19.1 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Address Map
00:19.2 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] DRAM Controller
00:19.3 Host bridge: Advanced Micro Devices [AMD] K8 [Athlon64/Opteron] Miscellaneous Control
01:06.0 VGA compatible controller: ATI Technologies Inc: Unknown device 515e (rev 02)
02:00.0 PCI bridge: NEC Corporation: Unknown device 0125 (rev 07)
02:00.1 PCI bridge: NEC Corporation: Unknown device 0125 (rev 07)
04:04.0 SCSI storage controller: Adaptec AIC-7902B U320 (rev 10)
04:04.1 SCSI storage controller: Adaptec AIC-7902B U320 (rev 10)
++++++++++++++++++++++++++++++++
my kernel is :
2.4.21-32
ethtool -i eth0
driver: forcedeth
version: 0.60-Driver Package V1.21
firmware-version:
bus-info: 00:08.0
++++++++++++++++++++++++++++++++
And I must reboot my machine to restart it . ifdown eth0;ifup etho cannot work.

Is there any idea???
Thx

Re: forcedeth is dead in large data transport
 

I would recommend you to submit a bug to the linux kernel as forcedeth is maintained in there (by Nvidia hackers and others). I know that you are a 2.6x kernel but I think it is the best you can do.

Re: forcedeth is dead in large data transport
 

I'm having a similar problem with forcedeth.c 0.60 which came with the latest fc6 kernel. Same problem with 0.59, it seems under load that the eth link just goes down and wont come back; ifconfig shows the link up but nothing works. I checked my switch, when this happens the RX errors on the switch start counting like crazy; looks like something real bad happened.

ifdown eth0;ifup eth0 - link still corrupted, no recovery

I found the only way to recover was to unload and reload the driver. Temporarily I've put this in a script with a ping check on the interface;

rmmod forcedeth ; modprobe forcedeth

Not a desirable solution, but I'm having no luck compiling the NVIDIA 0.62 source under FC6. I get warnings and errors; but that will be another thread...

I've ordered a different motherboard with non-nvidia hardware as a backup, in case I cant get this working. Currently, I have several Asus M2N-MX.

Re: forcedeth is dead in large data transport
 

I have similar problems... the connection drops and comes back again.
It looks however I can revive the connection by pinging from the machine itself.

I have a M2NPV-VM board with dual core.
It happens with openSuse 10.2, kernel 2.6.18.8-0.5-default.
Both with forcedeth drivers "0.59' and "0.62-Driver Package V1.23"

I have used BIOS 0901 and 1001.

One note: the master (boot) IDE device is a 4GB CF card with idebus=133

Re: forcedeth is dead in large data transport
 

Its funny that nvidia still didn't fixed that bug. I reported that like one year ago.

Re: forcedeth is dead in large data transport
 

Guys,
Has anything been done on this? I loaded FC7 and found that no only are the irq issues still there but if you try to use bonding (lacp) the system will (under load) freeze with no logs!

Bonding both ports on a Tyan S2932, dual core Opteron, 4G mem

Re: forcedeth is dead in large data transport
 

the forcedeth.c driver has a few known "quirks" and recently Jeff Garzik
posted a few patches which should improve the driver. Please test them
and report your findings:
[links to the 7 mails, in order 0-6]
http://marc.info/?l=linux-netdev&m=119260471502935&w=2
http://marc.info/?l=linux-netdev&m=119260472402995&w=2
http://marc.info/?l=linux-netdev&m=119260472202985&w=2
http://marc.info/?l=linux-netdev&m=119260471802953&w=2
http://marc.info/?l=linux-netdev&m=119260471902959&w=2
http://marc.info/?l=linux-netdev&m=119260472102976&w=2
http://marc.info/?l=linux-netdev&m=119260472402989&w=2