[tulip] Faster hd --> Centaur-P transmit freeze?
John Clemens
john@deater.net
Thu Jan 23 05:48:01 2003
I recently replaced an old 5400 RPM drive that failed with a nice new fast
40GB 7200 rpm one in my NFS server. I had been running 2.4.16 w/ stock
tulip driver for over a year no problems. Now, under heavy transmit load
(reading a large file off the new drive off of NFS) I get what appear to
be transmit lockups. I've tried 2.4.16, 2.4.18, 2.4.20 stock kernel
drivers, and then the tried and true Becker ones... still no joy.
Symptoms include little or no messages on the console, but no traffic gets
into or out of the box. A rmmod/insmod doesn't help, only a reboot.
Under light load it works fine. System is now 2.4.20.
The only messages on the console from the Becker drivers are the
occasional "too much work in interrupt" message. lots of times i don't
get anything, just no networking. The other ones complained of transmit
timeouts. Unmasking the interrupts from the IDE drives seems to help, and
just to be certain I've forced the card to use MII 100baseTx-HD (its on a
hub with various other network cards..collisions are high, as usual).
info and tulip-diag output from idle and stuck conditions included.
Notice it's stuck in "waiting for transmit to finish" state..Hmm...more
info upon request.
Any help would be appreciated..thanks
john.c
tulip.c:v0.95f 11/17/2002 Written by Donald Becker <becker@scyld.com>
http://www.scyld.com/network/tulip.html
eth0: ADMtek Centaur-P rev 17 at 0xd88a3000, 00:20:78:10:98:11, IRQ 11.
eth0: Transceiver selection forced to MII 100baseTx.
eth0: MII transceiver #1 config 3000 status 786d advertising 01e1.
eth0: Advertising 0080 on PHY 1, previously advertising 01e1.
tulip-diang -f -aa -mm -ee (idle):
tulip-diag.c:v2.16 12/17/2002 Donald Becker (becker@scyld.com)
http://www.scyld.com/diag/index.html
Index #1: Found a ADMtek AL985 Centaur-P adapter at 0x2800.
ADMtek AL985 Centaur-P chip registers at 0x2800:
0x00: fff98000 ffffffff ffffffff 1745a000 1745a200 fc664010 ff972117 ffffebff
0x40: fffe0000 fff597f8 00000000 fffe0000 00000000 00000200 00000000 c40ffec8
Extended registers:
0x80: 00664010 03fe6bff 804c0005 ffffffff 00000000 1745a260 1745a110 ffe0f000
0xa0: f0000000 10782000 ffff1198 00000000 40000000 00000000 00000000 00000000
0xc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0xe0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 a0000027
Comet duplex is reported in the MII status registers.
Transmit started, Receive started.
The Rx process state is 'Waiting for packets'.
The Tx process state is 'Idle'.
The transmit threshold is 128.
Comet MAC address registers 10782000 ffff1198
Comet multicast filter 0000000040000000.
EEPROM 256 words, 8 address bits.
Ethernet MAC Station Address 00:20:78:10:98:11.
Default connection type 'Autosense'.
PCI IDs Vendor 1317 Device 0985 Subsystem 1317 0574
PCI min_grant 255 max_latency 255.
CSR18 power-up setting 0x804c****.
EEPROM contents (256 words):
0x00: 0985 0002 0000 0000 2000 1078 1198 0000
0x08: 0000 0400 0000 0000 0000 0000 0000 0100
0x10: 0985 1317 0574 1317 ffff 0202 0000 804c
0x18: 0000 0000 0000 0000 0000 0000 0000 0000
0x20: 0000 0000 0000 0000 0000 0000 0000 0000
0x28: 0040 0040 0000 0000 0000 0000 0000 0000
0x30: 0000 0000 0000 0000 0000 0000 0000 0000
0x38: 0000 0000 0000 0000 0000 0000 0000 7354
0x40: 0301 396a 17ff 4903 ff00 0420 01bf 2227
0x48: 2315 0104 4341 5443 4e4f 4500 324e 3232
0x50: 2d37 4350 434d 4149 4500 324e 3232 0037
0x58: 3052 0031 1aff 0105 f827 0303 141b c1e0
0x60: 3f7d 4d55 065d 46b6 fc46 4524 ff30 28ff
0x68: 0032 071b 0820 60ca 0300 1b1f 2107 ca08
0x70: 2060 1f03 071b 0822 60ca 0340 1b1f 2307
0x78: ca08 6060 1f03 0014 0221 0006 ffff ffff
0x80: 0301 396a 17ff 4903 ff00 0420 01bf 2227
0x88: 2315 0104 4341 5443 4e4f 4500 324e 3232
0x90: 2d37 4350 434d 4149 4500 324e 3232 0037
0x98: 3052 0031 1aff 0105 f827 0303 141b c1e0
0xa0: 0301 396a 17ff 4903 ff00 0420 01bf 2227
0xa8: 2315 0104 4341 5443 4e4f 4500 324e 3232
0xb0: 2d37 4350 434d 4149 4500 324e 3232 0037
0xb8: 3052 0031 1aff 0105 f827 0303 141b c1e0
0xc0: 3f7d 4d55 065d 46b6 fc46 4524 ff30 28ff
0xc8: 0032 071b 0820 60ca 0300 1b1f 2107 ca08
0xd0: 2060 1f03 071b 0822 60ca 0340 1b1f 2307
0xd8: ca08 6060 1f03 0014 0221 0006 ffff ffff
0xe0: 0000 0000 0000 0000 0000 0000 0000 0000
0xe8: 0000 0000 0000 0000 0000 0000 0000 0000
0xf0: 0000 0000 0000 0000 0000 0000 0000 0000
0xf8: 0000 0000 0000 0000 0000 0000 0000 0000
ID block CRC 0xa8 (vs. 00).
Full contents CRC 0x7354 (read as 0x7354).
MII PHY found at address 1, status 0x786d.
MII PHY found at address 2, status 0x786d.
MII PHY found at address 3, status 0x786d.
MII PHY found at address 4, status 0x786d.
MII PHY #1 transceiver registers:
1000 786d 0022 5410 01e1 0081 0004 2001
ffff ffff ffff ffff ffff ffff ffff ffff
01c0 0040 0499 8020 4f02 0304 0026 0000
e60b cfbf 0000 ffff ffff ffff ffff ffff.
MII PHY #2 transceiver registers:
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff.
MII PHY #3 transceiver registers:
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff.
MII PHY #4 transceiver registers:
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff.
./tulip-diag -f -ee -mm -aa (stuck):
tulip-diag.c:v2.16 12/17/2002 Donald Becker (becker@scyld.com)
http://www.scyld.com/diag/index.html
Index #1: Found a ADMtek AL985 Centaur-P adapter at 0x2800.
ADMtek AL985 Centaur-P chip registers at 0x2800:
0x00: fff98000 ffffffff ffffffff 1745a000 1745a200 fc264010 ffbfe117 ffffebff
0x40: fffe0000 fff597f8 00000000 fffe0000 00000000 00000200 00000000 c40ffec8
Extended registers:
0x80: 00264010 03fe6bff 804c0004 0000ff00 00000000 1745a2f0 1745a160 ffe0f000
0xa0: f0000000 10782000 ffff1198 00000000 40000000 00000000 00000000 00000000
0xc0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 00000000
0xe0: 00000000 00000000 00000000 00000000 00000000 00000000 00000000 a0000027
Comet duplex is reported in the MII status registers.
Transmit started, Receive started.
The Rx process state is 'Waiting for packets'.
The Tx process state is 'Waiting for Tx to finish'.
The transmit unit is set to store-and-forward.
Comet MAC address registers 10782000 ffff1198
Comet multicast filter 0000000040000000.
EEPROM 256 words, 8 address bits.
Ethernet MAC Station Address 00:20:78:10:98:11.
Default connection type 'Autosense'.
PCI IDs Vendor 1317 Device 0985 Subsystem 1317 0574
PCI min_grant 255 max_latency 255.
CSR18 power-up setting 0x804c****.
EEPROM contents (256 words):
0x00: 0985 0002 0000 0000 2000 1078 1198 0000
0x08: 0000 0400 0000 0000 0000 0000 0000 0100
0x10: 0985 1317 0574 1317 ffff 0202 0000 804c
0x18: 0000 0000 0000 0000 0000 0000 0000 0000
0x20: 0000 0000 0000 0000 0000 0000 0000 0000
0x28: 0040 0040 0000 0000 0000 0000 0000 0000
0x30: 0000 0000 0000 0000 0000 0000 0000 0000
0x38: 0000 0000 0000 0000 0000 0000 0000 7354
0x40: 0301 396a 17ff 4903 ff00 0420 01bf 2227
0x48: 2315 0104 4341 5443 4e4f 4500 324e 3232
0x50: 2d37 4350 434d 4149 4500 324e 3232 0037
0x58: 3052 0031 1aff 0105 f827 0303 141b c1e0
0x60: 3f7d 4d55 065d 46b6 fc46 4524 ff30 28ff
0x68: 0032 071b 0820 60ca 0300 1b1f 2107 ca08
0x70: 2060 1f03 071b 0822 60ca 0340 1b1f 2307
0x78: ca08 6060 1f03 0014 0221 0006 ffff ffff
0x80: 0301 396a 17ff 4903 ff00 0420 01bf 2227
0x88: 2315 0104 4341 5443 4e4f 4500 324e 3232
0x90: 2d37 4350 434d 4149 4500 324e 3232 0037
0x98: 3052 0031 1aff 0105 f827 0303 141b c1e0
0xa0: 0301 396a 17ff 4903 ff00 0420 01bf 2227
0xa8: 2315 0104 4341 5443 4e4f 4500 324e 3232
0xb0: 2d37 4350 434d 4149 4500 324e 3232 0037
0xb8: 3052 0031 1aff 0105 f827 0303 141b c1e0
0xc0: 3f7d 4d55 065d 46b6 fc46 4524 ff30 28ff
0xc8: 0032 071b 0820 60ca 0300 1b1f 2107 ca08
0xd0: 2060 1f03 071b 0822 60ca 0340 1b1f 2307
0xd8: ca08 6060 1f03 0014 0221 0006 ffff ffff
0xe0: 0000 0000 0000 0000 0000 0000 0000 0000
0xe8: 0000 0000 0000 0000 0000 0000 0000 0000
0xf0: 0000 0000 0000 0000 0000 0000 0000 0000
0xf8: 0000 0000 0000 0000 0000 0000 0000 0000
ID block CRC 0xa8 (vs. 00).
Full contents CRC 0x7354 (read as 0x7354).
MII PHY found at address 1, status 0x784d.
MII PHY found at address 2, status 0x784d.
MII PHY found at address 3, status 0x784d.
MII PHY found at address 4, status 0x784d.
MII PHY #1 transceiver registers:
2000 784d 0022 5410 0081 0081 0004 2001
ffff ffff ffff ffff ffff ffff ffff ffff
01c0 0000 0600 8020 4f02 0304 0026 0000
f91f cfbf 0000 ffff ffff ffff ffff ffff.
MII PHY #2 transceiver registers:
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff.
MII PHY #3 transceiver registers:
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff.
MII PHY #4 transceiver registers:
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff
ffff ffff ffff ffff ffff ffff ffff ffff.