Serious e1000 timeout problem with kernel 2.6.8-1.521

From: Axel Suppantschitsch
Date: Sat Sep 04 2004 - 03:09:00 EST


Hiya,

I recently upgraded my network infrastructure to Gigabit Ethernet,
but now I run into serious network problems. At high loads the e1000 driver
times out, resets itself several times per minute. I already read about this
problem with the same and other network drivers, tried out a lot of possible
solutions (acpi=off), but nothing worked out for me. I also tried the latest
NAPI driver from Intel, no success.

At first the specs (details: dmesg.gz)

Fedora Core 2, latest patchlevel (kernel 2.6.8-1.521)
Athlon 1800+ XP (133MHz FSB)
512MB RAM (DDR 233MHz)
Diamond FireGL (Permedia2) PCI VGA Card
MSI KT6 Delta FISR Motherboard (VIA KT600 chipset) with Broadcom Gigabit
onboard
Intel Pro 1000/MT PCI Desktop Adapter (82541GI)
Realtek 8139 PCI Adapter
D-Link DGS-1008D Gigabit Switch
Cat 5 cables (checked with Fluke for compliance)

Following kernel messages are in the messages log:

Sep 3 23:52:26 matrix kernel: NETDEV WATCHDOG: eth1: transmit timed out
Sep 3 23:52:29 matrix kernel: e1000: eth1: e1000_watchdog: NIC Link is Up
1000 Mbps Full Duplex
Sep 3 23:53:04 matrix kernel: NETDEV WATCHDOG: eth1: transmit timed out
Sep 3 23:53:07 matrix kernel: e1000: eth1: e1000_watchdog: NIC Link is Up
1000 Mbps Full Duplex

Following ethtool information for the e1000 driver (eth1):

driver: e1000
version: 5.2.52-k4
firmware-version: N/A
bus-info: 0000:00:06.0

Settings for eth1:
Supported ports: [ TP ]
Supported link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Supports auto-negotiation: Yes
Advertised link modes: 10baseT/Half 10baseT/Full
100baseT/Half 100baseT/Full
1000baseT/Full
Advertised auto-negotiation: Yes
Speed: 1000Mb/s
Duplex: Full
Port: Twisted Pair
PHYAD: 0
Transceiver: internal
Auto-negotiation: on
Supports Wake-on: umbg
Wake-on: g
Current message level: 0x00000007 (7)
Link detected: yes

NIC statistics:
rx_packets: 410244
tx_packets: 1054111
rx_bytes: 400272468
tx_bytes: 1442819261
rx_errors: 0
tx_errors: 0
rx_dropped: 0
tx_dropped: 0
multicast: 0
collisions: 0
rx_length_errors: 0
rx_over_errors: 0
rx_crc_errors: 0
rx_frame_errors: 0
rx_fifo_errors: 0
rx_missed_errors: 0
tx_aborted_errors: 0
tx_carrier_errors: 0
tx_fifo_errors: 0
tx_heartbeat_errors: 0
tx_window_errors: 0
tx_abort_late_coll: 0
tx_deferred_ok: 0
tx_single_coll_ok: 0
tx_multi_coll_ok: 0
rx_long_length_errors: 0
rx_short_length_errors: 0
rx_align_errors: 0
tx_tcp_seg_good: 0
tx_tcp_seg_failed: 0
rx_flow_control_xon: 0
rx_flow_control_xoff: 0
tx_flow_control_xon: 0
tx_flow_control_xoff: 0
rx_csum_offload_good: 409990
rx_csum_offload_errors: 0
rx_long_byte_count: 400272468

Following information is from /proc/interrupts:

CPU0
0: 36642685 XT-PIC timer
1: 18 XT-PIC i8042
2: 0 XT-PIC cascade
5: 1287758 XT-PIC ehci_hcd, eth0, VIA8233
8: 1 XT-PIC rtc
9: 0 XT-PIC acpi
10: 297076 XT-PIC uhci_hcd, uhci_hcd, ohci1394, eth1
11: 0 XT-PIC uhci_hcd, uhci_hcd
12: 735 XT-PIC i8042
14: 366735 XT-PIC ide0
15: 385804 XT-PIC ide1
NMI: 0
ERR: 0

Please help me out,

Axel.

Attachment: dmesg.gz
Description: Binary data