linux – link network interface speed changed to 0


I have the Suse12 system with Intel 82599ES nic (with SFI port / SFP + 2 * 10-Gigabit), two ports are linked by lacp. Recently, the system network is inaccessible, lasted 3 minutes.

Looking in the message log, I notice that when the interface goes down, we get the following information:

2019-03-03T09: 23: 10.491731 + 08: 00 oradb12 core: [9519285.192448] ixgbe 0000: 02: 00.1 eth5: reset initialization due to tx timeout
2019-03-03T09: 23: 10.491754 + 08: 00 kernel of oradb12: [9519285.192464] ixgbe 0000: 02: 00.1 eth5: reset the adapter
2019-03-03T09: 23: 16.995739 + 08: 00 oradb12 core: [9519291.696952] ixgbe 0000: 02: 00.1 eth5: speed changed to 0 for port eth5
2019-03-03T09: 23: 16.995763 + 08: 00 oradb12 core: [9519291.697438] bond1: the link status is permanently disabled for the eth5 interface, which disables it

the system kernel version is as follows:

Linux oradb12 4.4.74-92.35-default # 1 SMP Mon Aug 7 18:24:48 UTC 2017 (c0fdc47) x86_64 x86_64 x86_64 GNU / Linux
oradb12: / etc / sysconfig / network # cat / etc / SuSE-release
SUSE Linux Enterprise Server 12 (x86_64)
VERSION = 12
PATCHLEVEL = 2

Link network interface is as follows:

oradb12: / etc / sysconfig / network # cat ifcfg-bond1
BOOTPROTO = & # 39; static & # 39;
STARTMODE = onboot & # 39;
BONDING_MASTER = 'yes & # 39;
BONDING_SLAVE0 = & # 39; eth3 & # 39;
BONDING_SLAVE1 = & # 39; eth5 & # 39;
IPADDR = 10.252.128.2
GATEWAY = 10.252.128.1
NETMASK = 255.255.255.0
USERCONTROL = "no"
BONDING_MODULE_OPTS = mode = 4 miimon = 100 use_carrier = 1 & # 39;
oradb12: / etc / sysconfig / network # cat ifcfg-eth3
NAME = & # 39; bond1-slave-eth3 & # 39;
TYPE = & # 39; Ethernet & # 39;
BOOTPROTO = "no"
STARTMODE = onboot & # 39;
MASTER = & # 39; bond1 & # 39;
SLAVE = 'yes & # 39;
USERCONTROL = "no"
oradb12: / etc / sysconfig / network # cat ifcfg-eth5
NAME = & # 39; bond1-slave-eth5 & # 39;
TYPE = & # 39; Ethernet & # 39;
BOOTPROTO = "no"
STARTMODE = onboot & # 39;
MASTER = & # 39; bond1 & # 39;
SLAVE = 'yes & # 39;
USERCONTROL = "no"

the status of the link network interface is as follows:

oradb12: / etc / sysconfig / network # cat / proc / net / bonding / bond1
Ethernet Channel Link Driver: v3.7.1 (April 27, 2011)

Link Mode: IEEE 802.3ad Dynamic Link Aggregation
Transmission hash strategy: layer 2 (0)
ITN status: up
MII Interval (ms): 100
Rise delay (ms): 0
Waiting time (ms): 0

802.3ad info
LACP rate: slow
Min links: 0
Aggregator selection policy (ad_select): stable
System priority: 65535
MAC address of the system: 48: fd: 8e: c9: 21: 64
Information about the active aggregator:
Aggregator ID: 1
Number of ports: 2
Key of the actor: 13
Partner key: 10273
Mac address of the partner: 74: 4a: a4: 08: ea: 14

Slave interface: eth3
ITN status: up
Speed: 10000 Mbps
Duplex: complete
Number of link failures: 1
Permanent Hardware Address: 48: fd: 8e: c9: 21: 64
ID of the queue of the slaves: 0
Aggregator ID: 1
Churn State Actor: none
Partner Churn Status: none
Churned Actor Count: 0
Number of partners shot: 0
the details actor lacp pdu:
system priority: 65535
system mac address: 48: fd: 8e: c9: 21: 64
shipping key: 13
port priority: 255
port number: 1
State of the port: 61
partner details lacp pdu:
system priority: 32768
system mac address: 74: 4a: a4: 08: ea: 14
operational key: 10273
Port Priority: 32768
shipping number: 33
State of the port: 61

Slave interface: eth5
ITN status: up
Speed: 10000 Mbps
Duplex: complete
Number of link failures: 24
Permanent Hardware Address: 48: fd: 8e: c9: 21: 65
ID of the queue of the slaves: 0
Aggregator ID: 1
Churn State Actor: none
Partner Churn Status: none
Churned Actor Count: 0
Number of partners shot: 0
the details actor lacp pdu:
system priority: 65535
system mac address: 48: fd: 8e: c9: 21: 64
shipping key: 13
port priority: 255
port number: 2
State of the port: 61
partner details lacp pdu:
system priority: 32768
system mac address: 74: 4a: a4: 08: ea: 14
operational key: 10273
Port Priority: 32768
shipping number: 87
State of the port: 61

the network interface driver information is as follows:

oradb12: / etc / sysconfig / network # ethtool -i eth3
driver: ixgbe
version: 4.2.1-k
firmware version: 0x800003df
Expansion-rom-release:
bus-info: 0000: 02: 00.0
support-statistics: yes
support-test: yes
supports-eeprom-access: yes
supports-register-dump: yes
supports-priv-flags: no
oradb12: / etc / sysconfig / network # ethtool -i eth5
driver: ixgbe
version: 4.2.1-k
firmware version: 0x800003df
Expansion-rom-release:
bus-info: 0000: 02: 00.1
support-statistics: yes
support-test: yes
supports-eeprom-access: yes
supports-register-dump: yes
supports-priv-flags: no

When the network interface goes down, restarting the network service on the server, running the network restart of the service, seems to solve the problem

I was wondering if anyone had ever encountered similar problems before and / or had any suggestions for solving the cause of something like this?