Public bug reported:
I'm having issues with an Intel E810-XXV card on a Dell server under Ubuntu
Jammy.
Details:
- hardware --> a1:00.0 Ethernet controller: Intel Corporation Ethernet
Controller E810-XXV for SFP (rev 02)
- tested with both GA and HWE kernels (`5.15.0-83-generic #92` and
`6.2.0-32-generic #32~22.04.1-Ubuntu`) with the same results.
- using a bond over the two ports of the same card, at 25Gbps to two
different switches, bond is using LACP with hash layer3+4 and fast
timeout. But I believe the bug is not directly related to bonding as the
problem seems to be in the interface.
- machine installed by maas. No issues during installation, but at that
time bond is not formed yet, later when linux is booted, the bond is
formed and works without issues for a while
- it works for about 2 to 3 hours fine, then the issue starts (may or
may not be related to network load, but it seems that it is triggered by
some tests that I run after openstack finishes installing)
- one of the legs of the bond freezes and everything that would go to
that lag is discarded, in and out, ping to random external hosts start
losing every second packet
- after some time you can see on the kernel log messages about "NETDEV
WATCHDOG: enp161s0f0 (ice): transmit queue 166 timed out" and a stack
trace
- the switch does log that the bond is flapping
** Affects: linux (Ubuntu)
Importance: Undecided
Status: New
--
You received this bug notification because you are a member of Kernel
Packages, which is subscribed to linux in Ubuntu.
https://bugs.launchpad.net/bugs/2036239
Title:
Intel E810-XXV - NETDEV WATCHDOG: (ice): transmit queue timed out
Status in linux package in Ubuntu:
New
Bug description:
I'm having issues with an Intel E810-XXV card on a Dell server under Ubuntu
Jammy.
Details:
- hardware --> a1:00.0 Ethernet controller: Intel Corporation Ethernet
Controller E810-XXV for SFP (rev 02)
- tested with both GA and HWE kernels (`5.15.0-83-generic #92` and
`6.2.0-32-generic #32~22.04.1-Ubuntu`) with the same results.
- using a bond over the two ports of the same card, at 25Gbps to two
different switches, bond is using LACP with hash layer3+4 and fast
timeout. But I believe the bug is not directly related to bonding as
the problem seems to be in the interface.
- machine installed by maas. No issues during installation, but at
that time bond is not formed yet, later when linux is booted, the bond
is formed and works without issues for a while
- it works for about 2 to 3 hours fine, then the issue starts (may or
may not be related to network load, but it seems that it is triggered
by some tests that I run after openstack finishes installing)
- one of the legs of the bond freezes and everything that would go to
that lag is discarded, in and out, ping to random external hosts start
losing every second packet
- after some time you can see on the kernel log messages about "NETDEV
WATCHDOG: enp161s0f0 (ice): transmit queue 166 timed out" and a stack
trace
- the switch does log that the bond is flapping
To manage notifications about this bug go to:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2036239/+subscriptions
--
Mailing list: https://launchpad.net/~kernel-packages
Post to : kernel-packages@lists.launchpad.net
Unsubscribe : https://launchpad.net/~kernel-packages
More help : https://help.launchpad.net/ListHelp
