As Danie1zhou suggested i post my question from https://social.technet.microsoft.com/Forums/windowsserver/en-US/732966e8-dc13-445d-853d-73131cdd69ba/server-2019-set-ndis-reset-network-card?forum=winserverhyperv here.
----------------------------------------------
Dear all
Environment:
3 node HyperV Failover cluster
each node:
- 2x Intel Xeon Gold 6138
- 512 GB RAM
- 1x 2 Port Intel X722
- 3x 2 Port Intel X710
- latest NIC driver and firmware
- Windows Server 2019 17763.805
SET:
Hash algorithm: dynamic
1x SET with the 2 Ports of Intel X722 for Cluster and LiveMigration
1x SET with the first Port of all 3 Intel X710 Networkcards for iSCSI Traffic
1x SET with the second Port of all 3 Intel X710 Networkcards for Data Traffic
After some time (with traffic faster than without) i can see the following events:
----------
Failed to move RSS queue 2 from VMQ 1 of switch 95AD556E-D325-46BB-87EC-AFDEA4ACE8F7 (Friendly Name: SET iSCSI), ndisStatus = -1073741823 .
----------
The network interface "Intel(R) Ethernet Controller X710 for 10GbE SFP+ #6" has begun resetting. There will be a momentary disruption in network connectivity while the hardware resets. Reason: The network driver detected that its hardware
has stopped responding to commands. This network interface has reset 1 time(s) since it was last initialized.
----------
NIC /DEVICE/{F4B0FE78-B659-4D0E-AB0A-83E52D3A5419} (Friendly Name: Intel(R) Ethernet Controller X710 for 10GbE SFP+ #4) is no longer operational.
----------
Intel(R) Ethernet Controller X710 for 10GbE SFP+ #6
Network link is disconnected.
----------
Then the network card comes back for a minute and the last 3 messages from above are written every minute.
The only way to get back to normal evacuate the vm to other hosts and reboot it.
Any idea what could be wrong here?
Thanks