Symptoms:
Virtual Machines(VMs) Frozen and unreachable. Where an ESXi reboot remedies the issue
vmkernel.log shows lines similar to:
vmkernel: cpu0:3682721)VSCSI: 3446: handle 15817106129953059(GID:8483)(vscsi0:1):Added handle (refCnt = 3) to vscsiResetHandleList vscsiResetHandleCount = 1
vmkernel: cpu23:2097490)VSCSI: 3700: handle 15817106129953059(GID:8483)(vscsi0:1):processing reset for handle ... state 1381192707
vmkernel: cpu1:2097490)VSCSI: 3700: handle 15817106129953059(GID:8483)(vscsi0:1):processing reset for handle ... state 1381192706
vmkernel: cpu1:2097490)VSCSI: 3700: handle 15817106129953059(GID:8483)(vscsi0:1):processing reset for handle ... state 1381192706
The host is using the "Async" version for the bnxtnet" driver of version 224.0.x.x or later for iSCSI uplinks .
VMware vSphere ESXi 8.0
The Broadcom bnxtnet async driver version 224.0.x.x or later has a known packet leak issue.
Broadcom has released new versions of bnxtnet and bnxtroce drivers containing the fix, starting with version 226.0.145.4-1.
VM can also experience network loss, encountered from this issue.