Kernel 6.10 oder neuer....

Some sample file transfer numbers:
# scp -pr *.iso 192.168.90.4:/mnt/pve/pve4vm/tmp
ClearOS-DVD-x86_64.iso 100% 1224MB 541.0MB/s 00:02
debian-10.6.0-amd64-netinst.iso 100% 349MB 558.3MB/s 00:00
debian-11.6.0-amd64-netinst.iso 100% 388MB 542.8MB/s 00:00
debian-12.6.0-amd64-netinst.iso 100% 631MB 549.8MB/s 00:01
debian-9.13.0-amd64-DVD-1.iso 100% 3574MB 555.2MB/s 00:06
debian-9.13.0-amd64-DVD-2.iso 100% 4458MB 550.9MB/s 00:08
debian-9.13.0-amd64-DVD-3.iso 100% 423MB 550.5MB/s 00:00
foo.iso 81% 8835MB 550.8MB/s 00:03 ETA
 
One MAJOR outstanding issue:
When I host a large SSD, using standard NFS v4.2, via the WisdPi, the system locks up after about 30 seconds.

I even tried the latest release of Fedora Server, on a slightly newer kernel, and no luck.

I suspect a bug in the Realtek driver.

I am going to try out a OWC Thunderbolt 10 GbE connection as a temporary solution.
 
When hosting the exact same files, using the exact same system, via a traditional Realtek 2.5 GbE USB dongle, there are no issues, and Windows 11 runs fine over NFS.

Crystal disk mark scores for the VM are as expected for 2.5 GbE and NFS.
 
When hosting the exact same files, using the exact same system, via the OWC 10GbaseT via thunderbolt dongle, there are no issues, and Windows 11 runs fine over NFS.

Crystal disk mark scores for the VM are as expected for 10GbE and NFS.

The server with the OWC Thunderbolt dongle has been 100% stable for a week with multiple VMs using an NFS mount for the QCOWs

Reply
Report Edit Delete
 
I seem to still be experiencing intermittent lockups, not sure if it is do to the driver (likely) or some other 6.11 issue.

My experiment with these 5 GbE dongles may be coming to an end.
 
I have removed all of the experiment 8157 USB dongles and replaced with the OWC 10 GbE TB3 dongles.

No system lockups or other issues.

These R8157 dongles will not be stable until Realtek reworks their drivers.

Since there is no real support channel, I have no way to ask for this.