@samuelolavo Thanks for your answer It's very weird because by seeing the command outputs that you pasted, it looks like everything is behaving as it should be. Even the PCI ID (segment:bus:device:function) seems to stay correct (0000:03:00.0) I'll ask others internally.

I've had a lot of updates happening in the homelab. I've replaced the T620 with an R740, expanded my storage for both HDD and NVME pools. Also did a little min-maxing on the hardware to help separate traffic, decrease some latency and jitter for internet traffic and introducing IDS There are a lot of additions and modifications, but I guess the other big one is setting up a Dell Precision 5820 with XCP-NG as a studio and prototyping rig. Replaced Ansible with AWX, added some more VMs and migrated others but in all that I've updated the diagrams as well! Will say that XCP-NG offers up the flexibility and performance that I've needed so far. Would love to try out the XOSTOR storage at some point but will have to move around my entire setup haha. This reference diagram breaks down each VLAN [image: 1772850854389-networking-and-vlans-reference-diagram.drawio.png] The physical equipment reference diagram gives a breakdown of the server equipment and NAS at both locations, including the home rack. It also shows a basic breakdown of each server configuration. [image: 1772850854434-physical-equipment-reference-diagram.drawio.png] The physical topology reference diagram gives a simplistic overview of the major networking and server equipment. [image: 1772850854468-physical-topology-reference-diagram.drawio.png] The logical topology reference diagram gives a more in-depth view of the networking, servers, VMs, VLANs and endpoint devices. [image: 1772850854364-logical-topology-reference-diagram.drawio.png] The colo reference diagram contains my off-site location with a rented dedicated server [image: 1772850854295-colo-reference-diagram.drawio.png] The Authentication reference diagram gives a break down of how user access is sourced or what security route it takes. [image: 1772850854275-authentication-reference-diagram.drawio.png] The shared storage and access reference diagram gives a break down of how most hardware interacts with each other in regards to network routing for users, endpoints, and member servers. [image: 1772850854483-shared-storage-and-acess-reference-diagram.drawio.png]

I am in the same situation as @vhaelan. same as in same iGPU (alderlake) passed-through, same output for those latest commands, same OS (Fedora CoreOS on latest Xcp-Ng stable). Tried current avenues suggested in this thread with no progress. It seems vhaelan has settled with CoreOS under Proxmox (which works!). He also mentioned it works in Debian under XCP-ng, though I haven't tested that myself. I would appreciate additional suggestions for troubleshooting to take this further, in case anyone has any other ideas.

@Greg_E Thanks, I've got another thread up and it's potentially being addressed!

Latest XO can be new tested along XCP-ng (with OpenSSL 3): https://xcp-ng.org/forum/topic/9964/xcp-ng-8-3-updates-announcements-and-testing/363 Feedback welcome

@ItzJay in your journalctl -i xo-server log you should have something like nbdkit logs of ${diskPath} are in ${tmpDir} where tmpDir is something like /tmp/xo-serverXXXX/stderr can you post the file ? alternatively, you can open a support ticket

thanks Andryi We us round robin when using NBD , but to be fair, it does not change the performance a lot in most of the case. The concurrency settings ( multiple connection to the same file ) is helping when there is a high latency between XO and the host. SO , @fcgo if you have thousand of VMs , you should enable NBD it will consume less resource on the DOM0 and XO , and it will be spread on all the possible hosts.

@Forza Too funny. I came across this post and clicked on the URL you referenced......and that earlier question was from me! Well, nothing has changed. I'm doing mirror'ed backups and I'm still blind as a bat.