@Andrew said: pcie_aspm=disable Just to help anyone who would run into it. Disabling ASPM via dom0 settings/kernel did not resolve the issue. Had to disable it in BIOS (NUC13) After kernel level disable it did show: lspci -vv -s 55:00.0 | grep -E 'LnkCap|LnkCtl|LnkSta' LnkCap: Port #0, Speed 5GT/s, Width x1, ASPM L1, Exit Latency L0s <2us, L1 <4us LnkCtl: ASPM L1 Enabled; RCB 64 bytes Disabled- CommClk+ LnkSta: Speed 5GT/s, Width x1, TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt- Only after BIOS disable it showed lspci -vv -s 55:00.0 | grep -E 'LnkCap|LnkCtl|LnkSta' LnkCap: Port #0, Speed 5GT/s, Width x1, ASPM L1, Exit Latency L0s <2us, L1 <4us LnkCtl: ASPM Disabled; RCB 64 bytes Disabled- CommClk+ LnkSta: Speed 5GT/s, Width x1, TrErr- Train- SlotClk+ DLActive- BWMgmt- ABWMgmt- LnkCtl2: Target Link Speed: 5GT/s, EnterCompliance- SpeedDis- LnkSta2: Current De-emphasis Level: -6dB, EqualizationComplete-, EqualizationPhase1- Running on NUC13ANBi7 Hope it helps anyone running into this problem.

@BrantleyHobbs said: @dinhngtu well it finally crashed again. I'll send the link to the bug report via DM. @john.c starting to come around to the hardware being an issue; when I got to the machine, it hadn't actually panicked and restarted, but it was unresponsive on the management NIC and while the display was still showing the usual xsconsole TUI, I was unable to log in because the USB ports were apparently disabled; no power to the mouse or keyboard. Going to try the stress test now that I know a new kernel is no help. @tjkreidl I definitely haven't put too much thought into provisioning VM's. I know the dangers (I help manage a vmware cluster at my day job), but at home I'll just throw hardware around as the spirit moves me. I only have a single host, so no time issues between hosts. Here's the specifics: Motherboard: Gigabyte X870 Gaming WiFi6 CPU: AMD Ryzen 9 7900X 12 core Power supply: Corsair RM750e RAID controller: Marvell 88SE9230 RAID configuration: RAID10 across 4 MZ7LH1T9HMLT0D3 enterprise Dell SSDs Local system disks: 2 KingSpec SSD 256GB, M.2 NVMe Gen3x4 SSD 2280 Local system disk configuration: RAID1 using mdadm Additional local disk: ST6000NM0044 RAM: 64GB (2x32GB sticks of Crucial Pro 64GB DDR5 RAM Kit (2x32GB), 5600MHz (or 5200MHz or 4800MHz) Desktop Memory UDIMM 288-pin) NIC: Dual Intel Corporation 82576 Gigabit Network Connection Definitely casual/home-lab setup. All commodity hardware (except the SSDs). The storage is almost certainly a bottleneck across the board. Interestingly, my backups (usually a trigger for a crash) had been running fine on the new kernel suggested by [dinhngtu] until I kicked off a cloud backup (to backblaze). I don't know exactly how xenorchestra is passing data up to cloud servers, but if it's mounted as block storage, my slow cable modem upload is absolutely going to perform horribly. I know it's slow. I just usually let it run for the few days it takes to push it up. I only do this once per month. The VM's are almost certainly overprovisioned on CPU. I do not overprovision RAM. dom0 has 8G and 16 vCPU's (I certainly do not recall setting either number; I think the installer did this). Excluding dom0, I have 23 vCPU's allocated across 7 running VMs. The CPU has 12 physical cores (along with the usual "hyperthreading" or whatever AMD calls it in the Ryzen architecture). All storage is local storage. I'm looking at acquiring some shared storage. All of that to say: this entire rig in this configuration (including the VM's) ran flawlessly on 8.2LTS. I didn't start having issues until I upgraded to 8.3. Having said that, it also ran for several months on 8.3 until I started getting crashes, which have been becoming increasingly common (to the point of stopping my backups to avoid corrupt virtual disks). I think maybe there really is a hardware problem going on here. I got mine as professionally refurbished Dell PowerEdge R620 three of them from Bargain Hardware in the United Kingdom. They are proving themselves to be highly stable and performant even if they are several generations old. Plus they’ve been through strenuous testing by Bargain Hardware, proper servers from them are extremely good. Plus my home lab were for less than you might think. The refurbishment company also has for Dell from Generation 13 to 17, then for HPE from Generation 9 to 11 and finally SuperMicro from Generation 9 to 13. When the servers are for home lab deployment, let them know and they can add a discount (for home labs - non commercial and personal use).

@ovicz I've built xapi-26.1.16-1.2.0.pirq.1.xcpng8.3 on xcp-ng-ndinh2. You can update as usual, then install my packages on top.

I went digging and three threads turned up people who already have this hardware. @yeopil21 in https://xcp-ng.org/forum/topic/11799 had an LPe37102-D on a Dell R770 that never showed up at all, @jinju0504 in https://xcp-ng.org/forum/topic/11946 ended up on the -alt package on an R670, and @lukas in https://xcp-ng.org/forum/topic/8847 was running an LPe31002-M6-D with NVMe-oF back on 8.3 beta2. That last one is the older generation, so I'd guess it's the side where you most want to hear nothing regressed. Tagging them in case the cards are still on their benches.

@seanmcg182 's post might be the answer to the original question, two years late. Your lspci -s 0000:05:00.0 -v at post 8 shows (rev ff) and !!! Unknown header type 7f, which is the same pair he had, and in his case it came from bifurcating the wrong PCIe port in the BIOS rather than from anything XCP-ng was doing. He says the unknown header is what then produced the device or resource busy error on VM start, which is the error you opened with. I don't know whether your board exposes bifurcation the way his X10DRH-CT does, so it might not transfer at all. @kuznetcoff777 if that machine is still around, it'd be worth a look either way.

@yllar said: @yannsionneau Hi, any news on the new iso? Hello @yllar In case you missed it, the ISO was released a few days ago: https://xcp-ng.org/blog/2026/08/14/xcp-ng-8-3-lts-refreshed-installation-isos/

Very cool, thanks for the feedback @maximsachs !

@poddingue, that is true, my first post here. I'll try to play with these BIOS settings again. and keep you posted. Cheers

Drivers are actually in @Team-Hypervisor-Kernel scope nowadays

@yannsionneau , may this link helps if you not anyway know it https://medium.com/@timemaster5/getting-amd-phoenix-igpu-passthrough-working-on-xen-xcp-ng-8856593f9c0d I will give it a try this weekend

@MajorP93 said: What you are describing must be a storage live migration then (XenMotion). That should work across pools, yes. I stand corrected because I did not factor in this variant in my initial answer. Yes, that's it - sorry - I should have been more explicit, even if 'lumbers along' wasn't a hint //EDIT: also there is no such thing as non-pool hosts. Even a single host setup has it's own pool. Pedantic, but true I technically meant 'not hosts in the source pool' I guess.

Your write-up is the kind of thing that saves the next person a weekend. One thing worth knowing before you commit to the whole-controller route. The passthrough page has a "Passing through Keyboards and Mice" section further down, and it says XCP-ng ships /etc/xensource/usb-policy.conf with DENY rules for mice and keyboards by default. You edit those to ALLOW, then refresh with /opt/xensource/libexec/usb_scan.py -d followed by xe pusb-scan host-uuid=<host_uuid>. It's at https://docs.xcp-ng.org/compute/ under USB Passthrough. I have no idea whether that covers your USB-to-serial adapter, which is a different device class, and passing the whole controller may still be the cleaner setup for two discrete workstations anyway. Might be worth a mention to @Team-Hypervisor-Kernel on the display question, because that one still puzzles me.

@poddingue Hello, sorry for the delayed response. We had some issues with the Supermicro IPMI and were waiting for a resolution. Here are the two log files: dmesg_xcp-ng-8320250606-aacraid-legacy.log dmesg_xcp-ng-8320250606-aacraid-uefi.log The alternative kernel did not work with your xcp-ng-8.3.0-20250606-aacraid.iso. I am also providing the log after installing the standard xcp-ng-8.3.0-20250606.iso: The files can be found at https://drive.google.com/drive/folders/1H-0FEruGK26oclD2WInDSOBJhVW2k8Xz?usp=sharing, as I wasn't able to upload the log files directly to the forum. I am also ready to participate in any further testing of new images, up to and including XCP-ng 9.0.

Good to hear, thanks a lot for your feedback.

That leftover NIC is probably a stale PIF that XAPI is still holding, even though the card is physically gone, and the Refresh button re-scans rather than removing it. The docs have proper "remove a physical NIC" steps that end in forgetting the old PIF with xe pif-forget: https://docs.xcp-ng.org/networking/#remove-a-physical-nic. For the GPU side, the PCI passthrough flow (hiding the device from dom0, then assigning it) is here: https://docs.xcp-ng.org/compute#detaching-a-pci-device. If the GPU still won't show up as assignable once the stale PIF is gone, it might be worth a mention to @Team-Hypervisor-Kernel.

@poddingue Thank you kindly! Honestly, whatever organizational structure you think is best is fine by me.

Thank you all (@olivierlambert , @teddyastie ) for your valuable responses

@tjkreidl I found that some Intel PRO GPU card have SRV-IO without any additional license, but this functionality is supported in Linux kernel 6.12 and up. I hope in new XCP-NG will have 6.12+ and support GPU sharing.

@taghjichte From my testing you would need to passthought a device for audio. If need for professional audio work then yes a pci passthough would be the perferred option. With that said. @dinhngtu As for sound I have never looked much into it but the only vm I heard make sound is from Fedora even while booted from install iso. Kubuntu or windows with xen drivers installed no audio. (find for me at the moment) While audio seems to work in Fedora from iso it seems to be limited to left channel. Local system is connected to 5.1 sound.

Nice!! Thanks for the feedback @mattrc , it's really cool to see that you can fully enjoy your machine