Adding @Team-Storage for a quick review

Let me reping @stormi or @Team-XAPI-Network

Reping @Team-Storage

Yeah, it's not surprising. Ceph S3 implementation is known to be "average" and failure-prone in those cases.

Do you know what software are they using? Ceph? Minio? Garage?

FYI, Vanny is a representative from Vinchin

Hi,

In those cases, my first bet is a memtest to check the RAM and CPU.

Ping @team-xo-frontend : don't forget to provide answers in here

I think the usual stuff: https://docs.xcp-ng.org/troubleshooting/log-files/

No it shouldn't. Have you removed the passthrough from the VM too? Without logs it's hard to tell, take a look inside if you can spot something

Are you sure your OS (TrueNAS) isn't waiting for the PCI device that's not passed through anymore?

Is it possible to tell us more about the need? Maybe it could help us to think about something on our side

We could probably make the doc even more precise. Adding @thomas-dkmt in the loop for that.

Yes but why it works with some and not others. I suspect the firmware version in the NIC itself.

Hmm it doesn't ring a bell to me. I would suggest to open a ticket in parallel so someone could take a look on next week

Hi,

Are you using QCOW2?

Exactly and that's what does the Rolling Pool Update feature

But how one could check the integrity of a few blocks without context of the parent?

If I remember some previous discussions, EVE-ng uses some features that doesn't work in nested mode with Xen.

Adding @florent and @bastien-nollet in the loop for reading those ideas on better reports and proxy automation on assignation.