Of course, follow the guides for Ceph posted previously. But in general for PVE updates we:
1) in Ceph set checkboxes for:
(any node > Ceph > OSD > Manage Global Flags)
nodeep-scrub
noout
norebalance
norecover
noscrub
2) run ha-manager...
That did not make much difference but "pci=pcie_bus_perf" this. For future reference to others:
1- CPU Type: Host and NUMA enabled
2- Check the nvme afinity and put it in CPU Affinity under CPU settings (---for d in /sys/bus/pci/devices/*/nvme...
It is on q35 otherwise it dos not let me do pcie option on the passthrough. this last change did it.
Read Test:
Jobs: 32 (f=32): [R(32)][2.5%][r=9684MiB/s][r=2479k IOPS][eta 01m:57s]
Jobs: 32 (f=32): [R(32)][4.2%][r=9630MiB/s][r=2465k IOPS][eta...
you can also use the vmware pvscsi option to emulate there scsi controller to so the VM should not know its running on KVM in proxmox rather than VMware
Building on what Francois asked -- that error "unable to get monitor info from DNS SRV with service name: ceph-mon" is a DNS resolution issue. When you don't specify the cluster or monitors explicitly, the Ceph client library tries to...
@vociferous, I apologize for the tardy reply. This was indeed the culprit! Great find and thank you!
In the interim, I have switched to console mode to mitigate it however it would be great to have this addressed upstream, or, as you said, just...
Check your VM is on chipset Q35 if not change it to Q35.
Your lspci show your drive MaxPayload is 128 bytes at the moment but the drive supports 512. so lets add "pci=pcie_bus_perf" to the vm kernel command line
ASPM policy is default try...
Here is the ouput for the affinity:
root@test1:~# for d in /sys/bus/pci/devices/*/nvme; do echo "$(dirname $d): NUMA $(cat $(dirname $d)/numa_node)"; done
/sys/bus/pci/devices/0000:c1:00.0: NUMA 0
/sys/bus/pci/devices/0000:c3:00.0: NUMA 0
I am...
Can you post the actual Windows build numbers for the affected VMs? Run winver or check Settings > System > About inside the guest. The specific build matters because Microsoft changed how VBS and Hyper-V enlightenments behave in certain updates...
Have you done owt inside the guest to tune Windows for running in a VM? Things like disabling the visual effects, killing hibernation and Fast Boot, setting the power plan to High Performance, deferring TRIM, and stripping out the background I/O...
This issue is not specific to Proxmox.
Microsoft have acknowledged the same problem on their own platforms. On Azure, VMs with VBS enabled stopped booting after the July 2025 updates. Microsoft released out-of-band patches KB5061977 and...
Run this on the host to check which NUMA node each NVMe sits on:
for d in /sys/bus/pci/devices/*/nvme; do echo "$(dirname $d): NUMA $(cat $(dirname $d)/numa_node)"; done
Then check which NUMA node your vCPUs are pinned to -- if they don't...
Das würde ich grundsätzlich anders aufziehen:
#1 VM mit OpenWRT und dann Wireguard Client als Paket nachinstallieren
Dann hast Du einen kompletten Software Router und kannst nach belieben den Traffic routen. NAT für management dazu etc...