Random CPU peaks at 100% with freezes, PVE 9.2.26

arukashi

Member
Jan 21, 2023
24
18
8
Hello!
Similar post to this

I have one VM running Windows 11 (it was Win10 when problem has emerged) which from time to time peaks at 100% CPU and freezes so no RDP connection is possible. After a certain amount of time all come back to normal. No idea what could trigger it inside VM.

Looks like the problem started after upgrading PVE 9.1 to 9.2. I know about https://pve.proxmox.com/wiki/Roadmap#9.2-known-issues, but the problem started even in Win10 VM
I don't know if this is just a coincidence, but never had this problem before PVE upgrade which I had to do because of infamous CVE-2026-98432

Normally type of CPU in VM config is host. I need nested virtualization for docker, and regular x86-64-vX is not an option. This morning i managed to changed it with whatever allows me to run VM normally, from this morning no hangs (fingers-crossed).

Diagnostic info
Host CPU: Intel(R) Xeon(R) W-2295 CPU @ 3.00GHz

proxmox-ve: 9.2.0 (running kernel: 7.0.14-26-pve)
pve-manager: 9.2.26 (running version: 9.2.26/41a0e2e09b9e6f9d)
proxmox-kernel-helper: 9.2.1
pve-kernel-5.15: 7.4-15
proxmox-kernel-7.0: 7.0.14-28
proxmox-kernel-7.0.14-28-pve-signed: 7.0.14-28
proxmox-kernel-7.0.14-26-pve-signed: 7.0.14-26
proxmox-kernel-6.17: 6.17.13-21
proxmox-kernel-6.17.13-21-pve-signed: 6.17.13-21
proxmox-kernel-6.8: 6.8.12-17
proxmox-kernel-6.8.12-17-pve-signed: 6.8.12-17
pve-kernel-5.15.158-2-pve: 5.15.158-2
pve-kernel-5.15.30-2-pve: 5.15.30-3
ceph-fuse: 19.2.6-pve4
corosync: 3.2.0-pve1
criu: 4.1.1-1
frr-pythontools: 10.6.1-1+pve3
ifupdown2: 3.3.0-1+pmx13
ksm-control-daemon: 1.5-1
libjs-extjs: 7.0.0-9
libproxmox-acme-perl: 1.7.2
libproxmox-backup-qemu0: 2.0.4
libproxmox-rs-perl: 0.4.2
libpve-access-control: 9.2.0
libpve-apiclient-perl: 3.4.3
libpve-cluster-api-perl: 9.1.9
libpve-cluster-perl: 9.1.9
libpve-common-perl: 9.2.8
libpve-guest-common-perl: 6.0.7
libpve-http-server-perl: 6.0.7
libpve-network-perl: 1.6.8
libpve-notify-perl: 9.1.9
libpve-rs-perl: 0.16.0
libpve-storage-perl: 9.1.15
libspice-server1: 0.15.2-1+b1
lvm2: 2.03.31-2+pmx1
lxc-pve: 7.0.0-2
lxcfs: 7.0.0-pve1
novnc-pve: 1.7.0-2
proxmox-backup-client: 4.2.10-1
proxmox-backup-file-restore: 4.2.10-1
proxmox-backup-restore-image: 1.1.0
proxmox-enterprise-support-keyring: 1.1
proxmox-firewall: 1.2.4
proxmox-kernel-helper: 9.2.1
proxmox-mail-forward: 1.1.0
proxmox-mini-journalreader: 1.7
proxmox-offline-mirror-helper: 0.8.0
proxmox-widget-toolkit: 5.2.12
pve-cluster: 9.1.9
pve-container: 6.1.18
pve-docs: 9.2.13
pve-edk2-firmware: 4.2026.08-1
pve-esxi-import-tools: 1.0.1
pve-firewall: 6.0.7
pve-firmware: 3.18-9
pve-ha-manager: 5.2.5
pve-i18n: 3.11.0
pve-qemu-kvm: 11.1.3-1
pve-xtermjs: 6.0.0-3
qemu-server: 9.2.15
smartmontools: 7.5-pve2
spiceterm: 3.4.2
swtpm: 0.10.2+pve1
vncterm: 1.9.2
zfsutils-linux: 2.4.4-pve1

agent: 1
bios: ovmf
boot: order=ide0;virtio0
cores: 12
cpu: Skylake-Client-noTSX-IBRS,flags=+nested-virt
ide0: pvearchive-SB31:iso/virtio-win-0.1.271.iso,media=cdrom,size=709474K
machine: pc-q35-11.1
memory: 32768
meta: creation-qemu=7.0.0,ctime=1663666466
name: vm
net0: virtio=9A:05:72:F0:68:71,bridge=vmbr4004
numa: 0
onboot: 1
ostype: win11
parent: beforeuprgd
scsihw: virtio-scsi-pci
smbios1: uuid=579f389a-f9c8-4c4a-b72d-9e3ae78d99d0
sockets: 1
tablet: 1
tpmstate0: local-zfs:vm-609-disk-2,size=4M,version=v2.0
virtio0: local-zfs:vm-609-disk-1,discard=on,size=240G
virtio1: local-zfs:vm-609-disk-0,discard=on,size=280G
vmgenid: b34e3d28-8aeb-4449-b391-52b742c0753f

Any help appreciated. Thanks
 
I think your change to cpu: Skylake-Client-noTSX-IBRS,flags=+nested-virt should help. Alternatively, as mentioned in the known issues, you can try upgrading to the latest version of Proxmox VE (PVE) and setting the machine version to 11.0+pve2 (latest). Doing that should allow you to use host for the CPU type.
 
As you can see i'm already on machine: pc-q35-11.1
Changing CPU type to Skylake-Client-noTSX-IBRS kinda made things better, but freezes now happens less often and with less duration. Still not ideal
 
I would recommend testing to switch to scsihw: virtio-scsi-single with iothread=1 enabled on each disk:
Ensure you back up the VM before making any changes.

- Verify the SCSI driver: Inside Windows, go to Device Manager > Storage controllers and confirm that the Red Hat VirtIO SCSI controller driver is already installed (from your mounted virtio-win-0.1.271.iso).

- Switch the SCSI controller: Shut down the VM completely. Hardware > SCSI Controller, change it from VirtIO SCSI to VirtIO SCSI single (scsihw: virtio-scsi-single).

- Move disks from VirtIO Block to SCSI: Detach virtio0 and virtio1 (they will appear as Unused Disk 0 and Unused Disk 1). Double-click each unused disk, set Bus/Device to SCSI (scsi0 and scsi1), and check IO thread (iothread=1), Discard (discard=on).

- Verify the Boot Order: Go to Options > Boot Order.
This is based on the wiki Windows 2025 guest best practices [2].

[2] https://pve.proxmox.com/wiki/Windows_2025_guest_best_practices
 
Okay, thanks.
Current config now looks like this
agent: 1
bios: ovmf
boot: order=ide0;scsi0;scsi1
cores: 12
cpu: Skylake-Client-noTSX-IBRS,flags=+nested-virt
efidisk0: local-zfs:vm-609-disk-3,efitype=4m,ms-cert=2023k,pre-enrolled-keys=1,size=1M
ide0: pvearchive-SB31:iso/virtio-win-0.1.271.iso,media=cdrom,size=709474K
machine: pc-q35-11.0+pve2
memory: 32768
meta: creation-qemu=7.0.0,ctime=1663666466
name: vm
net0: virtio=9A:05:72:F0:68:71,bridge=vmbr4004
numa: 0
onboot: 1
ostype: win11
parent: beforeuprgd
scsi0: local-zfs:vm-609-disk-1,discard=on,iothread=1,size=240G
scsi1: local-zfs:vm-609-disk-0,discard=on,iothread=1,size=280G
scsihw: virtio-scsi-single
smbios1: uuid=579f389a-f9c8-4c4a-b72d-9e3ae78d99d0
sockets: 1
tablet: 1
tpmstate0: local-zfs:vm-609-disk-2,size=4M,version=v2.0
vmgenid: b34e3d28-8aeb-4449-b391-52b742c0753f

This morning, before i did these changes, freezes occurred once again, but for a short amount of time