I think you're asking the wrong question.
what is the workload in vm count and minimum required iops/vm? how much capacity do you need?
ceph works fine with hard drives. its just slow.
https://www.thomas-krenn.com/en/products/storage-systems/stormagic-virtual-storage/stormagic-licenses (dont wanna sell just inform - pve-ceph wins for me :-))
From your writing, you clearly do not understand what PVE is, what qm does and to read through and disentangle it all seems like a waste of time. But qm is just a client to the PVE API (it simplifies QEMU only to a few relevant commands and...
This is absolutely needed and has to be very precise. I.e. which exact metric is used for both CPU and Memory "loads": CPU load vs CPU usage vs CPU pressure, Mem usage vs Mem pressure.
Currently testing CRS in lab and it seems to allow a node to...
Hi!
In more detail, each node's current cpu and memory usage is normalized with its own capacity (i.e. cpu_load = current_cpu / max_cpu and memory_load = current_memory / max_memory), where the node's current load is then a equal-weighted...
Are there any differences regarding kernel on those nodes? the ones that work and the one that does not? Do you have any errors on node-site regarding the disks (not ceph related) but storage-device related (host bus adapter etc.)?
Don't run 'apt upgrade' as it might not pull in all dependencies; use the official instructions instead: https://pve.proxmox.com/pve-docs/pve-admin-guide.html#system_software_updates
And here is a (another) recent thread where the same problem...
could you double check and post your network configuration/setup, including the switch config? in particular of the two "problematic" nodes? this looks like a network misconfiguration problem, though the logs don't give a clear indication *what*...
Hey zusammen,
gerne möchte ich (einige kennen mich sicherlich bereits von ProxLB, PegaProx und den Ansible Modulen für PVE) euch auf das Community-Event Proxday 2026 aufmerksam machen, der von der credativ GmbH veranstaltet wird. Das Konzept ist...
I have performed 6 successful installs across 5 different Proxmox PCs with this morning's pve-qemu-kvm v11.0.0-3 using qcow2 with SSD + Trim/Discard enabled and no seen issues. I am currently now performing 3x in-place repair / upgrades across 3x...
A patch: [1], thanks to @fiona, to "disable cet-ibt and cet-ss flags for modern Windows by default" is in qemu-server 9.1.12: [2], which already is available in pve-no-subscription.
[1]...
But thats only for having issues starting a vm on a different node. Im asking because if you add another pci card to a current node. the previous id of the card might change and vm wont boot then?
Hello Dunuin is this information still valid in 2026? So cards get renamed when adding another pci card, so vm might or cause trouble? is there something like "networking"-pinning for pci-devices that are not network-cards?