Search results

There is enough RAM available for 9 SSD OSDs in each host. You usually calculate with 5 GB RAM per OSD.

Your placement groups are not active, meaning no data transfer (read or write) can take place. You seem to have only one host (pve01) with OSDs. With the default replication size of 3 and the default failure zone "host" Ceph is unable to place the second and third copy. You need to add at least...

The default route (gateway 192.168.1.200) goes via vmbr0, so when you pull the cable from enp87s0 the host is only reachable from within its LAN 192.168.1.0/24.

Max 67000 IOPS bzw 3,2GB/s sieht doch gar nicht so schlecht aus. Das ist dann die summierte Performance, die über alle VMs zu erwarten ist. Die einzelne VM erhält eher das Ergebnis mit 4K und 1 IO-Thread.

Ich hoffe, auf dem VM-Image vm-113-disk-0 war nichts wichtiges drauf… Für 4K Blocksize und 4 Threads sieht das ganz OK aus. Setz die iodepth mal auf 128 und danach die bs auf 4M mit einer iodepth von 8 oder 16.

Direkt auf dem Proxmox-Knoten. Fio hat auch die Möglichkeit, mit RBDs zu sprechen.

Mach den Test mit fio mal direkt auf einem RBD zum Vergleich. Und spiele mal mit den Parameter --bs und --iodepth.

Ceph is all abaout data consistency. It is not guaranteed that the single remaining copy is a valid copy. This can only be assured when there is a "majority" of copies available that are all the same. It's basically the same principle like with the quorum of the MONs. BTW: It is not the number...

This is because the data will be moved from other OSDs. Give Ceph time to do it.

Set the reweight value for the OSDs back to 1.0

KRBD is an option in the storage configuration of Proxmox. It can be enabled or disabled on the pool and affects all VMs stored there. You would need to create a new pool in Ceph and a new storage on that pool in Proxmox without the KRBD setting. After that you could migrate the VM image to...

Do you happen to use KRBD for the VMs? With LVM on top of a mapped RBD? What is the load of the machines and how saturated is the network? Have you tried to switch to qemu+rbd (userspace RBD) for this VM?

You need to add the physical port eth0 to the bridge vmbr0. Without that there is no way for the network packets to reach the Internet.

Have you enabled compression on the RBD pool for the "vm-compression" storage? https://docs.ceph.com/en/latest/rados/configuration/bluestore-config-ref/#inline-compression

Why would a virtualized Ubuntu 24.04 not be supported by KVM / Proxmox? If you made a snapshot of the VM before the upgrade you could roll back to it.

Weird things can happen when the MTU sizes of the involved interfaces do not match.

The hostname mirrors.tencentyun.com has no IP address in the global DNS. download.proxmox.com seems to be blocked on the "Great Firewall".

I learn something new every day. :)

I do not think that it is possible to live migrate a container. A container are just processes running in a different namespace on the host's kernel. You cannot freeze a process and transport it to another host and unfreeze it there like you can do with a virtual machine.

AFAIK the IPv6 link local address is assigned automatically by the Linux kernel whenever a new interface goes up. As the bridge interface "Servers" should only transport Ethernet to and from the VMs and not the host you could disable IPv6 on it entirely: echo '1' >...