Recent content by itNGO

It's just the coordinator. So hosts transfer direct....

Open a support case at Veeam.....

CLI-> pveceph pool get POOLNAME

Erasure Coding or Mirror?

This is only an issue if using Erasure Coding, isn't it?

Naja, aber da steht doch 8.1 ODER neuer.... Also wird das vermutlich bald gefixt das 8.4 als "älter" als 8.1 behandelt wird.... ;-)

Angenommen dein Interface heißt enp3s0f0 (bitte ggf. durch dein tatsächliches Interface ersetzen, z. B. eth0, eno1, etc.): # Aktuellen Offload-Status anzeigen ethtool -k enp3s0f0 # EEE-Status anzeigen ethtool --show-eee enp3s0f0 # TCP Segmentation Offload deaktivieren ethtool -K enp3s0f0...

Mit ethtool "TCP Segmentation Offload", "Checksum Offload" und "Energy Efficient Ethernet" abschalten und noch mal testen. Die Karten spacken je nach Generation und Firmware in dem Bereich gerne mal rum und haben "micro-aussetzer"... mag der Kernel nich so....

Welche Netzwerkkarte wird für die Verbindung verwendet? Hersteller/Modell?

https://forum.proxmox.com/threads/renaming-zfs-storages-in-a-cluster-for-replication.164116/#post-758375

There is no need for NFS... You can just live migrate between the nodes if CPUs are compatible or offline migrate. ZFS will do the "replica-magic" then....

Yes I know, but that changes nothing about this is clearly documented as "recommendation". Being below the recommendations and crieing that is slow does help noone. And in Enterprise Datacenter all-flash for backup is nothing special anymore... not at our DCs and not in many others I know.... If...

Using at least a Special Device for Metadata solves this. Official recommendation for PBS is still use SSDs. This has not changed. So this is more a less a self made problem for users using rotating disks. The design in PBS and its deduplication needs millions of files and short access times to...

ProxmoxVE by default always runs with "highest performance". Windows by default is using something like balanced power profile. So this is expectet. ProxmoxVE is a datacenter server virtualisation. A location where expect maximum performance at all time. You might check if tunedadm with a...

Ceph needs the disks as direct attached without any raid. "JBOD". The redundancy level is then configured inside Ceph. (3 Copies with at least 2 online in a 3-node-Cluster) About support..... there are companies outside greece which do this. And everything is possible online and by remote...