Recent content by gurubert

  1. gurubert

    OSD crash blockiert gaanzen Ceph Kluster

    Sind die OSDs mit Version 19 erstellt worden? https://docs.clyso.com/docs/kb/known-bugs/squid/ Wobei in der Fehlerbeschreibung kein Hängen sondern ein Crash erwähnt wird.
  2. gurubert

    CheckMK Fehler Proxmox Monitoring: PVEScheduler und Interface Speed

    Beim Interface warnt Checkmk, weil sich die Geschwindigkeit seit dem ersten Service Discovery geändert hat. Ist das tatsächlich der Fall (von 10G auf 1G)? Oder ist das jetzt einfach anderes Interface an dem Index? Dann sollte besser der Interfacename im Servicenamen auftauchen. Dafür gibt es in...
  3. gurubert

    Ceph flapping OSDs - OSDs only using public network not the cluster one

    OSDs need both networks (Ceph public_network and cluster_network) to function on all nodes to be able to properly work . If one of these two networks do not work the OSDs flap.
  4. gurubert

    Promiscuous Port in PVE Cluster

    Is it configurable after you manually migrate the VM to node 2? What happens to the mirror port on node 1 after the migration?
  5. gurubert

    latency on ceph ssd

    Slow networking also adds latency.
  6. gurubert

    Ceph in 2026 HDD

    For erasure coding with k=8 and m=3 you need at least 12 nodes.
  7. gurubert

    ProxMox SDN

    The cluster should come back.
  8. gurubert

    ProxMox SDN

    All VMs will stop working as the Ceph cluster will stop working. The Proxmox cluster also will stop working.
  9. gurubert

    Connect Proxmox 9 to VMFS via iSCSI in read-only mode.

    There is the vmfs-tools package available on Debian. But this is out of the support scope of Proxmox.
  10. gurubert

    Proxmox / Ceph / Backups & Replica Policy

    Isn't the issue here that the client process requesting the data from the OSDs needs to know where in the CRUSH topology it runs? In a hyperconverged cluster with only three nodes this may be a very good optimization, because there all data is stored on the local node. In larger clusters this is...
  11. gurubert

    [SOLVED] Node in other building keeps showing up as offline to other 2 nodes, possible corosync issues?

    Ping times are way too high for corosync. And do I read that correctly that there is an Internet connection involved? Do you use some kind of VPN between the sites? As can be seen with the round trip times (rtt min/avg/max/mdev = 15.667/25.435/33.892/3.466 ms) there is also much jitter on the...
  12. gurubert

    [SOLVED] Node in other building keeps showing up as offline to other 2 nodes, possible corosync issues?

    What is the network latency between the nodes on the network used for corosync? is this network on a shared medium? Can there be congestion?
  13. gurubert

    Ceph OSD crashes on I/O errors under light load with kernel 7.x - ssd via pcie adapter - FIXED with 6.17.13-7-pve

    When even the kernel shows an IO error (in dmesg) it is time to replace the device.
  14. gurubert

    How to update the web interface after changing hostname from terminal without reboot?

    After changing the hostname a reboot is recommended as other services may also still use the old hostname.