Search results

  1. E

    NUMA and cores per sockets + memory size

    This option is to enable numa on vm, which is recommended when you have numa enabled hardware, it is not mandatory. If you have numa hardware, it will give you better performance if you use it
  2. E

    NUMA and cores per sockets + memory size

    Not mandatory Read the text below If your system has a NUMA architecture [33] we recommend to activate the option, as this will allow proper distribution of the VM resources on the host system. This option is also required to hot-plug cores or RAM in a VM.
  3. E

    NUMA and cores per sockets + memory size

    @Alwin According to this documentation If the NUMA option is used, it is recommended to set the number of sockets to the number of nodes of the host system Now if I see my hardware root@inc1pve17:~# numactl --hardware available: 4 nodes (0-3) node 0 cpus: 0 1 2 5 6 7 24 25 26 29 30 31 node 0...
  4. E

    VM is stuck

    These are not Proxmox logs, these are your OS logs. No relationship with Proxmox
  5. E

    [SOLVED] no connection between nodes on second bonding-interface

    Ok great, you can now mark the thread as solved
  6. E

    new node cluster interface keeps going down

    Please refrain from adding system with same IP back to existing cluster directly, first remove the configuration of old server from cluster and then add the same
  7. E

    [SOLVED] Proxmox Ceph Struck at

    On further analysis it was wrong crush rule applied to the cluster which triggered the same
  8. E

    [SOLVED] Proxmox Ceph Struck at

    Problem is solved by reapplying crush-map using following command ceph osd setcrushmap -i crush2.bin where crush2 is my crushmap downloaded earlier
  9. E

    Best Hardware RAID Controller For SuperMicro x9DRT-p server

    Better don't go for RAID and use JBOD Mode instead, see if your raid controller has that option
  10. E

    [SOLVED] Proxmox Ceph Struck at

    I am getting following error on newly create ceph cluster, its been 8 hours since i created new Pool cluster: id: 1411ea40-86a9-4ff5-aabf-74213d6e0785 health: HEALTH_WARN Degraded data redundancy: 1030 pgs undersized services: mon: 8 daemons, quorum...
  11. E

    Linux Bridge 10Gbs speed

    Why you need to build from scratch for update, just download updated driver from your OEM
  12. E

    [SOLVED] no connection between nodes on second bonding-interface

    How the two nodes connected ??? back to back or via Switch? if it is a switch, check lagg status in switch
  13. E

    Issue with Proxmox HA cluster failover

    Can you post output of command pvecm status ceph -s
  14. E

    3 node HA cluster Proxmox with Ceph

    Dear @sanojs Proxmox cluster and Ceph cluster are two independent cluster Proxmox cluster can even work with Single node by manually calling "pvecm expected 1" Ceph cluster requires minimum 3 nodes, If you look at your crush map using "ceph osd tree" You will see that osd are identified...
  15. E

    Linux Bridge 10Gbs speed

    @frednks Please use virtio in the VM>Hardware>Network Devices if you have use Intel E1000 it is 1G Max
  16. E

    Storage Heavy-Duty Setup

    Questions: 1. Each VM needs high performance storage (like 1500Mb/s). Will this setup work fine? if it is Mb/s = >> 187MB/s which is low performance and it is achievable with even SAS 2. Can 5-ports bonding substitute expensive 10Gbe expansion? (To the degree of 3Gbps, I mean) if you do a...
  17. E

    [SOLVED] Ceph Node down after upgrade to 6.2

    Ok good, you can mark the thread as solved if problem is solved
  18. E

    [SOLVED] Ceph Node down after upgrade to 6.2

    What do you mean by that ??
  19. E

    [SOLVED] Ceph Node down after upgrade to 6.2

    It look good , I don't see any issue in cluster , just verify ceph nodes are able to communicate check the logs
  20. E

    [SOLVED] Ceph Node down after upgrade to 6.2

    pvecm status whether it is shown activity blocked ??
Top Bottom