Bottleneck at 200 MiB/s?! 7 Node Ceph NVME & SSD Cluster

relink

New Member
Aug 22, 2024
14
1
3
Hey friends,

Observing strange performance limitation.

Backups PBS & Veeam topping out at around 200 MiB/s..

Esp. Veeam is telling, the bottleneck is actually the "source", which is the ceph cluster.

Backup Vault is capable of much more than this (24 x 14 TBs ZFS Z2 volume)

Each node is utilizing MLAG with 2x 25Gbit/s.
VMs using 10Gbit/s NIC virtio.

None of the OSD is showing high latencies or commit/apply issues while reading from ceph.

Did some screenshots, I've no idea what is limiting my transfer speeds...

Who has an idea? :)
 

Attachments

  • osd.png
    osd.png
    161.7 KB · Views: 4
  • pbs.png
    pbs.png
    85.9 KB · Views: 4
  • Screenshot 2025-02-03 125334.png
    Screenshot 2025-02-03 125334.png
    68.8 KB · Views: 5
  • Screenshot 2025-02-03 133825.png
    Screenshot 2025-02-03 133825.png
    41.3 KB · Views: 5
  • Screenshot 2025-02-03 142303.png
    Screenshot 2025-02-03 142303.png
    7.9 KB · Views: 5