slow migration speed

[giuppy]

Hi, I am migrating some test machines between nodes (10GB connection), The disk is getting transferred pretty fast then the VM state for some reason in extremely slow. Here the migration example:

2022-02-10 11:09:29 migration active, transferred 1.8 GiB of 2.0 GiB VM-state, 4.1 MiB/s
2022-02-10 11:09:30 migration active, transferred 1.8 GiB of 2.0 GiB VM-state, 5.0 MiB/s
2022-02-10 11:09:31 migration active, transferred 1.8 GiB of 2.0 GiB VM-state, 3.5 MiB/s
2022-02-10 11:09:32 migration active, transferred 1.8 GiB of 2.0 GiB VM-state, 3.3 MiB/s
2022-02-10 11:09:33 migration active, transferred 1.8 GiB of 2.0 GiB VM-state, 3.8 MiB/s
2022-02-10 11:09:34 migration active, transferred 1.8 GiB of 2.0 GiB VM-state, 4.3 MiB/s
2022-02-10 11:09:37 migration active, transferred 2.1 GiB of 2.0 GiB VM-state, 775.0 MiB/s
2022-02-10 11:09:37 average migration speed: 4.8 MiB/s - downtime 58 ms
2022-02-10 11:09:37 migration status: completed
all 'mirror' jobs are ready
drive-efidisk0: Completing block job_id...
drive-efidisk0: Completed successfully.
drive-ide0: Completing block job_id...
drive-ide0: Completed successfully.
drive-efidisk0: mirror-job finished
drive-ide0: mirror-job finished
2022-02-10 11:09:38 stopping NBD storage migration server on target.
  Logical volume "vm-149-disk-0" successfully removed
  Logical volume "vm-149-disk-1" successfully removed
2022-02-10 11:09:48 migration finished successfully (duration 00:09:21)
TASK OK

Any idea?

 

[mira]

Could it be there's a lot of data written to memory in the guest?

Please provide the output of pveversion -v and qm config 149.