[systemd-devel] limiting NFS activity

[Lennart Poettering]

On Mo, 17.10.22 18:52, Weatherby,Gerard (gweatherby at uchc.edu) wrote:

> We have a requirement to limit / throttle the IO activity to an NFS mount for a particular system slice. I’m trying to use cgroups v2
>
> Does IODeviceLatencyTargetSec work for NFS mounts?

No. That only works for block devices. NFS does not involve block devices.

> Does cgroups v2 support net_prio? Can I set it in a /etc/systemd/system/*slice.d/*conf file?

No. cgroupsv2 does not support that.

I am not sure if NFS supports what you are trying to do at all, as
traffic generated by NFS is probably not attributed back to a process
and hence a cgroup. You might want to ask the NFS community about
that.

Lennart

--
Lennart Poettering, Berlin