Just a quick question:Would this energy efficiency gain be available only on bare metal installations or also if running OPNsense as a VM through Proxmox?I am running OPNsense through Proxmox installed on Protectli VP2420.
I also use a Protectli VP2420, and after the 24.7 update have had higher CPU temps and utilization. After a little research on things to mitigate the problem, I added the "dev.cpu.0.cx_lowest" tunables.This reduced my CPU temps by ~4C, and haven't noticed any issues. I was concerned about possible stability or latency issues, but so far it has been a positive improvement.
Quote from: irrenarzt on September 14, 2024, 02:10:05 amI also use a Protectli VP2420, and after the 24.7 update have had higher CPU temps and utilization. After a little research on things to mitigate the problem, I added the "dev.cpu.0.cx_lowest" tunables.This reduced my CPU temps by ~4C, and haven't noticed any issues. I was concerned about possible stability or latency issues, but so far it has been a positive improvement.Instead of doing one entry for each cpu in Tunables, you can just do hw.acpi.cpu.cx_lowest = C3 one time
You cannot in any way control CPU power states from within a VM. That has to be done on your hypervisor, i.e. Proxmox.In the case of OPNsense running on hardware: yes, you are supposed to add tunables that are not present in the default setup.
Correct, I forgot to mention yesterday, I am also using the Tunable dev.hwpstate_intel.x.epp = 90 (x = 0...5), on top of the dev.cpu.y.cx_lowest = C3 (y = 0...11)Please could you share the link to the site with the information on what CPUs are compatible with the PowerD daemon, thank you
Quote from: logi on September 13, 2024, 02:09:59 pmCorrect, I forgot to mention yesterday, I am also using the Tunable dev.hwpstate_intel.x.epp = 90 (x = 0...5), on top of the dev.cpu.y.cx_lowest = C3 (y = 0...11)Please could you share the link to the site with the information on what CPUs are compatible with the PowerD daemon, thank youSorry. I don't have a link i could provide. I just tried different settings of PowerD and saw no effect on frequencies or temperature. Afterwards i searched the forum and found some discussions about the topic that confirmed my suspicions. In general, i guess, all CPUs that support Intel Speedshift have to use hwp instead of PowerD. Maybe you can find some information in the official FreeBSD documentation (https://docs.freebsd.org/en/books/handbook/config/#hwpstate_intel).