Hi,
I started using OMV a few three months ago and so far found it the best solution for my home lab needs. Thanks to the community for all the great work - and a free product!
What bothers me is power consumption of the old Dell server I host OMV on. In the old days, running Windows Server 2012r2 it produced little to no perceived heat from its exhaust. Now, under OMV with Proxmox Kernel, it actually turned a small room in the basement from a perfect wine storage (always pretty cold) to a decent sweat shop. The CPU fan is always spinning and blows out really warm air. CPU load though, is typically < 2%. Drives do spin down as they should. I guess, there is no active power management for the CPU. I will add intel on watts consumption of the total system asap.
I want to reduce the power consumption of the system and I am fine with creating some latencies.
What I tried:
- powertop shows that all 8 threads spend > 95% in C6 (which should be good = idle)
- cpupower frequency-info says, that "no cpufreq-driver is available or not recognized" (free translation from German output), full output:
root@omv:~# cpupower frequency-info
analysiere CPU 0:
kein oder nicht bestimmbarer cpufreq-Treiber aktiv
Folgende CPUs laufen mit der gleichen Hardware-Taktfrequenz: Not Available
Die Taktfrequenz folgender CPUs werden per Software koordiniert: Not Available
Maximale Dauer eines Taktfrequenzwechsels: Cannot determine or is not supported.
Not Available
mögliche Regler: Not Available
Unable to determine current policy
current CPU frequency: Unable to call hardware
current CPU frequency: Unable to call to kernel
boost state support:
Supported: yes
Active: yes
2667 MHz max turbo 4 active cores
2667 MHz max turbo 3 active cores
2800 MHz max turbo 2 active cores
2933 MHz max turbo 1 active cores
Alles anzeigen
then I checked:
root@omv:~# grep INTEL_PSTATE /boot/config*
/boot/config-5.4.124-1-pve:CONFIG_X86_INTEL_PSTATE=y
/boot/config-5.4.128-1-pve:CONFIG_X86_INTEL_PSTATE=y
my hardware details are:
root@omv:~# cat /proc/cpuinfo
processor : 0
vendor_id : GenuineIntel
cpu family : 6
model : 30
model name : Intel(R) Xeon(R) CPU X3440 @ 2.53GHz
stepping : 5
microcode : 0xa
cpu MHz : 1216.593
cache size : 8192 KB
physical id : 0
siblings : 8
core id : 0
cpu cores : 4
apicid : 0
initial apicid : 0
fpu : yes
fpu_exception : yes
cpuid level : 11
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 popcnt lahf_lm pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid dtherm ida flush_l1d
bugs : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit
bogomips : 5053.98
clflush size : 64
cache_alignment : 64
address sizes : 36 bits physical, 48 bits virtual
power management:
processor : 1
vendor_id : GenuineIntel
cpu family : 6
model : 30
model name : Intel(R) Xeon(R) CPU X3440 @ 2.53GHz
stepping : 5
microcode : 0xa
cpu MHz : 1580.330
cache size : 8192 KB
physical id : 0
siblings : 8
core id : 1
cpu cores : 4
apicid : 2
initial apicid : 2
fpu : yes
fpu_exception : yes
cpuid level : 11
wp : yes
flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ht tm pbe syscall nx rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni dtes64 monitor ds_cpl vmx smx est tm2 ssse3 cx16 xtpr pdcm sse4_1 sse4_2 popcnt lahf_lm pti ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid dtherm ida flush_l1d
bugs : cpu_meltdown spectre_v1 spectre_v2 spec_store_bypass l1tf mds swapgs itlb_multihit
bogomips : 5053.98
clflush size : 64
cache_alignment : 64
address sizes : 36 bits physical, 48 bits virtual
power management:
...and the same for the other 7
Alles anzeigen
It looks to me, as if the kernel modules for intel_pstat are not available. Since I am using ZFS, I followed a recommendation to ditch standard kernel in favor or Proxmox VE kernel (current: 5.4.128-1-pve). So I went to see if the PVE forum had a solution for me and I found this post: LINK There, they recommend tuning the CPU governor to powersave mode. However, if I try that, I get:
root@omv:~# echo "powersave" | tee /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor
tee: '/sys/devices/system/cpu/cpu*/cpufreq/scaling_governor': File or Directory not found
powersave
So now, I don't know what to do.
1. What is the recommended ways to optimize power consumption on OMV?
2. Could it be that the PVE kernel lacks the features and that I have to go back to standard Debian? If so, will my ZFS drives still work as fine?
3. How can I check if my CPU supports that (pretty sure a Xeon does...) and that its activated - or if not, how to?
4. How can I add the missing modules?
Sorry for so many questions.