A slight idle power consumption increase/regression recently

I’ve noticed that for the past three to four months of NVIDIA Linux driver releases the idle power consumption has slightly increased from 8W to around 11W for my GTX 1660 Ti. It’s not bothering me too much considering I’ve got a desktop PC but it still would be great to get back to the previous numbers/behavior because under Windows 10 it’s also around 8W.

System information:

GPU: GTX 1660 Ti
MB: TUF GAMING X570-PLUS (WI-FI)
CPU: Ryzen 5800X
OS: Fedora 35
Kernel: 5.14.13 vanilla
DE: XFCE with no compositing

X.org’s configuration:

Section "Device"
    Identifier  "Videocard0"
    Driver      "nvidia"
    VendorName  "NVIDIA"
    BoardName   "NVIDIA Corporation TU116 [GeForce GTX 1660 Ti] (rev a1)"
    Option      "Coolbits" "28"
    Option      "metamodes" "nvidia-auto-select +0+0 {ForceCompositionPipeline=On, ForceFullCompositionPipeline=On}"
    Option      "UseNvKmsCompositionPipeline" "Off"
EndSection

dmesg messages

input: HDA NVidia HDMI/DP,pcm=3 as /devices/pci0000:00/0000:00:03.1/0000:08:00.1/sound/card0/input4
input: HDA NVidia HDMI/DP,pcm=7 as /devices/pci0000:00/0000:00:03.1/0000:08:00.1/sound/card0/input5
input: HDA NVidia HDMI/DP,pcm=8 as /devices/pci0000:00/0000:00:03.1/0000:08:00.1/sound/card0/input6
input: HDA NVidia HDMI/DP,pcm=9 as /devices/pci0000:00/0000:00:03.1/0000:08:00.1/sound/card0/input7
input: HDA NVidia HDMI/DP,pcm=10 as /devices/pci0000:00/0000:00:03.1/0000:08:00.1/sound/card0/input8
input: HDA NVidia HDMI/DP,pcm=11 as /devices/pci0000:00/0000:00:03.1/0000:08:00.1/sound/card0/input9
input: HDA NVidia HDMI/DP,pcm=12 as /devices/pci0000:00/0000:00:03.1/0000:08:00.1/sound/card0/input10
nvidia: loading out-of-tree module taints kernel.
nvidia: module license 'NVIDIA' taints kernel.
nvidia-nvlink: Nvlink Core is being initialized, major device number 248
nvidia 0000:08:00.0: vgaarb: changed VGA decodes: olddecodes=io+mem,decodes=none:owns=io+mem
NVRM: loading NVIDIA UNIX x86_64 Kernel Module  495.29.05  Thu Sep 30 16:00:29 UTC 2021
nvidia-modeset: Loading NVIDIA Kernel Mode Setting Driver for UNIX platforms  495.29.05  Thu Sep 30 15:50:43 UTC 2021
[drm] [nvidia-drm] [GPU ID 0x00000800] Loading driver
[drm] Initialized nvidia-drm 0.0.0 20160202 for 0000:08:00.0 on minor 0
caller os_map_kernel_space.part.0+0x6d/0x90 [nvidia] mapping multiple BARs
$ cat /proc/driver/nvidia/params:
ResmanDebugLevel: 4294967295
RmLogonRC: 1
ModifyDeviceFiles: 1
DeviceFileUID: 0
DeviceFileGID: 0
DeviceFileMode: 438
InitializeSystemMemoryAllocations: 1
UsePageAttributeTable: 4294967295
EnableMSI: 1
RegisterForACPIEvents: 1
EnablePCIeGen3: 0
MemoryPoolSize: 0
KMallocHeapMaxSize: 0
VMallocHeapMaxSize: 0
IgnoreMMIOCheck: 0
TCEBypassMode: 0
EnableStreamMemOPs: 0
EnableUserNUMAManagement: 1
NvLinkDisable: 0
RmProfilingAdminOnly: 1
PreserveVideoMemoryAllocations: 0
EnableS0ixPowerManagement: 0
S0ixPowerManagementVideoMemoryThreshold: 256
DynamicPowerManagement: 3
DynamicPowerManagementVideoMemoryThreshold: 200
RegisterPCIDriver: 1
EnablePCIERelaxedOrderingMode: 0
EnableGpuFirmware: 18
RegistryDwords: ""
RegistryDwordsPerDevice: ""
RmMsg: ""
GpuBlacklist: ""
TemporaryFilePath: ""
ExcludedGpus: ""

$ cat /proc/driver/nvidia/gpus/0000:08:00.0/power
Runtime D3 status:          Disabled by default
Video Memory:               Active

GPU Hardware Support:
 Video Memory Self Refresh: Supported
 Video Memory Off:          Supported

Power Limits:
 Default:                   N/A milliwatts
 GPU Boost:                 N/A milliwatts
2 Likes

Has anyone paid attention to this? I know it because I see it on the screen at all times.

1 Like

Bump.

1 Like