jlay/tuned-amdgpu
1
0
Fork 0
Code Issues Pull requests Projects Activity

role/host_vars: properly prefix vars

Browse source
This commit is contained in:
Josh Lay 2024-08-27 06:54:55 -05:00
parent d07e6ca2fb
commit da32dcc252
No known key found for this signature in database
GPG key ID: 47AA304B2243B579
5 changed files with 41 additions and 47 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
README.md
View file

@ -3,14 +3,14 @@
Hacky solution to integrate AMDGPU power/clock control into `tuned` profiles Hacky solution to integrate AMDGPU power/clock control into `tuned` profiles
with Ansible. with Ansible.
Provides three variations of the `tuned` profiles found in `/usr/lib/tuned` Extends every `tuned` profile found in `/usr/lib/tuned`
using the [AMDGPU hwmon interfaces](https://docs.kernel.org/gpu/amdgpu/thermal.html): using the [AMDGPU hwmon interfaces](https://docs.kernel.org/gpu/amdgpu/thermal.html):
- `default`: the out-of-the-box configuration - `default`: the out-of-the-box GPU clock/power configuration
- `overclock`: the optimized card configuration. Includes all of the clock/voltage/power settings - `overclock`: the _optimized_ card configuration. Includes the clock/voltage/power settings outlined below.
- `peak`: the same as `overclock`, but with clock gating removed. May help profiling - `peak`: the same as `overclock`, but with clock gating removed. May help profiling.
Contrary to the name, `overclock` can be used to de-tune the card as well. Contrary to the name, the `overclock` profiles can be used to de-tune the card as well.
_Warning_: This is only tested with `RX6000` series GPUs, others may _not_ work properly. Use at your own risk! _Warning_: This is only tested with `RX6000` series GPUs, others may _not_ work properly. Use at your own risk!
@ -34,15 +34,14 @@ The playbook will render/make effective this config file: `/etc/tuned/amdgpu-pro
Here is a preview: Here is a preview:
```ini ```ini
gpu_clock_min=500 tuned_amdgpu_clock_min=500
gpu_clock_max=2715 tuned_amdgpu_clock_max=2715
gpumem_clock_static=1075 tuned_amdgpu_memclock_static=1075
gpu_power_multi_def=0.869969040247678 tuned_amdgpu_power_multi_def=0.869969040247678
gpu_power_multi_oc=1.0 tuned_amdgpu_power_multi_oc=1.0
gpu_mv_offset=+60 tuned_amdgpu_mv_offset=+60
``` ```
These are the result of [Variables](#Variables) below; changes outside of _Ansible_ are not immediately effective. Switching `tuned` profiles or restarting the service would be required.
Changes outside of _Ansible_ are not immediately effective. Switching `tuned` profiles or restarting the service would be required.
One can use `gamemode` for dynamic switching. Sample `~/.config/gamemode.ini` below: One can use `gamemode` for dynamic switching. Sample `~/.config/gamemode.ini` below:
@ -60,9 +59,9 @@ These are the variables you'll want to change/consider.
| Variable | Description | | Variable | Description |
|------------------------|---------------------------------------------------------------------------------------| |------------------------|---------------------------------------------------------------------------------------|
| gpu_clock_min | Sets the min (dynamic) GPU clock (in `Mhz`) for the non-default `amdgpu` profiles | | `tuned_amdgpu_clock_min` | Sets the min (dynamic) GPU clock (in `Mhz`) for the non-default `amdgpu` profiles |
| gpu_clock_max | Sets the max (dynamic) GPU clock (in `MHz`) for the non-default `amdgpu` profiles | | `tuned_amdgpu_clock_max` | Sets the max (dynamic) GPU clock (in `MHz`) for the non-default `amdgpu` profiles |
| gpumem_clock_static | Sets the _static_ memory clock for the GPU (in `MHz`). This is *not* the _effective_ data rate. _That_ would be a multiple of _this_ depending on the type of VRAM.<br/><br/>To avoid flickering this is *not* allowed to change with load, only between `default` and `overclock`/`peak` profiles. | | `tuned_amdgpu_memclock_static` | Sets the _static_ memory clock for the GPU (in `MHz`). This is *not* the _effective_ data rate. _That_ would be a multiple of _this_ depending on the type of VRAM.<br/><br/>To avoid flickering this is *not* allowed to change with load, only between `default` and `overclock`/`peak` profiles. |
| gpu_mv_offset | GPU core voltage offset. Takes +/- some integer in millivolts. Can be used to both over _and_ under volt. eg: `-50` _(undervolt `50mV` or `0.05V`)_ | | `tuned_amdgpu_mv_offset` | GPU core voltage offset. Takes +/- some integer in millivolts. Can be used to both over _and_ under volt. eg: `-50` _(undervolt `50mV` or `0.05V`)_ |
| gpu_power_multi_def | Float between `0.0` and `1.0`; controls power limit relative to the board _capability_. For _'default'_-named power profiles. | | `tuned_amdgpu_power_multi_def` | Float between `0.0` and `1.0`; controls power limit relative to the board _capability_. For _'default'_-named power profiles. |
| gpu_power_multi_oc | Similar to `gpu_power_multi_def`, for _'overclock'_-named power profiles. | | `tuned_amdgpu_power_multi_oc` | Similar to `tuned_amdgpu_power_multi_def`, for resulting _`overclock` and `peak` power profiles. |

21
host_vars/localhost.yml
View file

@ -1,26 +1,21 @@
--- ---
# the profile tries to find the card with displays attached to apply these settings. # the profile tries to find the card with displays attached to apply these settings.
# configuration of many GPUs not yet supported, one is assumed # configuration of many GPUs not yet supported, one is assumed
gpu_clock_min: "500" tuned_amdgpu_clock_min: "500"
gpu_clock_max: "2715" tuned_amdgpu_clock_max: "2715"
gpumem_clock_static: "1075" tuned_amdgpu_memclock_static: "1075"
gpu_power_multi_def: 0.869969040247678 # 281W - real default tuned_amdgpu_power_multi_def: 0.869969040247678 # 281W - real default
gpu_power_multi_oc: 1.0 # full board power capability tuned_amdgpu_power_multi_oc: 1.0 # full board power capability
# other multipliers for 323W boards like mine: # other multipliers for 323W boards like mine:
# 300W: 0.928792569659443 # 300W: 0.928792569659443
# 310: 0.959752321981424 # 310: 0.959752321981424
# sample worksheet in 'power_max multi tab calculator.ods' # sample worksheet in 'power_max multi tab calculator.ods'
gpu_mv_offset: "+25" # add 25mV or 0.025V tuned_amdgpu_mv_offset: "+45" # add 45mV / 0.045V
# gpu_mv_offset: "+75" # add 75mV or 0.075V # '-50' undervolts GPU core voltage 50mV / 0.05V; warning: here be dragons/instability
# gpu_mv_offset: "+150" # add 150mV or 0.15V
# gpu_mv_offset: "+133" # add 133mV or 0.133V
# gpu_mv_offset: "+75" # add 75mV or 0.075V
# gpu_mv_offset: "+125" # add 125mV or 0.125V
# '-50' undervolts GPU core voltage 50mV or 0.05V; untested - here be dragons/instability
# 'tuned' plugins - used to set the kernel cmdline via bootloader... and sysctl tunables # 'tuned' plugins - used to set the kernel cmdline via bootloader... and sysctl tunables
plugins: # ref: https://github.com/redhat-performance/tuned/tree/master/tuned/plugins tuned_amdgpu_plugins: # ref: https://github.com/redhat-performance/tuned/tree/master/tuned/plugins
bootloader: # 'cmdline' allows entries w/ a suffix, names should be unique across *all* profiles. values accept +/- operators bootloader: # 'cmdline' allows entries w/ a suffix, names should be unique across *all* profiles. values accept +/- operators
cmdline_amdgpu_general: "delayacct nowatchdog kvm.ignore_msrs=1 kvm_amd.npt=1 amdgpu.ppfeaturemask=0xfff7ffff" cmdline_amdgpu_general: "delayacct nowatchdog kvm.ignore_msrs=1 kvm_amd.npt=1 amdgpu.ppfeaturemask=0xfff7ffff"
cmdline_amdgpu_hugepages: "default_hugepagesz=1G hugepagesz=1G hugepages=16" cmdline_amdgpu_hugepages: "default_hugepagesz=1G hugepagesz=1G hugepages=16"

12
roles/tuned_amdgpu/tasks/main.yml
View file

@ -57,12 +57,12 @@
mode: '0644' mode: '0644'
when: vars[item] is defined when: vars[item] is defined
with_items: with_items:
- gpu_clock_min - tuned_amdgpu_clock_min
- gpu_clock_max - tuned_amdgpu_clock_max
- gpumem_clock_static - tuned_amdgpu_memclock_static
- gpu_power_multi_def - tuned_amdgpu_power_multi_def
- gpu_power_multi_oc - tuned_amdgpu_power_multi_oc
- gpu_mv_offset - tuned_amdgpu_mv_offset
become: true become: true
- name: Create custom profile directories - name: Create custom profile directories

14
roles/tuned_amdgpu/templates/amdgpu-profile.sh.j2
View file

@ -41,7 +41,7 @@ function amdgpu_profile_reset() {
echo 'r' | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage echo 'r' | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
# adjust power limit using multiplier against board capability # adjust power limit using multiplier against board capability
POWER_LIM_DEFAULT=$(/usr/bin/awk -v m="$POWER_CAP" -v n="${TUNED_gpu_power_multi_def}" 'BEGIN {printf "%.0f", (m*n)}') POWER_LIM_DEFAULT=$(/usr/bin/awk -v m="$POWER_CAP" -v n="${TUNED_tuned_amdgpu_power_multi_def}" 'BEGIN {printf "%.0f", (m*n)}')
echo "$POWER_LIM_DEFAULT" | tee "${HWMON_DIR}/power1_cap" echo "$POWER_LIM_DEFAULT" | tee "${HWMON_DIR}/power1_cap"
# extract the power-saving profile ID number # extract the power-saving profile ID number
@ -56,13 +56,13 @@ function amdgpu_profile_reset() {
} }
function amdgpu_profile_overclock() { function amdgpu_profile_overclock() {
echo "s 0 ${TUNED_gpu_clock_min}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage echo "s 0 ${TUNED_tuned_amdgpu_clock_min}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
echo "s 1 ${TUNED_gpu_clock_max}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage echo "s 1 ${TUNED_tuned_amdgpu_clock_max}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
echo "m 1 ${TUNED_gpumem_clock_static}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage echo "m 1 ${TUNED_tuned_amdgpu_memclock_static}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
# under/over-voltage is considered optional or less likely to be defined, checked before use # under/over-voltage is considered optional or less likely to be defined, checked before use
if [[ -n ${TUNED_gpu_mv_offset} ]]; then if [[ -n ${TUNED_tuned_amdgpu_mv_offset} ]]; then
echo "vo ${TUNED_gpu_mv_offset}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage echo "vo ${TUNED_tuned_amdgpu_mv_offset}" | tee /sys/class/drm/"${CARD}"/device/pp_od_clk_voltage
fi fi
# commit the changes # commit the changes
@ -74,7 +74,7 @@ function amdgpu_profile_overclock() {
echo 'manual' | tee /sys/class/drm/"${CARD}"/device/power_dpm_force_performance_level echo 'manual' | tee /sys/class/drm/"${CARD}"/device/power_dpm_force_performance_level
# adjust power limit using multiplier against board capability # adjust power limit using multiplier against board capability
POWER_LIM_OC=$(/usr/bin/awk -v m="$POWER_CAP" -v n="${TUNED_gpu_power_multi_oc}" 'BEGIN {printf "%.0f", (m*n)}') POWER_LIM_OC=$(/usr/bin/awk -v m="$POWER_CAP" -v n="${TUNED_tuned_amdgpu_power_multi_oc}" 'BEGIN {printf "%.0f", (m*n)}')
echo "$POWER_LIM_OC" | tee "${HWMON_DIR}/power1_cap" echo "$POWER_LIM_OC" | tee "${HWMON_DIR}/power1_cap"
# avoid display flickering, force OC'd memory to highest clock # avoid display flickering, force OC'd memory to highest clock

4
roles/tuned_amdgpu/templates/tuned.conf.j2
View file

@ -14,8 +14,8 @@ include=/etc/tuned/amdgpu-profile-vars.conf
type=script type=script
script={{ (tuned_amdgpu_profile_dir, 'amdgpu-clock.sh') | ansible.builtin.path_join }} script={{ (tuned_amdgpu_profile_dir, 'amdgpu-clock.sh') | ansible.builtin.path_join }}
{# call the state-managing script with the selected profile, item.0, as an argument #} {# call the state-managing script with the selected profile, item.0, as an argument #}
{% if plugins is defined %} {% if tuned_amdgpu_plugins is defined %}
{% for section, options in plugins.items() %} {% for section, options in tuned_amdgpu_plugins.items() %}
{#+ give each plugin section some space +#} {#+ give each plugin section some space +#}
[{{ section }}] [{{ section }}]
{% for key, value in options.items() %} {% for key, value in options.items() %}