refactor(aquamarine): cap the R9700 power limit from a udev rule

amdgpu registers power1_cap with its hwmon device, so a rule on each
card's hwmon add event replaces the oneshot that polled /sys/class/hwmon
for 60 s waiting for both cards to probe.

Assisted-by: Claude Code (claude-opus-5-5)
This commit is contained in:
Ryan Yin authored and ryan4yin | 二花 committed 2026-11-01 11:42:57 -06:00
1 parent 2036b97f85
commit ecf242d6ab
4 files changed
+6 -41

No files matched your search

+3 -4
View File
@@ -255,10 +255,9 @@ equivalent-generation consumer cards are "known to work", and never mentions
`Fail to open libdrm_amdgpu.so` message only appeared while the card was wedged (see "ROCm
userland in nixpkgs"). Expect `Card Series: N/A` until upstream names the R9700.
5. `hardware.amdgpu.overdrive` stays off unless undervolting is wanted; if it is turned on, set
`ppfeaturemask = "0xfff7ffff"` (nixpkgs#564601). A oneshot unit in `hardware-amd-gpu.nix` caps
both cards at 250 W through hwmon `power1_cap` to keep their fans quiet, and exits non-zero when
a card does not take the value; the cap needs no overdrive. `amdgpu.gpu_recovery=1` is set,
because the driver default is auto/off except SRIOV.
`ppfeaturemask = "0xfff7ffff"` (nixpkgs#564601). A udev rule in `hardware-amd-gpu.nix` caps both
cards at 250 W through hwmon `power1_cap` to keep their fans quiet; the cap needs no overdrive.
`amdgpu.gpu_recovery=1` is set, because the driver default is auto/off except SRIOV.
6. **Open:** set `HIP_VISIBLE_DEVICES` (and `ROCR_VISIBLE_DEVICES` where honoured) so the iGPU is
never selected; for llama.cpp prefer `--split-mode layer` or an RPC/pipeline split over tensor
parallelism, and build with `-DGGML_HIP=ON -DGPU_TARGETS=gfx1201`, no `HSA_OVERRIDE_GFX_VERSION`.
+3 -35
View File
@@ -1,6 +1,5 @@
{
pkgs,
mylib,
myvars,
...
}:
@@ -61,40 +60,9 @@
# default. amdgpu exposes the cap in microwatts and accepts anything inside [power1_cap_min,
# power1_cap_max] — 210-300 W on these cards. The set path (amdgpu_dpm_set_power_limit) has no
# overdrive gate, so the ppfeaturemask default stands.
systemd.services.amdgpu-power-cap = {
description = "Cap the power limit of every amdgpu card at 250 W";
wantedBy = [ "multi-user.target" ];
after = [ "systemd-modules-load.service" ];
path = [ pkgs.coreutils ];
serviceConfig = mylib.systemdHardening.privilegedOneshot // {
Type = "oneshot";
RemainAfterExit = true;
ExecStart = pkgs.writeShellScript "amdgpu-power-cap" ''
cap=250000000 # microwatts
want=2 # both R9700s; this host has no other amdgpu device
# The cards probe asynchronously, so retry briefly instead of racing the driver.
for _ in $(seq 1 60); do
capped=0
for hwmon in /sys/class/hwmon/hwmon*; do
[ "$(cat "$hwmon/name" 2>/dev/null)" = amdgpu ] || continue
# The subshell keeps a rejected write from printing one shell error per retry; the
# summary below is the line an operator needs.
if (echo "$cap" > "$hwmon/power1_cap") 2>/dev/null &&
[ "$(cat "$hwmon/power1_cap" 2>/dev/null)" = "$cap" ]; then
capped=$((capped + 1))
fi
done
if [ "$capped" -ge "$want" ]; then
echo "capped $capped amdgpu cards at 250 W"
exit 0
fi
sleep 1
done
echo "amdgpu power cap: only $capped of $want cards took the cap" >&2
exit 1
'';
};
};
services.udev.extraRules = ''
ACTION=="add", SUBSYSTEM=="hwmon", ATTR{name}=="amdgpu", ATTR{power1_cap}="250000000"
'';
# GPU panel in btop, and utilization/VRAM in node_exporter for the shared
# VictoriaMetrics scrape — the same shape as the Radeon iGPU hosts.
@@ -37,7 +37,6 @@ in
rapl-permissions = privilegedOneshot // {
CapabilityBoundingSet = [ "CAP_CHOWN" ];
};
amdgpu-power-cap = privilegedOneshot;
hdd-no-spindown = privilegedOneshot // {
CapabilityBoundingSet = [ "CAP_SYS_RAWIO" ];
DeviceAllow = [ "block-sd rw" ];
@@ -39,7 +39,6 @@ units "youko" [
// {
privilegedOneshot = {
rapl-permissions = privilegedUnit "aquamarine" "rapl-permissions";
amdgpu-power-cap = privilegedUnit "aquamarine" "amdgpu-power-cap";
hdd-no-spindown = privilegedUnit "youko" "hdd-no-spindown";
};
}