mitchell/hamlab
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases 14 Wiki Activity

GPUs: fan speed in % per card (nvidia-smi fan.speed, hwmon pwm1); 0% shows

Browse Source 
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Mitchell-Johnson
2026-11-14 17:09:10 -08:00
co-authored by Claude Opus 5.5
parent 95bb026b7f
commit afd4688358
5 changed files with 37 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
internal/metrics/gpu.go
+17 -2
View File
@@ -49,6 +49,7 @@ type GPU struct {
PowerW float64 `json:"power_w,omitempty"`
PowerCapW float64 `json:"power_cap_w,omitempty"`
FanRPM int `json:"fan_rpm,omitempty"`
FanPct *float64 `json:"fan_pct,omitempty"` // fan speed as a % of its range: nvidia-smi's fan.speed, or the hwmon's pwm1; nil when the card has no such reading (0 is a stopped fan)
MHz float64 `json:"mhz,omitempty"` // actual clock (0 when power-gated)
ReqMHz float64 `json:"req_mhz,omitempty"` // what the driver asked for
MaxMHz float64 `json:"max_mhz,omitempty"`
@@ -479,6 +480,14 @@ func (d *gpuDev) read(x *GPU, now time.Time) {
x.PowerCapW = p / 1e6
}
x.FanRPM = int(readF(d.hwmon + "/fan1_input"))
if pwm, err := strconv.ParseFloat(strings.TrimSpace(readStr(d.hwmon+"/pwm1")), 64); err == nil {
top := readF(d.hwmon + "/pwm1_max")
if top <= 0 {
top = 255
}
v := round1(pwm / top * 100)
x.FanPct = &v
}
}
d.prevAt = now
}
@@ -762,7 +771,7 @@ func ueventValue(p, key string) string {
// sample (~20 ms and ~75 ms on a GTX 965M), no root needed. The PCI address selects the
// card, so two NVIDIA GPUs stay apart.
func (d *gpuDev) readNvidia(x *GPU) {
if out, ok := runOut("nvidia-smi", "--id="+d.bus, "--query-gpu=utilization.gpu,utilization.encoder,utilization.decoder,memory.used,memory.total,clocks.sm,clocks.max.sm,temperature.gpu,power.draw,power.limit", "--format=csv,noheader,nounits"); ok {
if out, ok := runOut("nvidia-smi", "--id="+d.bus, "--query-gpu=utilization.gpu,utilization.encoder,utilization.decoder,memory.used,memory.total,clocks.sm,clocks.max.sm,temperature.gpu,power.draw,power.limit,fan.speed", "--format=csv,noheader,nounits"); ok {
parseNvidiaQuery(x, out)
}
if out, ok := runOut("nvidia-smi", "pmon", "-c", "1", "-s", "um", "--id="+d.bus); ok {
@@ -781,7 +790,8 @@ func nvNum(s string) (float64, bool) {
}
// parseNvidiaQuery fills a GPU from one --query-gpu line in the field order readNvidia asks
// for: gpu%, encoder%, decoder%, mem used MiB, mem total MiB, SM MHz, max SM MHz, °C, W, W cap.
// for: gpu%, encoder%, decoder%, mem used MiB, mem total MiB, SM MHz, max SM MHz, °C, W, W cap,
// fan % ("[N/A]" on a card with no fan of its own: a laptop's, a passive datacentre card).
func parseNvidiaQuery(x *GPU, line string) {
f := strings.Split(strings.TrimSpace(line), ",")
if len(f) < 10 {
@@ -817,6 +827,11 @@ func parseNvidiaQuery(x *GPU, line string) {
if v, ok := nvNum(f[9]); ok {
x.PowerCapW = v
}
if len(f) > 10 {
if v, ok := nvNum(f[10]); ok {
x.FanPct = &v
}
}
}
// parseNvidiaPmon reads `nvidia-smi pmon -c 1 -s um`: a header naming the columns, then one