feat(metrics): single chart engine + full-width stacked layout
- One engine: go-analyze/charts (grafana theme) for all live metrics - Server chart: CPU temp, CPU load%, mem load%, power W, fan RPMs - GPU charts: temp, load%, mem%, power W — one card per GPU, added dynamically - Charts 1400x280px SVG, rendered at width:100% in single-column layout - Add CPU load (from /proc/stat) and mem load (from /proc/meminfo) to LiveMetricSample - Add GPU mem utilization to GPUMetricRow (nvidia-smi utilization.memory) - Document charting architecture in bible-local/architecture/charting.md Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -13,18 +13,19 @@ import (
|
||||
|
||||
// GPUMetricRow is one telemetry sample from nvidia-smi during a stress test.
|
||||
type GPUMetricRow struct {
|
||||
ElapsedSec float64
|
||||
GPUIndex int
|
||||
TempC float64
|
||||
UsagePct float64
|
||||
PowerW float64
|
||||
ClockMHz float64
|
||||
ElapsedSec float64 `json:"elapsed_sec"`
|
||||
GPUIndex int `json:"index"`
|
||||
TempC float64 `json:"temp_c"`
|
||||
UsagePct float64 `json:"usage_pct"`
|
||||
MemUsagePct float64 `json:"mem_usage_pct"`
|
||||
PowerW float64 `json:"power_w"`
|
||||
ClockMHz float64 `json:"clock_mhz"`
|
||||
}
|
||||
|
||||
// sampleGPUMetrics runs nvidia-smi once and returns current metrics for each GPU.
|
||||
func sampleGPUMetrics(gpuIndices []int) ([]GPUMetricRow, error) {
|
||||
args := []string{
|
||||
"--query-gpu=index,temperature.gpu,utilization.gpu,power.draw,clocks.current.graphics",
|
||||
"--query-gpu=index,temperature.gpu,utilization.gpu,utilization.memory,power.draw,clocks.current.graphics",
|
||||
"--format=csv,noheader,nounits",
|
||||
}
|
||||
if len(gpuIndices) > 0 {
|
||||
@@ -45,16 +46,17 @@ func sampleGPUMetrics(gpuIndices []int) ([]GPUMetricRow, error) {
|
||||
continue
|
||||
}
|
||||
parts := strings.Split(line, ", ")
|
||||
if len(parts) < 5 {
|
||||
if len(parts) < 6 {
|
||||
continue
|
||||
}
|
||||
idx, _ := strconv.Atoi(strings.TrimSpace(parts[0]))
|
||||
rows = append(rows, GPUMetricRow{
|
||||
GPUIndex: idx,
|
||||
TempC: parseGPUFloat(parts[1]),
|
||||
UsagePct: parseGPUFloat(parts[2]),
|
||||
PowerW: parseGPUFloat(parts[3]),
|
||||
ClockMHz: parseGPUFloat(parts[4]),
|
||||
GPUIndex: idx,
|
||||
TempC: parseGPUFloat(parts[1]),
|
||||
UsagePct: parseGPUFloat(parts[2]),
|
||||
MemUsagePct: parseGPUFloat(parts[3]),
|
||||
PowerW: parseGPUFloat(parts[4]),
|
||||
ClockMHz: parseGPUFloat(parts[5]),
|
||||
})
|
||||
}
|
||||
return rows, nil
|
||||
|
||||
Reference in New Issue
Block a user