bee/audit/internal/platform/live_metrics.go

package platform

import (
	"bufio"
	"os"
	"strconv"
	"strings"
	"time"
)

// LiveMetricSample is a single point-in-time snapshot of server metrics
// collected for the web UI metrics page.
type LiveMetricSample struct {
	Timestamp  time.Time      `json:"ts"`
	Fans       []FanReading   `json:"fans"`
	Temps      []TempReading  `json:"temps"`
	PowerW     float64        `json:"power_w"`
	CPULoadPct float64        `json:"cpu_load_pct"`
	MemLoadPct float64        `json:"mem_load_pct"`
	GPUs       []GPUMetricRow `json:"gpus"`
}

// TempReading is a named temperature sensor value.
type TempReading struct {
	Name    string  `json:"name"`
	Celsius float64 `json:"celsius"`
}

// SampleLiveMetrics collects a single metrics snapshot from all available
// sources: GPU (via nvidia-smi), fans and temperatures (via ipmitool/sensors),
// and system power (via ipmitool dcmi). Missing sources are silently skipped.
func SampleLiveMetrics() LiveMetricSample {
	s := LiveMetricSample{Timestamp: time.Now().UTC()}

	// GPU metrics — try NVIDIA first, fall back to AMD
	if gpus, err := SampleGPUMetrics(nil); err == nil && len(gpus) > 0 {
		s.GPUs = gpus
	} else if amdGPUs, err := sampleAMDGPUMetrics(); err == nil && len(amdGPUs) > 0 {
		s.GPUs = amdGPUs
	}

	// Fan speeds — skipped silently if ipmitool unavailable
	fans, _ := sampleFanSpeeds()
	s.Fans = fans

	// CPU/system temperature — returns 0 if unavailable
	cpuTemp := sampleCPUMaxTemp()
	if cpuTemp > 0 {
		s.Temps = append(s.Temps, TempReading{Name: "CPU", Celsius: cpuTemp})
	}

	// System power — returns 0 if unavailable
	s.PowerW = sampleSystemPower()

	// CPU load — from /proc/stat
	s.CPULoadPct = sampleCPULoadPct()

	// Memory load — from /proc/meminfo
	s.MemLoadPct = sampleMemLoadPct()

	return s
}

// sampleCPULoadPct reads two /proc/stat snapshots 200ms apart and returns
// the overall CPU utilisation percentage.
var cpuStatPrev [2]uint64 // [total, idle]

func sampleCPULoadPct() float64 {
	total, idle := readCPUStat()
	if total == 0 {
		return 0
	}
	prevTotal, prevIdle := cpuStatPrev[0], cpuStatPrev[1]
	cpuStatPrev = [2]uint64{total, idle}
	if prevTotal == 0 {
		return 0
	}
	dt := float64(total - prevTotal)
	di := float64(idle - prevIdle)
	if dt <= 0 {
		return 0
	}
	pct := (1 - di/dt) * 100
	if pct < 0 {
		return 0
	}
	if pct > 100 {
		return 100
	}
	return pct
}

func readCPUStat() (total, idle uint64) {
	f, err := os.Open("/proc/stat")
	if err != nil {
		return 0, 0
	}
	defer f.Close()
	sc := bufio.NewScanner(f)
	for sc.Scan() {
		line := sc.Text()
		if !strings.HasPrefix(line, "cpu ") {
			continue
		}
		fields := strings.Fields(line)[1:] // skip "cpu"
		var vals [10]uint64
		for i := 0; i < len(fields) && i < 10; i++ {
			vals[i], _ = strconv.ParseUint(fields[i], 10, 64)
		}
		// idle = idle + iowait
		idle = vals[3] + vals[4]
		for _, v := range vals {
			total += v
		}
		return total, idle
	}
	return 0, 0
}

func sampleMemLoadPct() float64 {
	f, err := os.Open("/proc/meminfo")
	if err != nil {
		return 0
	}
	defer f.Close()
	vals := map[string]uint64{}
	sc := bufio.NewScanner(f)
	for sc.Scan() {
		fields := strings.Fields(sc.Text())
		if len(fields) >= 2 {
			v, _ := strconv.ParseUint(fields[1], 10, 64)
			vals[strings.TrimSuffix(fields[0], ":")] = v
		}
	}
	total := vals["MemTotal"]
	avail := vals["MemAvailable"]
	if total == 0 {
		return 0
	}
	used := total - avail
	return float64(used) / float64(total) * 100
}