DebTik/internal/aerotun/health.go

package aerotun

import (
	"encoding/json"
	"fmt"
	"os"
	"path/filepath"
	"sync"
	"time"

	"golang.org/x/sys/unix"
)

const healthHistoryLimit = 500

type HealthEvent struct {
	Time                    time.Time `json:"time"`
	TunnelID                string    `json:"tunnel_id"`
	Name                    string    `json:"name"`
	Type                    string    `json:"type"`
	Status                  string    `json:"status"`
	Previous                string    `json:"previous,omitempty"`
	PreviousDurationSeconds float64   `json:"previous_duration_seconds,omitempty"`
	Detail                  string    `json:"detail,omitempty"`
}

type healthState struct {
	name, status string
	since        time.Time
}
type healthMonitor struct {
	mu             sync.Mutex
	checkMu        sync.Mutex
	path           string
	events         []HealthEvent
	states         map[string]healthState
	done, stopped  chan struct{}
	once           sync.Once
	lastCPUSeconds float64
	lastCPUAt      time.Time
	processCPU     *float64
}

func newHealthMonitor(path string) *healthMonitor {
	h := &healthMonitor{path: path, states: make(map[string]healthState), done: make(chan struct{}), stopped: make(chan struct{})}
	if data, err := os.ReadFile(path); err == nil && len(data) <= 1024*1024 {
		_ = json.Unmarshal(data, &h.events)
	}
	if len(h.events) > healthHistoryLimit {
		h.events = h.events[len(h.events)-healthHistoryLimit:]
	}
	return h
}
func (h *healthMonitor) stop() { h.once.Do(func() { close(h.done) }); <-h.stopped }
func tunnelHealthStatus(t TunnelInstance) string {
	if t.Disabled {
		return "disabled"
	}
	if !t.Running {
		if t.LastError != "" {
			return "error"
		}
		return "stopped"
	}
	if t.Connected {
		return "connected"
	}
	return "waiting"
}
func (h *healthMonitor) addLocked(e HealthEvent) {
	h.events = append(h.events, e)
	if len(h.events) > healthHistoryLimit {
		h.events = append([]HealthEvent(nil), h.events[len(h.events)-healthHistoryLimit:]...)
	}
}
func (h *healthMonitor) saveLocked() error {
	data, err := json.Marshal(h.events)
	if err != nil {
		return err
	}
	if err = os.MkdirAll(filepath.Dir(h.path), 0700); err != nil {
		return err
	}
	f, err := os.CreateTemp(filepath.Dir(h.path), ".aerotun-health-*")
	if err != nil {
		return err
	}
	defer os.Remove(f.Name())
	if err = f.Chmod(0600); err == nil {
		_, err = f.Write(data)
	}
	if err == nil {
		err = f.Sync()
	}
	if closeErr := f.Close(); err == nil {
		err = closeErr
	}
	if err != nil {
		return err
	}
	return os.Rename(f.Name(), h.path)
}
func (h *healthMonitor) observe(rows []TunnelInstance, now time.Time) {
	h.mu.Lock()
	defer h.mu.Unlock()
	var usage unix.Rusage
	if unix.Getrusage(unix.RUSAGE_SELF, &usage) == nil {
		seconds := float64(usage.Utime.Sec) + float64(usage.Utime.Usec)/1e6 + float64(usage.Stime.Sec) + float64(usage.Stime.Usec)/1e6
		elapsed := now.Sub(h.lastCPUAt).Seconds()
		if !h.lastCPUAt.IsZero() && elapsed > 0 && seconds >= h.lastCPUSeconds {
			v := (seconds - h.lastCPUSeconds) / elapsed * 100
			h.processCPU = &v
		}
		h.lastCPUAt = now
		h.lastCPUSeconds = seconds
	}
	seen := make(map[string]bool)
	changed := false
	for _, row := range rows {
		seen[row.ID] = true
		status := tunnelHealthStatus(row)
		old, ok := h.states[row.ID]
		if !ok || old.status != status {
			e := HealthEvent{Time: now, TunnelID: row.ID, Name: row.Name, Type: "state", Status: status, Detail: row.LastError}
			if ok {
				e.Previous = old.status
				e.PreviousDurationSeconds = now.Sub(old.since).Seconds()
			}
			h.addLocked(e)
			h.states[row.ID] = healthState{name: row.Name, status: status, since: now}
			changed = true
		} else if old.name != row.Name {
			old.name = row.Name
			h.states[row.ID] = old
		}
	}
	for id, old := range h.states {
		if !seen[id] {
			h.addLocked(HealthEvent{Time: now, TunnelID: id, Name: old.name, Type: "state", Status: "removed", Previous: old.status, PreviousDurationSeconds: now.Sub(old.since).Seconds()})
			delete(h.states, id)
			changed = true
		}
	}
	if changed {
		if err := h.saveLocked(); err != nil {
			fmt.Fprintf(os.Stderr, "AeroTUN health history: %v\n", err)
		}
	}
}
func (h *healthMonitor) history(id string) []HealthEvent {
	h.mu.Lock()
	defer h.mu.Unlock()
	out := make([]HealthEvent, 0, len(h.events))
	for i := len(h.events) - 1; i >= 0; i-- {
		if id == "" || h.events[i].TunnelID == id {
			out = append(out, h.events[i])
		}
	}
	return out
}
func (h *healthMonitor) status(id string) (string, time.Time) {
	h.mu.Lock()
	defer h.mu.Unlock()
	s := h.states[id]
	return s.status, s.since
}
func (m *Manager) monitorHealth() {
	defer close(m.health.stopped)
	tick := time.NewTicker(2 * time.Second)
	defer tick.Stop()
	for {
		m.health.observe(m.List(), time.Now())
		select {
		case <-m.health.done:
			return
		case <-tick.C:
		}
	}
}
func (m *Manager) HealthHistory(id string) []HealthEvent {
	if m.health == nil {
		return []HealthEvent{}
	}
	return m.health.history(id)
}
func (m *Manager) ProcessCPUPercent() *float64 {
	if m.health == nil {
		return nil
	}
	m.health.mu.Lock()
	defer m.health.mu.Unlock()
	if m.health.processCPU == nil {
		return nil
	}
	v := *m.health.processCPU
	return &v
}

type HealthSummary struct {
	TunnelID string    `json:"tunnel_id"`
	Status   string    `json:"status"`
	Since    time.Time `json:"since"`
}

func (m *Manager) HealthSummaries() []HealthSummary {
	rows := m.List()
	out := make([]HealthSummary, 0, len(rows))
	for _, t := range rows {
		status, since := tunnelHealthStatus(t), time.Time{}
		if m.health != nil {
			if recorded, at := m.health.status(t.ID); recorded == status {
				since = at
			}
		}
		out = append(out, HealthSummary{TunnelID: t.ID, Status: status, Since: since})
	}
	return out
}