v0.0.3 - To be come a daemon.

2025-12-29 23:17:09 +02:00
parent 6dd55cd2ba
commit 3ebf93d206
5 changed files with 310 additions and 47 deletions
--- a/README.md
+++ b/README.md
@@ -0,0 +1,57 @@
+# Ping Service
+
+A Go-based monitoring service that periodically pings IP addresses from a configurable input source (file, HTTP, or Unix socket), applies cooldown periods to avoid frequent pings, optionally performs traceroute on successes, and outputs JSON results to a destination (file, HTTP, or socket). Includes health checks and metrics.
+
+## Features
+- Reads IPs from file, HTTP endpoint, or Unix socket.
+- Configurable ping interval and per-IP cooldown.
+- Optional traceroute (ICMP/TCP) with max hops.
+- JSON output with ping stats and traceroute details.
+- HTTP health endpoints: `/health`, `/ready`, `/metrics`.
+- Graceful shutdown and verbose logging support.
+
+## Configuration
+Edit `config.yaml`:
+```yaml
+input_file: "http://localhost:8080"  # Or file path or socket
+output_file: "http://localhost:8081" # Or file path or socket
+interval_seconds: 30                 # Poll interval
+cooldown_minutes: 10                 # Min time between same-IP pings
+enable_traceroute: true              # Enable traceroute
+traceroute_max_hops: 30              # Max TTL
+health_check_port: 8090              # Health server port
+```
+
+## Building
+```bash
+go build -o ping_service
+```
+
+## Installation as Service (Linux)
+```bash
+chmod +x install.sh
+sudo ./install.sh
+sudo systemctl start ping-service
+```
+
+- Check status: `sudo systemctl status ping-service`
+- View logs: `sudo journalctl -u ping-service -f`
+- Stop: `sudo systemctl stop ping-service`
+
+## Usage
+Run directly:
+```bash
+./ping_service -config config.yaml -verbose
+```
+
+For testing HTTP I/O:
+- Run `python3 input_http_server.py` (serves IPs on port 8080).
+- Run `python3 output_http_server.py` (receives results on port 8081).
+
+## Health Checks
+- `curl http://localhost:8090/health` (status, uptime, stats)
+- `curl http://localhost:8090/ready` (readiness)
+- `curl http://localhost:8090/metrics` (Prometheus metrics)
+
+Version: 0.0.3
+Dependencies: `go-ping/ping`, `gopkg.in/yaml.v
--- a/config.yaml
+++ b/config.yaml
@@ -10,3 +10,4 @@ interval_seconds: 30
 cooldown_minutes: 10
 enable_traceroute: true
 traceroute_max_hops: 30
+health_check_port: 8090
--- a/install.sh
+++ b/install.sh
@@ -0,0 +1,33 @@
+#!/bin/bash
+set -e
+
+echo "Installing ping-service..."
+
+# Create user
+sudo useradd -r -s /bin/false pingservice || true
+
+# Create directories
+sudo mkdir -p /opt/ping-service
+sudo mkdir -p /var/log/ping-service
+
+# Copy files
+sudo cp ping_service /opt/ping-service/
+sudo cp config.yaml /opt/ping-service/
+sudo chown -R pingservice:pingservice /opt/ping-service
+sudo chown -R pingservice:pingservice /var/log/ping-service
+
+# Install systemd service
+sudo cp ping-service.service /etc/systemd/system/
+sudo systemctl daemon-reload
+sudo systemctl enable ping-service
+sudo systemctl start ping-service
+
+echo "✅ Installation complete!"
+echo ""
+echo "Useful commands:"
+echo "  sudo systemctl status ping-service    # Check status"
+echo "  sudo systemctl stop ping-service      # Stop service"
+echo "  sudo systemctl start ping-service     # Start service"
+echo "  sudo systemctl restart ping-service   # Restart service"
+echo "  sudo journalctl -u ping-service -f    # View logs"
+echo "  curl http://localhost:8090/health     # Health check"
--- a/ping_service.go
+++ b/ping_service.go
@@ -2,6 +2,7 @@ package main

 import (
 	"bytes"
+	"context"
 	"encoding/json"
 	"flag"
 	"fmt"
@@ -11,41 +12,46 @@ import (
 	"net/http"
 	"os"
 	"os/exec"
+	"os/signal"
 	"regexp"
 	"strconv"
 	"strings"
 	"sync"
+	"syscall"
 	"time"

 	"github.com/go-ping/ping"
 	"gopkg.in/yaml.v3"
 )

+const VERSION = "1.0.0"
+
 type Config struct {
-	InputFile       string `yaml:"input_file"`
-	OutputFile      string `yaml:"output_file"`
-	IntervalSeconds int    `yaml:"interval_seconds"`
-	CooldownMinutes int    `yaml:"cooldown_minutes"`
-	EnableTraceroute bool  `yaml:"enable_traceroute"`
-	TracerouteMaxHops int  `yaml:"traceroute_max_hops"`
+	InputFile        string `yaml:"input_file"`
+	OutputFile       string `yaml:"output_file"`
+	IntervalSeconds  int    `yaml:"interval_seconds"`
+	CooldownMinutes  int    `yaml:"cooldown_minutes"`
+	EnableTraceroute bool   `yaml:"enable_traceroute"`
+	TracerouteMaxHops int   `yaml:"traceroute_max_hops"`
+	HealthCheckPort  int    `yaml:"health_check_port"`
 }

 type PingResult struct {
-	IP         string        `json:"ip"`
-	Sent       int           `json:"sent"`
-	Received   int           `json:"received"`
-	PacketLoss float64       `json:"packet_loss"`
-	AvgRtt     time.Duration `json:"avg_rtt"`
-	Timestamp  time.Time     `json:"timestamp"`
-	Error      string        `json:"error,omitempty"`
-	Traceroute *TracerouteResult `json:"traceroute,omitempty"`
+	IP         string             `json:"ip"`
+	Sent       int                `json:"sent"`
+	Received   int                `json:"received"`
+	PacketLoss float64            `json:"packet_loss"`
+	AvgRtt     time.Duration      `json:"avg_rtt"`
+	Timestamp  time.Time          `json:"timestamp"`
+	Error      string             `json:"error,omitempty"`
+	Traceroute *TracerouteResult  `json:"traceroute,omitempty"`
 }

 type TracerouteResult struct {
-	Method    string         `json:"method"` // "icmp" or "tcp"
+	Method    string          `json:"method"`
 	Hops      []TracerouteHop `json:"hops"`
-	Completed bool           `json:"completed"`
-	Error     string         `json:"error,omitempty"`
+	Completed bool            `json:"completed"`
+	Error     string          `json:"error,omitempty"`
 }

 type TracerouteHop struct {
@@ -55,11 +61,23 @@ type TracerouteHop struct {
 	Timeout bool          `json:"timeout,omitempty"`
 }

+type HealthStatus struct {
+	Status        string    `json:"status"`
+	Version       string    `json:"version"`
+	Uptime        string    `json:"uptime"`
+	LastRun       time.Time `json:"last_run"`
+	TotalPings    int64     `json:"total_pings"`
+	SuccessfulPings int64   `json:"successful_pings"`
+	FailedPings   int64     `json:"failed_pings"`
+}
+
 var (
-	// cooldownCache stores IP -> last ping time
 	cooldownCache = make(map[string]time.Time)
 	cacheMux      sync.Mutex
 	verbose       bool
+	startTime     time.Time
+	health        HealthStatus
+	healthMux     sync.RWMutex
 )

 func main() {
@@ -67,12 +85,19 @@ func main() {
 	configPath := flag.String("config", "config.yaml", "Path to config file")
 	verboseFlag := flag.Bool("v", false, "Enable verbose logging")
 	flag.BoolVar(verboseFlag, "verbose", false, "Enable verbose logging")
+	versionFlag := flag.Bool("version", false, "Show version")
 	help := flag.Bool("help", false, "Show help message")
 	flag.Parse()

+	if *versionFlag {
+		fmt.Printf("ping-service version %s\n", VERSION)
+		os.Exit(0)
+	}
+
 	if *help {
-		fmt.Println("Ping Service - Monitor network endpoints via ping")
-		fmt.Println("\nUsage:")
+		fmt.Println("Ping Service - Monitor network endpoints via ping and traceroute")
+		fmt.Printf("Version: %s\n\n", VERSION)
+		fmt.Println("Usage:")
 		flag.PrintDefaults()
 		fmt.Println("\nConfig file format (YAML):")
 		fmt.Println("  input_file: Path/URL to file containing IPs (one per line)")
@@ -81,10 +106,18 @@ func main() {
 		fmt.Println("  cooldown_minutes: Minimum time between pings for same IP")
 		fmt.Println("  enable_traceroute: Enable traceroute after successful ping")
 		fmt.Println("  traceroute_max_hops: Maximum TTL for traceroute (default: 30)")
+		fmt.Println("  health_check_port: HTTP port for health checks (default: 8090)")
 		os.Exit(0)
 	}

 	verbose = *verboseFlag
+	startTime = time.Now()
+	
+	// Initialize health status
+	health = HealthStatus{
+		Status:  "starting",
+		Version: VERSION,
+	}

 	config := loadConfig(*configPath)
 	if config.CooldownMinutes == 0 {
@@ -93,19 +126,131 @@ func main() {
 	if config.TracerouteMaxHops == 0 {
 		config.TracerouteMaxHops = 30
 	}
+	if config.HealthCheckPort == 0 {
+		config.HealthCheckPort = 8090
+	}
+
+	// Start health check server
+	go startHealthCheckServer(config.HealthCheckPort)
+
+	// Setup graceful shutdown
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	sigChan := make(chan os.Signal, 1)
+	signal.Notify(sigChan, os.Interrupt, syscall.SIGTERM)
+
+	go func() {
+		sig := <-sigChan
+		log.Printf("Received signal %v, shutting down gracefully...", sig)
+		updateHealth("shutting_down")
+		cancel()
+	}()

 	ticker := time.NewTicker(time.Duration(config.IntervalSeconds) * time.Second)
-	log.Printf("App started. Cooldown set to %d mins. Polling every %ds...", config.CooldownMinutes, config.IntervalSeconds)
+	defer ticker.Stop()
+
+	log.Printf("App started. Version: %s", VERSION)
+	log.Printf("Cooldown set to %d mins. Polling every %ds...", config.CooldownMinutes, config.IntervalSeconds)
 	if config.EnableTraceroute {
 		log.Printf("Traceroute enabled (max %d hops)", config.TracerouteMaxHops)
 	}
+	log.Printf("Health check available at http://localhost:%d/health", config.HealthCheckPort)
+	
+	updateHealth("running")

+	// Main loop
 	for {
-		process(config)
-		<-ticker.C
+		select {
+		case <-ctx.Done():
+			log.Println("Shutdown complete")
+			return
+		case <-ticker.C:
+			process(config)
+		}
 	}
 }

+func startHealthCheckServer(port int) {
+	http.HandleFunc("/health", healthCheckHandler)
+	http.HandleFunc("/ready", readinessHandler)
+	http.HandleFunc("/metrics", metricsHandler)
+	
+	addr := fmt.Sprintf(":%d", port)
+	log.Printf("Starting health check server on %s", addr)
+	
+	server := &http.Server{
+		Addr:         addr,
+		ReadTimeout:  5 * time.Second,
+		WriteTimeout: 5 * time.Second,
+	}
+	
+	if err := server.ListenAndServe(); err != nil && err != http.ErrServerClosed {
+		log.Printf("Health check server error: %v", err)
+	}
+}
+
+func healthCheckHandler(w http.ResponseWriter, r *http.Request) {
+	healthMux.RLock()
+	defer healthMux.RUnlock()
+	
+	health.Uptime = time.Since(startTime).String()
+	
+	w.Header().Set("Content-Type", "application/json")
+	json.NewEncoder(w).Encode(health)
+}
+
+func readinessHandler(w http.ResponseWriter, r *http.Request) {
+	healthMux.RLock()
+	defer healthMux.RUnlock()
+	
+	if health.Status == "running" {
+		w.WriteHeader(http.StatusOK)
+		w.Write([]byte(`{"ready": true}`))
+	} else {
+		w.WriteHeader(http.StatusServiceUnavailable)
+		w.Write([]byte(`{"ready": false}`))
+	}
+}
+
+func metricsHandler(w http.ResponseWriter, r *http.Request) {
+	healthMux.RLock()
+	defer healthMux.RUnlock()
+	
+	// Prometheus-style metrics
+	w.Header().Set("Content-Type", "text/plain")
+	fmt.Fprintf(w, "# HELP ping_service_total_pings Total number of pings\n")
+	fmt.Fprintf(w, "# TYPE ping_service_total_pings counter\n")
+	fmt.Fprintf(w, "ping_service_total_pings %d\n", health.TotalPings)
+	
+	fmt.Fprintf(w, "# HELP ping_service_successful_pings Successful pings\n")
+	fmt.Fprintf(w, "# TYPE ping_service_successful_pings counter\n")
+	fmt.Fprintf(w, "ping_service_successful_pings %d\n", health.SuccessfulPings)
+	
+	fmt.Fprintf(w, "# HELP ping_service_failed_pings Failed pings\n")
+	fmt.Fprintf(w, "# TYPE ping_service_failed_pings counter\n")
+	fmt.Fprintf(w, "ping_service_failed_pings %d\n", health.FailedPings)
+	
+	fmt.Fprintf(w, "# HELP ping_service_uptime_seconds Uptime in seconds\n")
+	fmt.Fprintf(w, "# TYPE ping_service_uptime_seconds gauge\n")
+	fmt.Fprintf(w, "ping_service_uptime_seconds %.0f\n", time.Since(startTime).Seconds())
+}
+
+func updateHealth(status string) {
+	healthMux.Lock()
+	defer healthMux.Unlock()
+	health.Status = status
+}
+
+func updateStats(lastRun time.Time, successful, failed int) {
+	healthMux.Lock()
+	defer healthMux.Unlock()
+	health.LastRun = lastRun
+	health.TotalPings += int64(successful + failed)
+	health.SuccessfulPings += int64(successful)
+	health.FailedPings += int64(failed)
+}
+
 func loadConfig(path string) *Config {
 	f, err := os.ReadFile(path)
 	if err != nil {
@@ -120,6 +265,8 @@ func loadConfig(path string) *Config {
 }

 func process(cfg *Config) {
+	startTime := time.Now()
+	
 	// 1. Read IPs
 	data, err := readSource(cfg.InputFile)
 	if err != nil {
@@ -141,7 +288,7 @@ func process(cfg *Config) {
 				if verbose {
 					log.Printf("Skipping %s (cooldown: %v remaining)", ip, time.Duration(cfg.CooldownMinutes)*time.Minute-time.Since(last))
 				}
-				continue // Skip this IP
+				continue
 			}
 		}
 		ipsToPing = append(ipsToPing, ip)
@@ -163,13 +310,21 @@ func process(cfg *Config) {
 	// 2. Perform Pings
 	var wg sync.WaitGroup
 	results := make([]PingResult, len(ipsToPing))
+	successful := 0
+	failed := 0

 	for i, ip := range ipsToPing {
 		wg.Add(1)
 		go func(idx int, targetIP string) {
 			defer wg.Done()
 			results[idx] = runPing(targetIP)
-
+			
+			if results[idx].Error == "" && results[idx].Received > 0 {
+				successful++
+			} else {
+				failed++
+			}
+			
 			// If ping successful and traceroute enabled, do traceroute
 			if cfg.EnableTraceroute && results[idx].Error == "" && results[idx].Received > 0 {
 				if verbose {
@@ -177,7 +332,7 @@ func process(cfg *Config) {
 				}
 				results[idx].Traceroute = runTraceroute(targetIP, cfg.TracerouteMaxHops)
 			}
-
+			
 			if verbose {
 				if results[idx].Error != "" {
 					log.Printf("Pinged %s: ERROR - %s", results[idx].IP, results[idx].Error)
@@ -194,25 +349,25 @@ func process(cfg *Config) {
 	}
 	wg.Wait()

+	// Update stats
+	updateStats(time.Now(), successful, failed)
+
 	// 3. Write Output
 	outputData, _ := json.MarshalIndent(results, "", "  ")
 	err = writeDestination(cfg.OutputFile, outputData)
 	if err != nil {
 		log.Printf("Output Error: %v", err)
 	} else if verbose {
-		log.Printf("Wrote results to %s", cfg.OutputFile)
+		log.Printf("Wrote results to %s (took %v)", cfg.OutputFile, time.Since(startTime))
 	}
 }

-// Logic: If socket exists, dial it. If not, listen on it.
 func handleSocket(path string, data []byte, mode string) ([]byte, error) {
 	if _, err := os.Stat(path); err == nil {
-		// SOCKET EXISTS: Connect as Client
 		conn, err := net.DialTimeout("unix", path, 2*time.Second)
 		if err != nil {
-			// If we can't connect, the socket might be "stale" (file exists but no one listening)
 			os.Remove(path)
-			return handleSocket(path, data, mode) // Recursive call to create listener
+			return handleSocket(path, data, mode)
 		}
 		defer conn.Close()

@@ -223,7 +378,6 @@ func handleSocket(path string, data []byte, mode string) ([]byte, error) {
 			return nil, err
 		}
 	} else {
-		// SOCKET DOES NOT EXIST: Create as Server
 		l, err := net.Listen("unix", path)
 		if err != nil {
 			return nil, err
@@ -231,7 +385,6 @@ func handleSocket(path string, data []byte, mode string) ([]byte, error) {
 		defer l.Close()
 		defer os.Remove(path)

-		// Set a timeout so the app doesn't hang forever if no one connects
 		l.(*net.UnixListener).SetDeadline(time.Now().Add(10 * time.Second))

 		conn, err := l.Accept()
@@ -294,7 +447,6 @@ func runPing(ip string) PingResult {

 	pinger.Count = 3
 	pinger.Timeout = time.Second * 5
-	// pinger.SetPrivileged(true) // Uncomment if running on Linux/Windows as admin

 	err = pinger.Run()
 	if err != nil {
@@ -316,16 +468,14 @@ func runTraceroute(ip string, maxHops int) *TracerouteResult {
 		Hops:   []TracerouteHop{},
 	}

-	// Try ICMP traceroute first
 	if tr := tryICMPTraceroute(ip, maxHops); tr != nil {
 		return tr
 	}

-	// If ICMP fails, try TCP traceroute on common ports
 	if verbose {
 		log.Printf("ICMP traceroute failed for %s, trying TCP...", ip)
 	}
-
+	
 	for _, port := range []int{80, 443, 22} {
 		if tr := tryTCPTraceroute(ip, port, maxHops); tr != nil {
 			tr.Method = fmt.Sprintf("tcp/%d", port)
@@ -339,8 +489,7 @@ func runTraceroute(ip string, maxHops int) *TracerouteResult {

 func tryICMPTraceroute(ip string, maxHops int) *TracerouteResult {
 	var cmd *exec.Cmd
-
-	// Detect OS and use appropriate command
+	
 	switch {
 	case fileExists("/usr/bin/traceroute"):
 		cmd = exec.Command("traceroute", "-m", strconv.Itoa(maxHops), "-n", "-q", "1", ip)
@@ -349,7 +498,6 @@ func tryICMPTraceroute(ip string, maxHops int) *TracerouteResult {
 	case fileExists("/bin/traceroute"):
 		cmd = exec.Command("traceroute", "-m", strconv.Itoa(maxHops), "-n", "-q", "1", ip)
 	default:
-		// Try without full path
 		cmd = exec.Command("traceroute", "-m", strconv.Itoa(maxHops), "-n", "-q", "1", ip)
 	}

@@ -363,12 +511,10 @@ func tryICMPTraceroute(ip string, maxHops int) *TracerouteResult {

 func tryTCPTraceroute(ip string, port int, maxHops int) *TracerouteResult {
 	var cmd *exec.Cmd
-
-	// Try tcptraceroute if available
+	
 	if fileExists("/usr/bin/tcptraceroute") || fileExists("/usr/sbin/tcptraceroute") {
 		cmd = exec.Command("tcptraceroute", "-m", strconv.Itoa(maxHops), "-n", "-q", "1", ip, strconv.Itoa(port))
 	} else {
-		// Try traceroute with TCP (-T flag on Linux)
 		cmd = exec.Command("traceroute", "-T", "-p", strconv.Itoa(port), "-m", strconv.Itoa(maxHops), "-n", "-q", "1", ip)
 	}

@@ -388,10 +534,8 @@ func parseTracerouteOutput(output string, method string) *TracerouteResult {
 	}

 	lines := strings.Split(output, "\n")
-
-	// Regex to match: " 1  192.168.1.1  1.234 ms"
+	
 	hopRegex := regexp.MustCompile(`^\s*(\d+)\s+([0-9.]+)\s+([0-9.]+)\s*ms`)
-	// Regex to match timeouts: " 1  * * *"
 	timeoutRegex := regexp.MustCompile(`^\s*(\d+)\s+\*`)

 	for _, line := range lines {
@@ -425,4 +569,4 @@ func parseTracerouteOutput(output string, method string) *TracerouteResult {
 func fileExists(path string) bool {
 	_, err := os.Stat(path)
 	return err == nil
-}
+}
--- a/ping_service.service
+++ b/ping_service.service
@@ -0,0 +1,28 @@
+[Unit]
+Description=Network Ping and Traceroute Service
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+User=pingservice
+Group=pingservice
+WorkingDirectory=/opt/ping-service
+ExecStart=/opt/ping-service/ping_service -config /opt/ping-service/config.yaml -v
+Restart=always
+RestartSec=10
+
+# Security hardening
+NoNewPrivileges=true
+PrivateTmp=true
+ProtectSystem=strict
+ProtectHome=true
+ReadWritePaths=/opt/ping-service
+
+# Logging
+StandardOutput=journal
+StandardError=journal
+SyslogIdentifier=ping-service
+
+[Install]
+WantedBy=multi-user.target