Add health check and self reporting of health

This avoids panicing and instead provides an HTTP endpoint to report health

go.mod

@@ -4,7 +4,7 @@ go 1.20
 
 require (
 	git.iamthefij.com/iamthefij/slog v1.3.0
-	github.com/prometheus/client_golang v1.19.0
+	github.com/prometheus/client_golang v1.15.0
 	gopkg.in/yaml.v2 v2.4.0
 )
 
@@ -14,10 +14,10 @@ require (
 	github.com/golang/protobuf v1.5.3 // indirect
 	github.com/kr/text v0.2.0 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
-	github.com/prometheus/client_model v0.5.0 // indirect
+	github.com/prometheus/client_model v0.3.0 // indirect
-	github.com/prometheus/common v0.48.0 // indirect
+	github.com/prometheus/common v0.42.0 // indirect
-	github.com/prometheus/procfs v0.12.0 // indirect
+	github.com/prometheus/procfs v0.9.0 // indirect
 	github.com/rogpeppe/go-internal v1.10.0 // indirect
-	golang.org/x/sys v0.16.0 // indirect
+	golang.org/x/sys v0.6.0 // indirect
-	google.golang.org/protobuf v1.33.0 // indirect
+	google.golang.org/protobuf v1.30.0 // indirect
 )

go.sum

@@ -182,16 +182,12 @@ github.com/prometheus/client_golang v1.12.1/go.mod h1:3Z9XVyYiZYEO+YQWt3RD2R3jrb
 github.com/prometheus/client_golang v1.14.0/go.mod h1:8vpkKitgIVNcqrRBWh1C4TIUQgYNtG/XQE4E/Zae36Y=
 github.com/prometheus/client_golang v1.15.0 h1:5fCgGYogn0hFdhyhLbw7hEsWxufKtY9klyvdNfFlFhM=
 github.com/prometheus/client_golang v1.15.0/go.mod h1:e9yaBhRPU2pPNsZwE+JdQl0KEt1N9XgF6zxWmaC0xOk=
-github.com/prometheus/client_golang v1.19.0 h1:ygXvpU1AoN1MhdzckN+PyD9QJOSD4x7kmXYlnfbA6JU=
-github.com/prometheus/client_golang v1.19.0/go.mod h1:ZRM9uEAypZakd+q/x7+gmsvXdURP+DABIEIjnmDdp+k=
 github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
 github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/prometheus/client_model v0.2.0/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
 github.com/prometheus/client_model v0.3.0 h1:UBgGFHqYdG/TPFD1B1ogZywDqEkwp3fBMvqdiQ7Xew4=
 github.com/prometheus/client_model v0.3.0/go.mod h1:LDGWKZIo7rky3hgvBe+caln+Dr3dPggB5dvjtD7w9+w=
-github.com/prometheus/client_model v0.5.0 h1:VQw1hfvPvk3Uv6Qf29VrPF32JB6rtbgI6cYPYQjL0Qw=
-github.com/prometheus/client_model v0.5.0/go.mod h1:dTiFglRmd66nLR9Pv9f0mZi7B7fk5Pm3gvsjB5tr+kI=
 github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y86RQel1bk4=
 github.com/prometheus/common v0.10.0/go.mod h1:Tlit/dnDKsSWFlCLTWaA1cyBgKHSMdTB80sz/V91rCo=
 github.com/prometheus/common v0.26.0/go.mod h1:M7rCNAaPfAosfx8veZJCuw84e35h3Cfd9VFqTh1DIvc=
@@ -199,8 +195,6 @@ github.com/prometheus/common v0.32.1/go.mod h1:vu+V0TpY+O6vW9J44gczi3Ap/oXXR10b+
 github.com/prometheus/common v0.37.0/go.mod h1:phzohg0JFMnBEFGxTDbfu3QyL5GI8gTQJFhYO5B3mfA=
 github.com/prometheus/common v0.42.0 h1:EKsfXEYo4JpWMHH5cg+KOUWeuJSov1Id8zGR8eeI1YM=
 github.com/prometheus/common v0.42.0/go.mod h1:xBwqVerjNdUDjgODMpudtOMwlOwf2SaTr1yjz4b7Zbc=
-github.com/prometheus/common v0.48.0 h1:QO8U2CdOzSn1BBsmXJXduaaW+dY/5QLjfB8svtSzKKE=
-github.com/prometheus/common v0.48.0/go.mod h1:0/KsvlIEfPQCQ5I2iNSAWKPZziNCvRs5EC6ILDTlAPc=
 github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
 github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
 github.com/prometheus/procfs v0.1.3/go.mod h1:lV6e/gmhEcM9IjHGsFOCxxuZ+z1YqCvr4OA4YeYWdaU=
@@ -209,8 +203,6 @@ github.com/prometheus/procfs v0.7.3/go.mod h1:cz+aTbrPOrUb4q7XlbU9ygM+/jj0fzG6c1
 github.com/prometheus/procfs v0.8.0/go.mod h1:z7EfXMXOkbkqb9IINtpCn86r/to3BnA0uaxHdg830/4=
 github.com/prometheus/procfs v0.9.0 h1:wzCHvIvM5SxWqYvwgVL7yJY8Lz3PKn49KQtpgMYJfhI=
 github.com/prometheus/procfs v0.9.0/go.mod h1:+pB4zwohETzFnmlpe6yd2lSc+0/46IYZRB/chUwxUZY=
-github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
-github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
 github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
 github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
 github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
@@ -373,8 +365,6 @@ golang.org/x/sys v0.3.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0 h1:MVltZSvRTcU2ljQOhs94SXPftV6DCNnZViHeQps87pQ=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.16.0 h1:xWw16ngr6ZMtmxDyKyIgsE93KNKz5HKmMa3b8ALHidU=
-golang.org/x/sys v0.16.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
@@ -514,10 +504,6 @@ google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqw
 google.golang.org/protobuf v1.28.1/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 google.golang.org/protobuf v1.30.0 h1:kPPoIgf3TsEvrm0PFe15JQ+570QVxYzEvvHqChK+cng=
 google.golang.org/protobuf v1.30.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
-google.golang.org/protobuf v1.32.0 h1:pPC6BG5ex8PDFnkbrGU3EixyhKcQ2aDuBS36lqK/C7I=
-google.golang.org/protobuf v1.32.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
-google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI=
-google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
 gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=

health.go

@@ -0,0 +1,72 @@
+package main
+
+import (
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+)
+
+type HealthCheckHandler struct {
+	isMinitorHealthy bool
+	monitors         []*Monitor
+}
+
+func NewHealthCheckHandler(monitors []*Monitor) *HealthCheckHandler {
+	return &HealthCheckHandler{
+		false,
+		monitors,
+	}
+}
+
+func (hch *HealthCheckHandler) MinitorHealthy(healthy bool) {
+	hch.isMinitorHealthy = healthy
+}
+
+func (hch HealthCheckHandler) MinitorHealthCheck() (bool, string) {
+	if hch.isMinitorHealthy {
+		return true, "OK"
+	} else {
+		return false, "UNHEALTHY"
+	}
+}
+
+func (hch HealthCheckHandler) MonitorsHealthCheck() (bool, string) {
+	downMonitors := []string{}
+
+	for _, monitor := range hch.monitors {
+		if !monitor.IsUp() {
+			downMonitors = append(downMonitors, monitor.Name)
+		}
+	}
+
+	if len(downMonitors) == 0 {
+		return true, "OK"
+	} else {
+		return false, fmt.Sprintf("UNHEALTHY: The following monitors are unhealthy: %s", strings.Join(downMonitors, ", "))
+	}
+}
+
+func (hch HealthCheckHandler) ServeHTTP(w http.ResponseWriter, r *http.Request) {
+	var healthy bool
+
+	var body string
+
+	if monitors := r.URL.Query().Get("monitors"); monitors != "" {
+		healthy, body = hch.MonitorsHealthCheck()
+	} else {
+		healthy, body = hch.MinitorHealthCheck()
+	}
+
+	if healthy {
+		w.WriteHeader(http.StatusOK)
+	} else {
+		w.WriteHeader(http.StatusServiceUnavailable)
+	}
+
+	_, _ = io.WriteString(w, body)
+}
+
+func HandleHealthCheck() {
+	http.Handle("/metrics", HealthChecks)
+}

health_test.go

@@ -0,0 +1,79 @@
+package main
+
+import (
+	"testing"
+)
+
+func TestNewHealthCheck(t *testing.T) {
+	monitors := []*Monitor{
+		{Name: "Test Monitor"},
+	}
+	hc := NewHealthCheckHandler(monitors)
+
+	monitors[0].alertCount++
+
+	if healthy, _ := hc.MinitorHealthCheck(); healthy {
+		t.Errorf("Initial hc state should be unhealthy until some successful alert is sent")
+	}
+
+	if healthy, _ := hc.MonitorsHealthCheck(); healthy {
+		t.Errorf("Faking an alert on the monitor pointer should make this unhealthy")
+	}
+}
+
+func TestMinitorHealthCheck(t *testing.T) {
+	monitors := []*Monitor{
+		{Name: "Test Monitor"},
+	}
+	hc := NewHealthCheckHandler(monitors)
+
+	t.Run("MinitorHealthCheck(healthy)", func(t *testing.T) {
+		hc.MinitorHealthy(true)
+		healthy, body := hc.MinitorHealthCheck()
+		if !healthy {
+			t.Errorf("Expected healthy check")
+		}
+		if body != "OK" {
+			t.Errorf("Expected OK response")
+		}
+	})
+
+	t.Run("MinitorHealthCheck(unhealthy)", func(t *testing.T) {
+		hc.MinitorHealthy(false)
+		healthy, body := hc.MinitorHealthCheck()
+		if healthy {
+			t.Errorf("Expected healthy check")
+		}
+		if body != "UNHEALTHY" {
+			t.Errorf("Expected UNHEALTHY response")
+		}
+	})
+}
+
+func TestMonitorsHealthCheck(t *testing.T) {
+	monitors := []*Monitor{
+		{Name: "Test Monitor"},
+	}
+	hc := NewHealthCheckHandler(monitors)
+
+	t.Run("MonitorsHealthCheck(healthy)", func(t *testing.T) {
+		healthy, body := hc.MonitorsHealthCheck()
+		if !healthy {
+			t.Errorf("Expected healthy check")
+		}
+		if body != "OK" {
+			t.Errorf("Expected OK response")
+		}
+	})
+
+	t.Run("MonitorsHealthCheck(unhealthy)", func(t *testing.T) {
+		monitors[0].alertCount++
+		healthy, body := hc.MonitorsHealthCheck()
+		if healthy {
+			t.Errorf("Expected healthy check")
+		}
+		if body != "UNHEALTHY: The following monitors are unhealthy: Test Monitor" {
+			t.Errorf("Expected UNHEALTHY response")
+		}
+	})
+}

main.go

@@ -4,6 +4,7 @@ import (
 	"errors"
 	"flag"
 	"fmt"
+	"net/http"
 	"time"
 
 	"git.iamthefij.com/iamthefij/slog"
@@ -16,6 +17,10 @@ var (
 	MetricsPort = 8080
 	// Metrics contains all active metrics
 	Metrics = NewMetrics()
+	// Self monitor rather than panicing
+	SelfMonitor = false
+	// HealthChecks contains health check values
+	HealthChecks *HealthCheckHandler = nil
 
 	// PyCompat enables support for legacy Python templates
 	PyCompat = false
@@ -51,7 +56,13 @@ func sendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) erro
 					output,
 				)
 
+				if SelfMonitor {
+					Metrics.SetMonitorStatus(fmt.Sprintf("Alert %s", alertName), false)
+				}
+
 				return err
+			} else {
+				Metrics.SetMonitorStatus(fmt.Sprintf("Alert %s", alertName), true)
 			}
 
 			// Count alert metrics
@@ -69,6 +80,8 @@ func sendAlerts(config *Config, monitor *Monitor, alertNotice *AlertNotice) erro
 
 func checkMonitors(config *Config) error {
 	// TODO: Run this in goroutines and capture exceptions
+	healthy := true
+
 	for _, monitor := range config.Monitors {
 		if monitor.ShouldCheck() {
 			success, alertNotice := monitor.Check()
@@ -80,17 +93,32 @@ func checkMonitors(config *Config) error {
 
 			if alertNotice != nil {
 				err := sendAlerts(config, monitor, alertNotice)
-				// If there was an error in sending an alert, exit early and bubble it up
+				// If there was an error in sending an alert, mark as unhealthy or bubble up
 				if err != nil {
+					if SelfMonitor {
+						healthy = false
+					} else {
 						return err
 					}
 				}
 			}
 		}
+	}
+
+	if HealthChecks != nil {
+		HealthChecks.MinitorHealthy(healthy)
+	}
 
 	return nil
 }
 
+// ServeMetricsAndHealth starts the default http server
+func ServeMetricsAndHealth() {
+	host := fmt.Sprintf(":%d", MetricsPort)
+
+	_ = http.ListenAndServe(host, nil)
+}
+
 func main() {
 	showVersion := flag.Bool("version", false, "Display the version of minitor and exit")
 	configPath := flag.String("config", "config.yml", "Alternate configuration path (default: config.yml)")
@@ -98,7 +126,9 @@ func main() {
 	flag.BoolVar(&slog.DebugLevel, "debug", false, "Enables debug logs (default: false)")
 	flag.BoolVar(&ExportMetrics, "metrics", false, "Enables prometheus metrics exporting (default: false)")
 	flag.BoolVar(&PyCompat, "py-compat", false, "Enables support for legacy Python Minitor config. Will eventually be removed. (default: false)")
-	flag.IntVar(&MetricsPort, "metrics-port", MetricsPort, "The port that Prometheus metrics should be exported on, if enabled. (default: 8080)")
+	flag.IntVar(&MetricsPort, "metrics-port", MetricsPort, "The port that Prometheus metrics and healthchecks should be exported on, if enabled. (default: 8080)")
+	flag.BoolVar(&SelfMonitor, "self-monitor", false, "Enables self-monitoring. Export metrics rather than panic when alerts fail. (default: false)")
+
 	flag.Parse()
 
 	// Print version if flag is provided
@@ -115,8 +145,19 @@ func main() {
 	// Serve metrics exporter, if specified
 	if ExportMetrics {
 		slog.Infof("Exporting metrics to Prometheus on port %d", MetricsPort)
+		HandleMetrics()
+	}
 
-		go ServeMetrics()
+	if SelfMonitor {
+		slog.Infof("Starting healthcheck endpoint on port %d", MetricsPort)
+
+		HealthChecks = NewHealthCheckHandler(config.Monitors)
+
+		HandleHealthCheck()
+	}
+
+	if ExportMetrics || SelfMonitor {
+		go ServeMetricsAndHealth()
 	}
 
 	// Start main loop

main_test.go

@@ -7,6 +7,7 @@ func TestCheckMonitors(t *testing.T) {
 		config      Config
 		expectErr   bool
 		name        string
+		selfMonitor bool
 	}{
 		{
 			config:    Config{},
@@ -24,6 +25,7 @@ func TestCheckMonitors(t *testing.T) {
 			},
 			expectErr:   false,
 			name:        "Monitor success, no alerts",
+			selfMonitor: false,
 		},
 		{
 			config: Config{
@@ -37,6 +39,7 @@ func TestCheckMonitors(t *testing.T) {
 			},
 			expectErr:   false,
 			name:        "Monitor failure, no alerts",
+			selfMonitor: false,
 		},
 		{
 			config: Config{
@@ -50,6 +53,7 @@ func TestCheckMonitors(t *testing.T) {
 			},
 			expectErr:   false,
 			name:        "Monitor recovery, no alerts",
+			selfMonitor: false,
 		},
 		{
 			config: Config{
@@ -64,6 +68,7 @@ func TestCheckMonitors(t *testing.T) {
 			},
 			expectErr:   true,
 			name:        "Monitor failure, unknown alerts",
+			selfMonitor: false,
 		},
 		{
 			config: Config{
@@ -78,6 +83,22 @@ func TestCheckMonitors(t *testing.T) {
 			},
 			expectErr:   true,
 			name:        "Monitor recovery, unknown alerts",
+			selfMonitor: false,
+		},
+		{
+			config: Config{
+				Monitors: []*Monitor{
+					{
+						Name:       "Success",
+						Command:    CommandOrShell{Command: []string{"true"}},
+						AlertUp:    []string{"unknown"},
+						alertCount: 1,
+					},
+				},
+			},
+			expectErr:   false,
+			name:        "Monitor recovery, unknown alerts, with Health Check",
+			selfMonitor: true,
 		},
 		{
 			config: Config{
@@ -97,6 +118,7 @@ func TestCheckMonitors(t *testing.T) {
 			},
 			expectErr:   false,
 			name:        "Monitor failure, successful alert",
+			selfMonitor: false,
 		},
 		{
 			config: Config{
@@ -117,10 +139,34 @@ func TestCheckMonitors(t *testing.T) {
 			},
 			expectErr:   true,
 			name:        "Monitor failure, bad alert",
+			selfMonitor: false,
+		},
+		{
+			config: Config{
+				Monitors: []*Monitor{
+					{
+						Name:       "Failure",
+						Command:    CommandOrShell{Command: []string{"false"}},
+						AlertDown:  []string{"bad"},
+						AlertAfter: 1,
+					},
+				},
+				Alerts: map[string]*Alert{
+					"bad": {
+						Name:    "bad",
+						Command: CommandOrShell{Command: []string{"false"}},
+					},
+				},
+			},
+			expectErr:   false,
+			name:        "Monitor failure, bad alert, with Health Check",
+			selfMonitor: true,
 		},
 	}
 
 	for _, c := range cases {
+		SelfMonitor = c.selfMonitor
+
 		err := c.config.Init()
 		if err != nil {
 			t.Errorf("checkMonitors(%s): unexpected error reading config: %v", c.name, err)

metrics.go

@@ -1,7 +1,6 @@
 package main
 
 import (
-	"fmt"
 	"net/http"
 
 	"github.com/prometheus/client_golang/prometheus"
@@ -107,11 +106,7 @@ func (metrics *MinitorMetrics) CountAlert(monitor string, alert string) {
 	).Inc()
 }
 
-// ServeMetrics starts an http server with a Prometheus metrics handler
+// HandleMetrics add Prometheus metrics handler to default http server
-func ServeMetrics() {
+func HandleMetrics() {
 	http.Handle("/metrics", promhttp.Handler())
-
-	host := fmt.Sprintf(":%d", MetricsPort)
-
-	_ = http.ListenAndServe(host, nil)
 }