minitor-go/main.go

118 lines
3.0 KiB
Go
Raw Normal View History

2019-09-21 22:03:26 +00:00
package main
import (
"flag"
"fmt"
2019-10-02 16:37:29 +00:00
"log"
2019-09-21 22:03:26 +00:00
"time"
)
2019-10-04 23:17:20 +00:00
var (
// LogDebug will control whether debug messsages should be logged
LogDebug = false
// ExportMetrics will track whether or not we want to export metrics to prometheus
ExportMetrics = false
// MetricsPort is the port to expose metrics on
MetricsPort = 8080
// Metrics contains all active metrics
Metrics = NewMetrics()
2019-10-04 23:17:20 +00:00
// version of minitor being run
version = "dev"
)
2019-10-04 23:17:36 +00:00
func checkMonitors(config *Config) error {
for _, monitor := range config.Monitors {
if monitor.ShouldCheck() {
success, alertNotice := monitor.Check()
hasAlert := alertNotice != nil
// Track status metrics
Metrics.SetMonitorStatus(monitor.Name, success)
Metrics.CountCheck(monitor.Name, success, hasAlert)
// Should probably consider refactoring everything below here
if alertNotice != nil {
if LogDebug {
log.Printf("DEBUG: Recieved an alert notice from %s", alertNotice.MonitorName)
}
alertNames := monitor.GetAlertNames(alertNotice.IsUp)
if alertNames == nil {
// This should only happen for a recovery alert. AlertDown is validated not empty
log.Printf(
"WARNING: Recieved alert, but no alert mechanisms exist. MonitorName=%s IsUp=%t",
alertNotice.MonitorName, alertNotice.IsUp,
)
}
for _, alertName := range alertNames {
if alert, ok := config.Alerts[alertName]; ok {
output, err := alert.Send(*alertNotice)
if err != nil {
log.Printf(
"ERROR: Alert '%s' failed. result=%v: output=%s",
alert.Name,
err,
output,
)
2019-10-04 23:17:36 +00:00
return fmt.Errorf(
"Unsuccessfully triggered alert '%s'. "+
"Crashing to avoid false negatives: %v",
alert.Name,
err,
2019-10-04 23:17:36 +00:00
)
}
// Count alert metrics
Metrics.CountAlert(monitor.Name, alert.Name)
} else {
// This case should never actually happen since we validate against it
log.Printf("ERROR: Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
return fmt.Errorf("Unknown alert for monitor %s: %s", alertNotice.MonitorName, alertName)
}
}
}
}
}
2019-10-04 23:17:36 +00:00
return nil
}
2019-09-21 22:03:26 +00:00
func main() {
// Get debug flag
flag.BoolVar(&LogDebug, "debug", false, "Enables debug logs (default: false)")
flag.BoolVar(&ExportMetrics, "metrics", false, "Enables prometheus metrics exporting (default: false)")
2019-10-04 23:17:20 +00:00
var showVersion = flag.Bool("version", false, "Display the version of minitor and exit")
flag.Parse()
2019-10-04 23:17:20 +00:00
// Print version if flag is provided
if *showVersion {
log.Println("Minitor version:", version)
2019-10-04 23:17:20 +00:00
return
}
// Load configuration
config, err := LoadConfig("config.yml")
if err != nil {
log.Fatalf("Error loading config: %v", err)
}
2019-09-21 22:03:26 +00:00
// Serve metrics exporter, if specified
if ExportMetrics {
log.Println("INFO: Exporting metrics to Prometheus")
go ServeMetrics()
}
// Start main loop
2019-09-21 22:03:26 +00:00
for {
2019-10-04 23:17:36 +00:00
err = checkMonitors(&config)
if err != nil {
panic(err)
}
2019-09-21 22:03:26 +00:00
sleepTime := time.Duration(config.CheckInterval) * time.Second
time.Sleep(sleepTime)
}
}