示例#1
0
文件: agent.go 项目: Wikia/telegraf
// gatherWithTimeout gathers from the given input, with the given timeout.
//   when the given timeout is reached, gatherWithTimeout logs an error message
//   but continues waiting for it to return. This is to avoid leaving behind
//   hung processes, and to prevent re-calling the same hung process over and
//   over.
func gatherWithTimeout(
	shutdown chan struct{},
	input *models.RunningInput,
	acc *accumulator,
	timeout time.Duration,
) {
	ticker := time.NewTicker(timeout)
	defer ticker.Stop()
	done := make(chan error)
	go func() {
		done <- input.Input.Gather(acc)
	}()

	for {
		select {
		case err := <-done:
			if err != nil {
				log.Printf("E! ERROR in input [%s]: %s", input.Name(), err)
			}
			return
		case <-ticker.C:
			log.Printf("E! ERROR: input [%s] took longer to collect than "+
				"collection interval (%s)",
				input.Name(), timeout)
			continue
		case <-shutdown:
			return
		}
	}
}
示例#2
0
文件: agent.go 项目: Wikia/telegraf
func panicRecover(input *models.RunningInput) {
	if err := recover(); err != nil {
		trace := make([]byte, 2048)
		runtime.Stack(trace, true)
		log.Printf("E! FATAL: Input [%s] panicked: %s, Stack:\n%s\n",
			input.Name(), err, trace)
		log.Println("E! PLEASE REPORT THIS PANIC ON GITHUB with " +
			"stack trace, configuration, and OS information: " +
			"https://github.com/influxdata/telegraf/issues/new")
	}
}
示例#3
0
文件: agent.go 项目: Wikia/telegraf
// gatherer runs the inputs that have been configured with their own
// reporting interval.
func (a *Agent) gatherer(
	shutdown chan struct{},
	input *models.RunningInput,
	interval time.Duration,
	metricC chan telegraf.Metric,
) {
	defer panicRecover(input)

	ticker := time.NewTicker(interval)
	defer ticker.Stop()

	for {
		acc := NewAccumulator(input, metricC)
		acc.SetPrecision(a.Config.Agent.Precision.Duration,
			a.Config.Agent.Interval.Duration)
		input.SetDebug(a.Config.Agent.Debug)
		input.SetDefaultTags(a.Config.Tags)

		internal.RandomSleep(a.Config.Agent.CollectionJitter.Duration, shutdown)

		start := time.Now()
		gatherWithTimeout(shutdown, input, acc, interval)
		elapsed := time.Since(start)

		log.Printf("D! Input [%s] gathered metrics, (%s interval) in %s\n",
			input.Name(), interval, elapsed)

		select {
		case <-shutdown:
			return
		case <-ticker.C:
			continue
		}
	}
}