Add orphan GC sweeper and Prometheus metrics with explicit registration
Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -62,6 +62,14 @@ type probeJob struct {
|
||||
interval time.Duration
|
||||
}
|
||||
|
||||
// ProbeMetrics receives every probe result and the retirement of a
|
||||
// proxy's series. Implemented by internal/metrics; defined here so this
|
||||
// package carries no metrics dependency.
|
||||
type ProbeMetrics interface {
|
||||
ObserveProbe(proxy string, latency time.Duration, success bool)
|
||||
ForgetProxy(proxy string)
|
||||
}
|
||||
|
||||
// Engine runs the probe scheduler and worker pool as a manager Runnable. It
|
||||
// never writes Proxy status itself — keeping the reconciler the single
|
||||
// status writer — and instead emits a GenericEvent per status-affecting
|
||||
@@ -87,6 +95,10 @@ type Engine struct {
|
||||
// ProbeTLSConfig overrides TLS verification for https probe URLs; nil
|
||||
// means system roots. Needed for private CAs (and tests).
|
||||
ProbeTLSConfig *tls.Config
|
||||
// Metrics, when non-nil, is fed on every probe — the status writes are
|
||||
// transition-only by design, so metrics are where high-frequency
|
||||
// signal (true probe recency, every latency sample) lives.
|
||||
Metrics ProbeMetrics
|
||||
|
||||
probeFn func(context.Context, *url.URL, crawlv1alpha1.HealthCheckSpec, *tls.Config) probeResult
|
||||
|
||||
@@ -220,6 +232,11 @@ func (e *Engine) tick(ctx context.Context, now time.Time, jobs chan<- probeJob)
|
||||
for key := range e.states {
|
||||
if _, ok := probeable[key]; !ok {
|
||||
delete(e.states, key)
|
||||
if e.Metrics != nil {
|
||||
// Retire the per-proxy series with the state, or series
|
||||
// for deleted proxies leak forever.
|
||||
e.Metrics.ForgetProxy(key.String())
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -252,6 +269,10 @@ func newState(p *crawlv1alpha1.Proxy, now time.Time, interval time.Duration) *st
|
||||
// threshold-crossing flip, or a material latency change (beyond
|
||||
// max(LatencyFloor, 50% of reported) and rate-limited by MinReportInterval).
|
||||
func (e *Engine) record(job probeJob, res probeResult, now time.Time) {
|
||||
if e.Metrics != nil {
|
||||
e.Metrics.ObserveProbe(job.key.String(), res.latency, res.ok)
|
||||
}
|
||||
|
||||
e.mu.Lock()
|
||||
defer e.mu.Unlock()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user