Expose delivery metrics on /metrics (closes #209)
All checks were successful
check / check (push) Successful in 4m13s

/metrics carried only the inbound HTTP surface, so a destination
failing for an hour, a growing retry backlog and a stuck-open circuit
breaker were all invisible: the receive side stays healthy in each
case because it is.

New internal/metrics registers, on the existing default registry that
the go-http-metrics recorder and the promhttp handler already share:

- webhooker_events_received_total
- webhooker_delivery_attempts_total
- webhooker_deliveries_succeeded_total
- webhooker_deliveries_failed_total
- webhooker_delivery_retries_total
- webhooker_delivery_duration_seconds
- webhooker_deliveries_pending / _retrying
- webhooker_circuit_breakers_open

The route mounting is untouched.

Every delivery metric carries one label, target_type, whose domain is
the four target-type constants; anything outside it collapses to
"unknown" so no series can be minted from a UUID. Target ids, event
ids and entrypoint ids are deliberately not labels.

Instrumentation sits at the points every target type already passes
through: processDelivery for the attempt counter and the duration
histogram, updateDeliveryStatus for the outcome counters. The
queue-depth gauges are counted out of the per-webhook databases by a
30s sampler rather than tracked as deltas, which would need seeding at
startup and would drift on any transition that failed to persist. The
open-breaker gauge is recounted from the target's breaker registry on
every state change.
This commit is contained in:
2026-08-20 04:19:12 +00:00
parent 10c8dd2331
commit b8c8b75e04
11 changed files with 1219 additions and 2 deletions

301
internal/metrics/metrics.go Normal file
View File

@@ -0,0 +1,301 @@
// Package metrics defines the Prometheus collectors describing
// webhooker's delivery pipeline: how many events arrive, how many
// deliveries are attempted, how they end, how long they take, how
// deep the queues are, and how many circuit breakers are open.
//
// The inbound HTTP metrics come from the go-http-metrics recorder in
// internal/middleware and land on prometheus.DefaultRegisterer. These
// collectors register there too, so both surfaces are gathered by the
// one promhttp handler mounted on the authenticated /metrics route.
package metrics
import (
"sync"
"time"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promauto"
"sneak.berlin/go/webhooker/internal/database"
)
// namespace prefixes every collector defined here.
const namespace = "webhooker"
// targetTypeLabel is the only label any delivery metric carries, and
// cardinality is the whole reason for that.
//
// A target type is one of four compile-time constants, so the label
// domain is bounded by construction. Target ids, event ids and
// entrypoint ids are not: they are UUIDs minted per operator action
// or per inbound request, a series is never reclaimed once it exists,
// and labelling by any of them makes /metrics a memory leak that
// grows with traffic. normalizeTargetType enforces the bound at every
// call site — a type the registry does not know collapses into
// unknownTargetType rather than minting a series of its own.
const targetTypeLabel = "target_type"
// unknownTargetType is the bucket for a target type outside the known
// set, so an unrecognised value cannot mint a new series.
const unknownTargetType = "unknown"
// Delivery duration buckets, exponential from 5ms so the last bucket
// (about 98s) sits above the 30s outbound HTTP client timeout.
const (
durationBucketStart = 0.005
durationBucketFactor = 3
durationBucketCount = 10
)
// knownTargetTypes is the fixed label domain: the target types the
// delivery engine implements.
//
//nolint:gochecknoglobals // the label domain, built once per process
var knownTargetTypes = []database.TargetType{
database.TargetTypeHTTP,
database.TargetTypeDatabase,
database.TargetTypeLog,
database.TargetTypeSlack,
}
// defaultSet is the process-wide metric set, registered on the same
// registry the HTTP middleware and the /metrics handler already use.
// It is built on first use rather than in an init so that a test
// binary that never touches metrics never registers them.
//
//nolint:gochecknoglobals // one process-wide registration, by design
var defaultSet = sync.OnceValue(func() *Set {
return New(prometheus.DefaultRegisterer)
})
// Default returns the process-wide metric set.
func Default() *Set {
return defaultSet()
}
// Set is one registered group of webhooker's delivery collectors.
// Production uses the single Default set; tests build their own
// against a private registry so assertions are not disturbed by
// deliveries other tests are making concurrently.
type Set struct {
eventsReceived prometheus.Counter
deliveryAttempts *prometheus.CounterVec
deliveriesSucceeded *prometheus.CounterVec
deliveriesFailed *prometheus.CounterVec
deliveryRetries *prometheus.CounterVec
deliveryDuration *prometheus.HistogramVec
deliveriesPending *prometheus.GaugeVec
deliveriesRetrying *prometheus.GaugeVec
circuitBreakersOpen *prometheus.GaugeVec
}
// New registers a full set of delivery collectors on reg and returns
// it. It panics if reg already holds them, which is the intended
// behaviour for a duplicate registration.
func New(reg prometheus.Registerer) *Set {
factory := promauto.With(reg)
s := &Set{
eventsReceived: factory.NewCounter(
prometheus.CounterOpts{
Namespace: namespace,
Name: "events_received_total",
Help: "Webhook events received and " +
"stored, so the receive and deliver " +
"sides can be compared.",
},
),
deliveryDuration: factory.NewHistogramVec(
prometheus.HistogramOpts{
Namespace: namespace,
Name: "delivery_duration_seconds",
Help: "Wall time of a single delivery " +
"attempt, by target type.",
Buckets: prometheus.ExponentialBuckets(
durationBucketStart,
durationBucketFactor,
durationBucketCount,
),
},
[]string{targetTypeLabel},
),
}
s.registerCounters(factory)
s.registerGauges(factory)
s.initSeries()
return s
}
// EventReceived counts one inbound webhook event stored.
func (s *Set) EventReceived() {
s.eventsReceived.Inc()
}
// DeliveryAttempted counts one delivery attempt dispatched to a
// target.
func (s *Set) DeliveryAttempted(t database.TargetType) {
s.deliveryAttempts.
WithLabelValues(normalizeTargetType(t)).
Inc()
}
// ObserveDeliveryDuration records how long one delivery attempt took.
func (s *Set) ObserveDeliveryDuration(
t database.TargetType, d time.Duration,
) {
s.deliveryDuration.
WithLabelValues(normalizeTargetType(t)).
Observe(d.Seconds())
}
// DeliveryStatusChanged counts a delivery's transition into a new
// status. The mapping from status to counter lives here, next to the
// collectors, so the engine has a single call for every transition it
// persists. A move back to pending is not an outcome and counts
// nothing.
func (s *Set) DeliveryStatusChanged(
t database.TargetType, status database.DeliveryStatus,
) {
label := normalizeTargetType(t)
switch status {
case database.DeliveryStatusDelivered:
s.deliveriesSucceeded.WithLabelValues(label).Inc()
case database.DeliveryStatusFailed:
s.deliveriesFailed.WithLabelValues(label).Inc()
case database.DeliveryStatusRetrying:
s.deliveryRetries.WithLabelValues(label).Inc()
case database.DeliveryStatusPending:
}
}
// SetQueueDepths publishes the pending and retrying queue depths from
// one sample. Every known target type is written on every call, so a
// type whose queue has drained reads zero instead of holding its last
// value forever.
func (s *Set) SetQueueDepths(
pending, retrying map[database.TargetType]int,
) {
for _, t := range knownTargetTypes {
label := string(t)
s.deliveriesPending.WithLabelValues(label).
Set(float64(pending[t]))
s.deliveriesRetrying.WithLabelValues(label).
Set(float64(retrying[t]))
}
}
// SetCircuitBreakersOpen publishes how many of a target type's
// circuit breakers are currently open.
func (s *Set) SetCircuitBreakersOpen(
t database.TargetType, open int,
) {
s.circuitBreakersOpen.
WithLabelValues(normalizeTargetType(t)).
Set(float64(open))
}
func (s *Set) registerCounters(factory promauto.Factory) {
s.deliveryAttempts = factory.NewCounterVec(
prometheus.CounterOpts{
Namespace: namespace,
Name: "delivery_attempts_total",
Help: "Delivery attempts dispatched to a " +
"target, by target type.",
},
[]string{targetTypeLabel},
)
s.deliveriesSucceeded = factory.NewCounterVec(
prometheus.CounterOpts{
Namespace: namespace,
Name: "deliveries_succeeded_total",
Help: "Deliveries that reached the delivered " +
"state, by target type.",
},
[]string{targetTypeLabel},
)
s.deliveriesFailed = factory.NewCounterVec(
prometheus.CounterOpts{
Namespace: namespace,
Name: "deliveries_failed_total",
Help: "Deliveries that failed terminally and " +
"will not be retried, by target type.",
},
[]string{targetTypeLabel},
)
s.deliveryRetries = factory.NewCounterVec(
prometheus.CounterOpts{
Namespace: namespace,
Name: "delivery_retries_total",
Help: "Deliveries put back into the retrying " +
"state, by target type.",
},
[]string{targetTypeLabel},
)
}
func (s *Set) registerGauges(factory promauto.Factory) {
s.deliveriesPending = factory.NewGaugeVec(
prometheus.GaugeOpts{
Namespace: namespace,
Name: "deliveries_pending",
Help: "Deliveries currently in the pending " +
"state, by target type.",
},
[]string{targetTypeLabel},
)
s.deliveriesRetrying = factory.NewGaugeVec(
prometheus.GaugeOpts{
Namespace: namespace,
Name: "deliveries_retrying",
Help: "Deliveries currently in the retrying " +
"state, by target type.",
},
[]string{targetTypeLabel},
)
s.circuitBreakersOpen = factory.NewGaugeVec(
prometheus.GaugeOpts{
Namespace: namespace,
Name: "circuit_breakers_open",
Help: "Delivery circuit breakers currently " +
"open, by target type.",
},
[]string{targetTypeLabel},
)
}
// initSeries materialises every known-target-type series at zero, so
// a dashboard and an alert rule see a target type that has not
// delivered yet rather than a missing series.
func (s *Set) initSeries() {
for _, t := range knownTargetTypes {
label := string(t)
s.deliveryAttempts.WithLabelValues(label)
s.deliveriesSucceeded.WithLabelValues(label)
s.deliveriesFailed.WithLabelValues(label)
s.deliveryRetries.WithLabelValues(label)
s.deliveriesPending.WithLabelValues(label)
s.deliveriesRetrying.WithLabelValues(label)
s.circuitBreakersOpen.WithLabelValues(label)
}
}
// normalizeTargetType maps a target type onto the bounded label
// domain, collapsing anything outside it to unknownTargetType.
func normalizeTargetType(t database.TargetType) string {
for _, known := range knownTargetTypes {
if t == known {
return string(known)
}
}
return unknownTargetType
}