flyemoji
75642d90cf
Introduce internal/metrics exposing the four metric families spec §23 mandates at minimum: felis_servers_total (gauge by desired state), felis_start_duration_seconds (histogram with Minecraft cold-start buckets), felis_image_build_failures_total and felis_reaper_worlds_deleted_total (counters). Collectors are package-level vars so any subsystem records without an import cycle; Register wires them into a prometheus.Registerer and is idempotent. Wire registration into the operator against controller-runtime's global Registry, so /metrics on the manager's existing metrics endpoint carries the felis_* families. Instrument the reaper to increment felis_reaper_worlds_deleted_total in lockstep with Summary.WorldsReaped, at the one point a world's PVC has actually been deleted.
95 lines
2.9 KiB
Go
95 lines
2.9 KiB
Go
package metrics
|
|
|
|
import (
|
|
"strings"
|
|
"testing"
|
|
|
|
"github.com/prometheus/client_golang/prometheus"
|
|
"github.com/prometheus/client_golang/prometheus/testutil"
|
|
)
|
|
|
|
// wantNames is the exact set of metric names spec §23 mandates "at minimum".
|
|
// Pinning them here makes a rename a deliberate, test-visible act rather than a
|
|
// silent dashboard/alert break.
|
|
var wantNames = []string{
|
|
"felis_servers_total",
|
|
"felis_start_duration_seconds",
|
|
"felis_image_build_failures_total",
|
|
"felis_reaper_worlds_deleted_total",
|
|
}
|
|
|
|
func TestRegisterExposesNamedFelisMetrics(t *testing.T) {
|
|
reg := prometheus.NewRegistry()
|
|
if err := Register(reg); err != nil {
|
|
t.Fatalf("Register: %v", err)
|
|
}
|
|
|
|
// Record into each collector through its typed API so a Gather emits the
|
|
// family — this proves the exported vars are the ones actually registered,
|
|
// not shadow copies.
|
|
ServersTotal.WithLabelValues("Running").Set(3)
|
|
StartDurationSeconds.Observe(12.5)
|
|
ImageBuildFailuresTotal.Inc()
|
|
ReaperWorldsDeletedTotal.Add(2)
|
|
|
|
mfs, err := reg.Gather()
|
|
if err != nil {
|
|
t.Fatalf("Gather: %v", err)
|
|
}
|
|
got := map[string]bool{}
|
|
for _, mf := range mfs {
|
|
got[mf.GetName()] = true
|
|
}
|
|
for _, name := range wantNames {
|
|
if !got[name] {
|
|
t.Errorf("mandated metric %q not exposed by the registry", name)
|
|
}
|
|
}
|
|
// Nothing may leak out from under the felis_ namespace — a stray name would
|
|
// mean a collector was declared without the namespace prefix.
|
|
for name := range got {
|
|
if !strings.HasPrefix(name, "felis_") {
|
|
t.Errorf("metric %q is not under the felis_ namespace", name)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestRegisterIsIdempotent(t *testing.T) {
|
|
reg := prometheus.NewRegistry()
|
|
if err := Register(reg); err != nil {
|
|
t.Fatalf("first Register: %v", err)
|
|
}
|
|
// A second Register into the same registry must not error: setup that runs
|
|
// twice (manager restart, test re-entry) should be harmless, not fatal.
|
|
if err := Register(reg); err != nil {
|
|
t.Fatalf("second Register should be idempotent, got: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestCountersRecordExpectedValues(t *testing.T) {
|
|
// These collectors are package-level singletons. This test asserts on a
|
|
// gauge child labelled "Stopped" (no other test touches it) and a >=1 bound
|
|
// on the build-failure counter, so values stay stable regardless of test
|
|
// ordering or accumulation across the binary.
|
|
reg := prometheus.NewRegistry()
|
|
if err := Register(reg); err != nil {
|
|
t.Fatalf("Register: %v", err)
|
|
}
|
|
|
|
ImageBuildFailuresTotal.Inc()
|
|
if got := testutil.ToFloat64(ImageBuildFailuresTotal); got < 1 {
|
|
t.Errorf("image build failures = %v, want >= 1", got)
|
|
}
|
|
|
|
g := ServersTotal.WithLabelValues("Stopped")
|
|
g.Set(7)
|
|
if got := testutil.ToFloat64(g); got != 7 {
|
|
t.Errorf("servers_total{state=Stopped} = %v, want 7", got)
|
|
}
|
|
|
|
StartDurationSeconds.Observe(30)
|
|
if n := testutil.CollectAndCount(StartDurationSeconds); n != 1 {
|
|
t.Errorf("start_duration_seconds collected %d metrics, want 1 histogram", n)
|
|
}
|
|
}
|