Files
egress-proxies-operator/internal/metrics/metrics_test.go
T
kacerrandClaude Opus 5 9a3ee963a0 Wire the provider health monitor into the manager, with gauges
--provider-check-interval (1m; 0 = off, else at least 10s) and
--provider-check-timeout (15s) are validated before the providers config
loads. Checkers are collected from the unwrapped providers in config
order, so checks never count as provider requests. Three scrape-time
gauges per {provider,target} read the monitor's snapshot: up, check
duration and check timestamp. The e2e suite waits for the kubernetes
ProviderHealth to turn Ready and asserts its gauge in the scrape.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-11 20:23:55 +00:00

156 lines
5.3 KiB
Go

package metrics
import (
"strings"
"testing"
"time"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/testutil"
)
// register wires a fresh registry — the reason Register exists instead of
// init()-time self-registration.
func register(t *testing.T, m *Metrics, phases map[string]int, active int) *prometheus.Registry {
t.Helper()
reg := prometheus.NewRegistry()
err := m.Register(reg,
func() map[string]int { return phases },
func() int { return active },
)
if err != nil {
t.Fatalf("Register: %v", err)
}
return reg
}
func TestRegister_scrapeTimeCollectors(t *testing.T) {
t.Parallel()
m := New()
reg := register(t, m, map[string]int{"Ready": 3, "Provisioning": 1}, 7)
expected := `
# HELP proxy_operator_leases_active Currently active leases.
# TYPE proxy_operator_leases_active gauge
proxy_operator_leases_active 7
# HELP proxy_operator_proxies Proxy objects by phase.
# TYPE proxy_operator_proxies gauge
proxy_operator_proxies{phase="Provisioning"} 1
proxy_operator_proxies{phase="Ready"} 3
`
if err := testutil.GatherAndCompare(reg, strings.NewReader(expected),
"proxy_operator_proxies", "proxy_operator_leases_active"); err != nil {
t.Error(err)
}
}
func TestObserveProbe_andForget(t *testing.T) {
t.Parallel()
m := New()
reg := register(t, m, nil, 0)
m.ObserveProbe("default/p1", 30*time.Millisecond, true)
m.ObserveProbe("default/p1", 40*time.Millisecond, false)
m.ObserveProbe("default/p2", 10*time.Millisecond, true)
if got := testutil.CollectAndCount(m.healthcheckDuration); got != 2 {
t.Errorf("duration series = %d, want 2 (one per proxy)", got)
}
if got := testutil.ToFloat64(m.healthcheckFailures.WithLabelValues("default/p1")); got != 1 {
t.Errorf("p1 failures = %v, want 1 (only the failed probe)", got)
}
m.ForgetProxy("default/p1")
if got := testutil.CollectAndCount(m.healthcheckDuration); got != 1 {
t.Errorf("duration series after ForgetProxy = %d, want 1 — series must not leak", got)
}
if got := testutil.CollectAndCount(m.healthcheckFailures); got != 0 {
t.Errorf("failure series after ForgetProxy = %d, want 0", got)
}
_ = reg
}
func TestLeaseRequest(t *testing.T) {
t.Parallel()
m := New()
register(t, m, nil, 0)
m.LeaseRequest("granted")
m.LeaseRequest("granted")
m.LeaseRequest("no_match")
if got := testutil.ToFloat64(m.leaseRequests.WithLabelValues("granted")); got != 2 {
t.Errorf("granted = %v, want 2", got)
}
if got := testutil.ToFloat64(m.leaseRequests.WithLabelValues("no_match")); got != 1 {
t.Errorf("no_match = %v, want 1", got)
}
}
func TestProviderRequest(t *testing.T) {
t.Parallel()
m := New()
register(t, m, nil, 0)
m.ProviderRequest("gcp-eu", "create", "ok")
m.ProviderRequest("gcp-eu", "create", "quota_exceeded")
if got := testutil.ToFloat64(m.providerRequests.WithLabelValues("gcp-eu", "create", "ok")); got != 1 {
t.Errorf("ok = %v, want 1", got)
}
if got := testutil.ToFloat64(m.providerRequests.WithLabelValues("gcp-eu", "create", "quota_exceeded")); got != 1 {
t.Errorf("quota_exceeded = %v, want 1", got)
}
}
func TestRegister_freshRegistryPerTest(t *testing.T) {
t.Parallel()
// Registering the same metric set on two registries must both succeed —
// the property init()-style global registration would break.
m1, m2 := New(), New()
register(t, m1, nil, 0)
register(t, m2, nil, 0)
}
func TestRegisterProviderTargets_scrape(t *testing.T) {
t.Parallel()
checked := time.Unix(1757602800, 0)
targets := []ProviderTarget{
{Provider: "kvm-home", Target: "nas1", Up: true, Duration: 84 * time.Millisecond, CheckedAt: checked},
{Provider: "kvm-home", Target: "nas2", Up: false, Duration: 15 * time.Second, CheckedAt: checked},
}
reg := prometheus.NewRegistry()
if err := RegisterProviderTargets(reg, func() []ProviderTarget { return targets }); err != nil {
t.Fatalf("RegisterProviderTargets: %v", err)
}
expected := `
# HELP proxy_operator_provider_check_duration_seconds Duration of the target's latest provider health check.
# TYPE proxy_operator_provider_check_duration_seconds gauge
proxy_operator_provider_check_duration_seconds{provider="kvm-home",target="nas1"} 0.084
proxy_operator_provider_check_duration_seconds{provider="kvm-home",target="nas2"} 15
# HELP proxy_operator_provider_check_timestamp_seconds Unix time of the target's latest provider health check.
# TYPE proxy_operator_provider_check_timestamp_seconds gauge
proxy_operator_provider_check_timestamp_seconds{provider="kvm-home",target="nas1"} 1.7576028e+09
proxy_operator_provider_check_timestamp_seconds{provider="kvm-home",target="nas2"} 1.7576028e+09
# HELP proxy_operator_provider_target_up Whether the target passed its latest provider health check (1) or not (0).
# TYPE proxy_operator_provider_target_up gauge
proxy_operator_provider_target_up{provider="kvm-home",target="nas1"} 1
proxy_operator_provider_target_up{provider="kvm-home",target="nas2"} 0
`
if err := testutil.GatherAndCompare(reg, strings.NewReader(expected)); err != nil {
t.Error(err)
}
}
func TestRegisterProviderTargets_emptySnapshotHasNoSeries(t *testing.T) {
t.Parallel()
reg := prometheus.NewRegistry()
if err := RegisterProviderTargets(reg, func() []ProviderTarget { return nil }); err != nil {
t.Fatalf("RegisterProviderTargets: %v", err)
}
if n, err := testutil.GatherAndCount(reg); err != nil || n != 0 {
t.Errorf("series before the first check = %d (%v), want 0", n, err)
}
}