Files
graphql-monitoring-proxy/admin_dashboard_cluster_test.go
T
lukaszraczylo c2c75d69c0 perf+coverage: optimisation pass + coverage push to ≥70%
Performance / resource usage:
- circuit_breaker_metrics: fix data race on failCounters map (RWMutex + double-checked locking)
- server.go: drop user_id and op_name metric labels (Prometheus cardinality bound); de-duplicate extractUserInfo
- graphql.go: gate runtime.ReadMemStats per-request behind ENABLE_ALLOCATION_TRACKING flag (default off)
- graphql.go: collapse two-pass AST scan into single pass; lower-case once
- sanitization.go: cache compiled redaction regexes per pattern via sync.Map; hoist inner constants to pkg vars
- proxy.go: hoist connection/timeout substrings to pkg vars; sentinel errors for static error paths; drop dead Headers map alloc
- metrics_aggregator.go: log-field allocation guarded by Logger.IsLevelEnabled
- logging/logger.go: add IsLevelEnabled helper
- lru_cache.go: 16-shard sharding, FNV-1a routing (concurrent throughput +22%)
- cache/memory/lru_memory_cache.go: gzip compress/decompress moved outside mu.Lock
- rps_tracker.go: RWMutex+uint64 -> atomic.Uint64
- retry_budget.go: drop unused mutex
- api.go: bannedUsersIDs map+RWMutex -> sync.Map (+ snapshot/replace helpers)
- tracing/tracing.go: pkg-level constSpanAttrs, copy-then-append in StartSpanWithAttributes
- admin_dashboard.go: handleStatsWebSocket reuses bytes.Buffer + json.Encoder per connection

Build / runtime:
- Makefile: -ldflags="-s -w" -trimpath, CGO_ENABLED=0 for build (=1 for test recipes)
- Dockerfile + Dockerfile.goreleaser: ENV GOMEMLIMIT=512MiB
- main.go: blank import go.uber.org/automaxprocs (cgroup-aware GOMAXPROCS)
- main.go: PPROF_PORT env var wires net/http/pprof on 127.0.0.1 only with full server timeouts
- README.md: env-var docs + metric-label docs updated; cardinality note

Test coverage push (per package):
- main 51.2% -> 74.7%
- cache 66.3% -> 93.7%
- cache/redis 45.5% -> 98.2%
- tracing 66.7% -> 72.9%
- (cache/memory 91.6%, logging 91.9%, monitoring 77.6%, pkg/pools 100% unchanged)

New test files: coverage_micro_test, coverage_extras_test, server_handlers_test,
api_health_test, admin_dashboard_cluster_test, metrics_aggregator_test, concerns_test,
cache/cache_coverage_test, cache/redis/redis_coverage_test, tracing/tracing_coverage_test.

Bug fix: connection_resilience_test.go TestIntegratedHealthManagement.health_manager_startup
was sync.Once-coupled to InitializeBackendHealth and panicked when another test (e.g. via
parseConfig) had already triggered Once. Use NewBackendHealthManager directly.
2026-04-19 19:49:24 +01:00

248 lines
7.2 KiB
Go

package main
import (
"encoding/json"
"io"
"net/http/httptest"
"testing"
"github.com/gofiber/fiber/v2"
libpack_logger "github.com/lukaszraczylo/graphql-monitoring-proxy/logging"
libpack_monitoring "github.com/lukaszraczylo/graphql-monitoring-proxy/monitoring"
"github.com/stretchr/testify/assert"
)
// newClusterApp registers all cluster + control routes on a fresh Fiber app.
func newClusterApp(t *testing.T) (*fiber.App, *AdminDashboard) {
t.Helper()
app := fiber.New()
logger := libpack_logger.New()
dashboard := NewAdminDashboard(logger)
dashboard.RegisterRoutes(app)
return app, dashboard
}
// ensureNilAggregator guarantees no metrics aggregator is active for the test
// and restores the original value after.
func ensureNilAggregator(t *testing.T) {
t.Helper()
aggregatorMutex.Lock()
orig := metricsAggregator
metricsAggregator = nil
aggregatorMutex.Unlock()
t.Cleanup(func() {
aggregatorMutex.Lock()
metricsAggregator = orig
aggregatorMutex.Unlock()
})
}
// ---- getClusterStats -------------------------------------------------------
func TestGetClusterStats_NoAggregator_Returns503(t *testing.T) {
ensureNilAggregator(t)
app, _ := newClusterApp(t)
req := httptest.NewRequest("GET", "/admin/api/cluster/stats", nil)
resp, err := app.Test(req)
assert.NoError(t, err)
assert.Equal(t, 503, resp.StatusCode)
var body map[string]any
raw, _ := io.ReadAll(resp.Body)
assert.NoError(t, json.Unmarshal(raw, &body))
assert.Equal(t, false, body["cluster_mode"])
assert.NotEmpty(t, body["error"])
}
// ---- getClusterInstances ---------------------------------------------------
func TestGetClusterInstances_NoAggregator_Returns503(t *testing.T) {
ensureNilAggregator(t)
app, _ := newClusterApp(t)
req := httptest.NewRequest("GET", "/admin/api/cluster/instances", nil)
resp, err := app.Test(req)
assert.NoError(t, err)
assert.Equal(t, 503, resp.StatusCode)
var body map[string]any
raw, _ := io.ReadAll(resp.Body)
assert.NoError(t, json.Unmarshal(raw, &body))
assert.Equal(t, false, body["cluster_mode"])
assert.NotEmpty(t, body["error"])
}
// ---- getClusterDebug -------------------------------------------------------
func TestGetClusterDebug_NoAggregator_Returns200WithFalseFlag(t *testing.T) {
ensureNilAggregator(t)
// also set cfg so the redis_cache_enabled branch is exercised
cfg = &config{
Logger: libpack_logger.New(),
}
cfg.Cache.CacheEnable = true
cfg.Cache.CacheRedisEnable = false
app, _ := newClusterApp(t)
req := httptest.NewRequest("GET", "/admin/api/cluster/debug", nil)
resp, err := app.Test(req)
assert.NoError(t, err)
assert.Equal(t, 200, resp.StatusCode)
var body map[string]any
raw, _ := io.ReadAll(resp.Body)
assert.NoError(t, json.Unmarshal(raw, &body))
assert.Equal(t, false, body["aggregator_initialized"])
assert.Equal(t, false, body["redis_cache_enabled"])
assert.Equal(t, true, body["cache_enabled"])
}
func TestGetClusterDebug_NilCfg_Returns200WithDefaults(t *testing.T) {
ensureNilAggregator(t)
orig := cfg
cfg = nil
defer func() { cfg = orig }()
app, _ := newClusterApp(t)
req := httptest.NewRequest("GET", "/admin/api/cluster/debug", nil)
resp, err := app.Test(req)
assert.NoError(t, err)
assert.Equal(t, 200, resp.StatusCode)
var body map[string]any
raw, _ := io.ReadAll(resp.Body)
assert.NoError(t, json.Unmarshal(raw, &body))
assert.Equal(t, false, body["aggregator_initialized"])
assert.Equal(t, false, body["redis_cache_enabled"])
}
// ---- forcePublish ----------------------------------------------------------
func TestForcePublish_NoAggregator_Returns503(t *testing.T) {
ensureNilAggregator(t)
app, _ := newClusterApp(t)
req := httptest.NewRequest("POST", "/admin/api/cluster/force-publish", nil)
resp, err := app.Test(req)
assert.NoError(t, err)
assert.Equal(t, 503, resp.StatusCode)
var body map[string]any
raw, _ := io.ReadAll(resp.Body)
assert.NoError(t, json.Unmarshal(raw, &body))
assert.Equal(t, false, body["success"])
assert.NotEmpty(t, body["error"])
}
// ---- gatherAllStats / gatherAllStatsWithMode / gatherAllStatsClusterAware --
func newDashboardForGather(t *testing.T) *AdminDashboard {
t.Helper()
logger := libpack_logger.New()
monitoring := libpack_monitoring.NewMonitoring(&libpack_monitoring.InitConfig{})
cfg = &config{
Logger: logger,
Monitoring: monitoring,
}
return NewAdminDashboard(logger)
}
func TestGatherAllStats_ReturnsExpectedTopLevelKeys(t *testing.T) {
ensureNilAggregator(t)
ad := newDashboardForGather(t)
result := ad.gatherAllStats()
assert.NotNil(t, result)
// cluster_mode must be false when no aggregator
assert.Equal(t, false, result["cluster_mode"])
// stats sub-map must exist
statsRaw, ok := result["stats"]
assert.True(t, ok, "stats key must be present")
stats, ok := statsRaw.(map[string]any)
assert.True(t, ok)
assert.NotEmpty(t, stats["timestamp"])
assert.NotNil(t, stats["uptime_seconds"])
assert.NotNil(t, stats["uptime_human"])
assert.NotEmpty(t, stats["version"])
assert.NotNil(t, stats["requests"])
// health sub-map must exist
healthRaw, ok := result["health"]
assert.True(t, ok, "health key must be present")
health, ok := healthRaw.(map[string]any)
assert.True(t, ok)
assert.NotNil(t, health["status"])
assert.NotNil(t, health["backend"])
}
func TestGatherAllStatsWithMode_FalseMode_ReturnsLocalStats(t *testing.T) {
ensureNilAggregator(t)
ad := newDashboardForGather(t)
result := ad.gatherAllStatsWithMode(false)
assert.NotNil(t, result)
assert.Equal(t, false, result["cluster_mode"])
assert.NotNil(t, result["stats"])
assert.NotNil(t, result["health"])
}
func TestGatherAllStatsWithMode_TrueModeNoAggregator_FallsBackToLocal(t *testing.T) {
ensureNilAggregator(t)
ad := newDashboardForGather(t)
// With no aggregator, cluster mode request must fall back to local stats.
result := ad.gatherAllStatsWithMode(true)
assert.NotNil(t, result)
assert.Equal(t, false, result["cluster_mode"])
}
func TestGatherAllStatsClusterAware_NoAggregator_FallsBackToLocal(t *testing.T) {
ensureNilAggregator(t)
ad := newDashboardForGather(t)
result := ad.gatherAllStatsClusterAware()
assert.NotNil(t, result)
assert.Equal(t, false, result["cluster_mode"])
}
func TestGatherAllStats_NilCfg_ReturnsStatsWithoutRequests(t *testing.T) {
ensureNilAggregator(t)
origCfg := cfg
cfg = nil
defer func() { cfg = origCfg }()
ad := NewAdminDashboard(nil)
result := ad.gatherAllStats()
assert.NotNil(t, result)
stats, ok := result["stats"].(map[string]any)
assert.True(t, ok)
// when cfg is nil, "requests" key must NOT be present
_, hasRequests := stats["requests"]
assert.False(t, hasRequests)
}
func TestGatherAllStats_RequestStatsShape(t *testing.T) {
ensureNilAggregator(t)
ad := newDashboardForGather(t)
result := ad.gatherAllStats()
stats := result["stats"].(map[string]any)
requests, ok := stats["requests"].(map[string]any)
assert.True(t, ok, "requests must be a map")
assert.NotNil(t, requests["total"])
assert.NotNil(t, requests["succeeded"])
assert.NotNil(t, requests["failed"])
assert.NotNil(t, requests["skipped"])
assert.NotNil(t, requests["success_rate_pct"])
assert.NotNil(t, requests["failure_rate_pct"])
assert.NotNil(t, requests["skip_rate_pct"])
assert.NotNil(t, requests["avg_requests_per_second"])
assert.NotNil(t, requests["current_requests_per_second"])
}