COSI-65: Update metrics address example and CI doc

.github/scripts/e2e_tests_metrics.sh

@@ -41,7 +41,10 @@ log_and_run kubectl port-forward -n "$NAMESPACE" svc/"$SERVICE" "$LOCAL_PORT":"$
 PORT_FORWARD_PID=$!
 
 # Wait a few seconds to ensure port-forward is established
-log_and_run sleep 5
+while ! nc -vz localhost $LOCAL_PORT > /dev/null 2>&1 ; do
+    # echo sleeping
+    sleep 0.1
+done
 
 # Fetch metrics
 log_and_run curl -s http://localhost:$LOCAL_PORT/metrics > /tmp/metrics_output.log

.github/workflows/e2e-feature-tests.yml

@@ -116,10 +116,14 @@ jobs:
       run: |
         .github/scripts/e2e_tests_brownfield_use_case.sh
 
-    # the script accepts number of requests for  APIs for CREATE_BUCKET, DELETE_BUCKET, GET_INFO
+    # the script accepts number of requests for APIs: CREATE_BUCKET, DELETE_BUCKET, GET_INFO
     # GRANT_ACCESS and REVOKE_ACCESS in order
-    # Example below we we are testing for 2 CREATE_BUCKET, 1 DELETE_BUCKET,
-    # 1 GET_INFO, 2 GRANT_ACCESS and 2 REVOKE_ACCESS API counts
+    # Example below we are testing for those API counts:
+    # - 2 CREATE_BUCKET
+    # - 1 DELETE_BUCKET
+    # - 1 GET_INFO
+    # - 2 GRANT_ACCESS
+    # - 2 REVOKE_ACCESS
     - name: E2E tests for metrics using API call metrics generated from above tests
       run: |
         .github/scripts/e2e_tests_metrics.sh 2 1 1 2 2

.github/workflows/helm-validation.yml

@@ -72,10 +72,14 @@ jobs:
       run: |
         .github/scripts/verify_helm_install.sh
 
-    # the script accepts number of requests for  APIs for CREATE_BUCKET, DELETE_BUCKET, GET_INFO
+    # the script accepts number of requests for APIs: CREATE_BUCKET, DELETE_BUCKET, GET_INFO
     # GRANT_ACCESS and REVOKE_ACCESS in order
-    # Example below we we are testing for 0 CREATE_BUCKET, 0 DELETE_BUCKET,
-    # 1 GET_INFO, 0 GRANT_ACCESS and 0 REVOKE_ACCESS API counts
+    # Example below we are testing for those API counts:
+    # - 0 CREATE_BUCKET
+    # - 0 DELETE_BUCKET
+    # - 1 GET_INFO
+    # - 0 GRANT_ACCESS
+    # - 0 REVOKE_ACCESS
     - name: Verify metrics for healthcheck route
       run: |
         .github/scripts/e2e_tests_metrics.sh 0 0 1 0 0

cmd/scality-cosi-driver/cmd.go

@@ -42,10 +42,10 @@ const (
 
 var (
 	driverAddress        = flag.String("driver-address", defaultDriverAddress, "driver address for the socket file, default: unix:///var/lib/cosi/cosi.sock")
-	driverPrefix         = flag.String("driver-prefix", defaultDriverPrefix, "prefix for COSI driver, e.g. <prefix>.scality.com, default cosi.scality.com")
-	driverMetricsAddress = flag.String("driver-metrics-address", defaultMetricsAddress, "The address to expose Prometheus metrics, default: :8080")
+	driverPrefix         = flag.String("driver-prefix", defaultDriverPrefix, "prefix for COSI driver, e.g. <prefix>.scality.com, default: cosi")
+	driverMetricsAddress = flag.String("driver-metrics-address", defaultMetricsAddress, "The address (hostname:port) to expose Prometheus metrics, default: 0.0.0.0:8080")
 	driverMetricsPath    = flag.String("driver-metrics-path", defaultMetricsPath, "path for the metrics endpoint, default: /metrics")
-	driverMetricsPrefix  = flag.String("driver-custom-metrics-prefix", defaultMetricsPrefix, "prefix for the metrics, default: scality_cosi_driver_")
+	driverMetricsPrefix  = flag.String("driver-custom-metrics-prefix", defaultMetricsPrefix, "prefix for the metrics, default: scality_cosi_driver")
 )
 
 func init() {
@@ -89,8 +89,7 @@ func run(ctx context.Context) error {
 	}
 
 	err = server.Run(ctx, registry)
-	shutdownCtx, shutdownCancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer shutdownCancel()
+	shutdownCtx, _ := context.WithTimeout(context.Background(), 5*time.Second)
 	if shutdownErr := metricsServer.Shutdown(shutdownCtx); shutdownErr != nil {
 		klog.ErrorS(shutdownErr, "Failed to gracefully shutdown metrics server")
 	}

docs/metrics-overview.md

@@ -31,5 +31,5 @@ grpc_server_started_total{grpc_method="DriverGetInfo",grpc_service="cosi.v1alpha
 
 ## Additional Resource
 
-- [gRPC-Go Prometheus Metrics](https://github.com/grpc-ecosystem/go-grpc-prometheus)
+- [gRPC-Go Prometheus Metrics](https://github.com/grpc-ecosystem/go-grpc-middleware)
 - [Default Prometheus Metrics](https://pkg.go.dev/github.com/prometheus/client_golang/prometheus#pkg-subdirectories)

pkg/grpcfactory/server.go

@@ -38,7 +38,7 @@ func (s *COSIProvisionerServer) Run(ctx context.Context, registry prometheus.Reg
 
 	srvMetrics := grpcprom.NewServerMetrics(
 		grpcprom.WithServerHandlingTimeHistogram(
-			grpcprom.WithHistogramBuckets([]float64{0.001, 0.01, 0.1, 0.3, 0.6, 1, 3, 6, 9, 20, 30, 60, 90, 120}),
+			grpcprom.WithHistogramBuckets([]float64{0.01, 0.1, 0.5, 1, 2, 5}),
 		),
 	)
 	if err := registry.Register(srvMetrics); err != nil {