Update prometheus params passed to run monitored tmpnet cmd (#4343)

Author: aaronbuchwald

.github/actions/c-chain-reexecution-benchmark/action.yml

@@ -30,6 +30,10 @@ inputs:
     description: 'The duration of the AWS role to assume for S3 access.'
     required: true
     default: '43200' # 12 hours
+  prometheus-url:
+    description: 'The URL of the prometheus instance.'
+    required: true
+    default: ''
   prometheus-push-url:
     description: 'The push URL of the prometheus instance.'
     required: true
@@ -93,6 +97,7 @@ runs:
             BENCHMARK_OUTPUT_FILE=${{ env.BENCHMARK_OUTPUT_FILE }} \
             RUNNER_NAME=${{ inputs.runner_name }} \
             METRICS_ENABLED=true
+        prometheus_url: ${{ inputs.prometheus-url }}
         prometheus_push_url: ${{ inputs.prometheus-push-url }}
         prometheus_username: ${{ inputs.prometheus-username }}
         prometheus_password: ${{ inputs.prometheus-password }}

.github/workflows/c-chain-reexecution-benchmark-container.yml

@@ -105,6 +105,7 @@ jobs:
           end-block: ${{ matrix.end-block }}
           block-dir-src: ${{ matrix.block-dir-src }}
           current-state-dir-src: ${{ matrix.current-state-dir-src }}
+          prometheus-url: ${{ secrets.PROMETHEUS_URL || '' }}
           prometheus-push-url: ${{ secrets.PROMETHEUS_PUSH_URL || '' }}
           prometheus-username: ${{ secrets.PROMETHEUS_USERNAME || '' }}
           prometheus-password: ${{ secrets.PROMETHEUS_PASSWORD || '' }}

.github/workflows/c-chain-reexecution-benchmark-gh-native.yml

@@ -95,6 +95,7 @@ jobs:
           end-block: ${{ matrix.end-block }}
           block-dir-src: ${{ matrix.block-dir-src }}
           current-state-dir-src: ${{ matrix.current-state-dir-src }}
+          prometheus-url: ${{ secrets.PROMETHEUS_URL || '' }}
           prometheus-push-url: ${{ secrets.PROMETHEUS_PUSH_URL || '' }}
           prometheus-username: ${{ secrets.PROMETHEUS_USERNAME || '' }}
           prometheus-password: ${{ secrets.PROMETHEUS_PASSWORD || '' }}

tests/reexecute/c/vm_reexecute_test.go

@@ -18,6 +18,7 @@ import (
 	"time"
 
 	"github.com/ava-labs/coreth/plugin/factory"
+	"github.com/google/uuid"
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/stretchr/testify/require"
 	"go.uber.org/zap"
@@ -62,10 +63,12 @@ var (
 	executionTimeout   time.Duration
 	labelsArg          string
 
-	labels = map[string]string{
+	networkUUID string = uuid.NewString()
+	labels             = map[string]string{
 		"job":               "c-chain-reexecution",
 		"is_ephemeral_node": "false",
 		"chain":             "C",
+		"network_uuid":      networkUUID,
 	}
 
 	configKey         = "config"
@@ -174,7 +177,7 @@ func benchmarkReexecuteRange(
 	r.NoError(prefixGatherer.Register("avalanche_snowman", consensusRegistry))
 
 	if metricsEnabled {
-		collectRegistry(b, "c-chain-reexecution", time.Minute, prefixGatherer, labels)
+		collectRegistry(b, "c-chain-reexecution", prefixGatherer, labels)
 	}
 
 	log := tests.NewDefaultLogger("c-chain-reexecution")
@@ -541,13 +544,14 @@ func newConsensusMetrics(registry prometheus.Registerer) (*consensusMetrics, err
 
 // collectRegistry starts prometheus and collects metrics from the provided gatherer.
 // Attaches the provided labels + GitHub labels if available to the collected metrics.
-func collectRegistry(tb testing.TB, name string, timeout time.Duration, gatherer prometheus.Gatherer, labels map[string]string) {
+func collectRegistry(tb testing.TB, name string, gatherer prometheus.Gatherer, labels map[string]string) {
 	r := require.New(tb)
 
-	ctx, cancel := context.WithTimeout(context.Background(), timeout)
-	tb.Cleanup(cancel)
+	startPromCtx, cancel := context.WithTimeout(context.Background(), tests.DefaultTimeout)
+	defer cancel()
 
-	r.NoError(tmpnet.StartPrometheus(ctx, tests.NewDefaultLogger("prometheus")))
+	logger := tests.NewDefaultLogger("prometheus")
+	r.NoError(tmpnet.StartPrometheus(startPromCtx, logger))
 
 	server, err := tests.NewPrometheusServer(gatherer)
 	r.NoError(err)
@@ -567,6 +571,10 @@ func collectRegistry(tb testing.TB, name string, timeout time.Duration, gatherer
 				return nil
 			}(),
 		))
+
+		checkMetricsCtx, cancel := context.WithTimeout(context.Background(), tests.DefaultTimeout)
+		defer cancel()
+		r.NoError(tmpnet.CheckMetricsExist(checkMetricsCtx, logger, networkUUID))
 	})
 
 	sdConfigFilePath, err = tmpnet.WritePrometheusSDConfig(name, tmpnet.SDConfig{