[opampsupervisor] Add HealthCheckPort configuration parameter (open-telemetry#34704)

**Description:** <Describe what has changed.>
<!--Ex. Fixing a bug - Describe the bug and how this fixes the issue.
Ex. Adding a feature - Explain what this achieves.-->
Add a new configuration parameter to `agent` called `health_check_port`.
If this is set, then the supervisor will configure the agent's
healthcheck extension to use the given port. If it is unset, then we
will grab a random port same as before.

**Link to tracking Issue:** open-telemetry#34643

**Testing:** <Describe what testing was performed and which tests were
added.>
- Updated config validation tests
- Verified that healthcheck extension is configured with the correct
port and works as expected

Author: dpaasman00

.chloggen/supervisor-healthcheck-port-configurable.yaml

@@ -0,0 +1,27 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: opampsupervisor
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Add new config parameter `agent.health_check_port` to allow configuring the port used by the agent healthcheck extension."
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [34643]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext:
+
+# If your change doesn't affect end users or the exported elements of any package,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+# Optional: The change log or logs in which this entry should be included.
+# e.g. '[user]' or '[user, api]'
+# Include 'user' if the change is relevant to end users.
+# Include 'api' if there is a change to a library API.
+# Default: '[user]'
+change_logs: []

cmd/opampsupervisor/e2e_test.go

@@ -337,18 +337,19 @@ func TestSupervisorStartsWithNoOpAMPServer(t *testing.T) {
 
 	// The supervisor is started without a running OpAMP server.
 	// The supervisor should start successfully, even if the OpAMP server is stopped.
-	s := newSupervisor(t, "basic", map[string]string{
-		"url": server.addr,
+	s := newSupervisor(t, "healthcheck_port", map[string]string{
+		"url":              server.addr,
+		"healthcheck_port": "12345",
 	})
 
 	require.Nil(t, s.Start())
 	defer s.Shutdown()
 
 	// Verify the collector is running by checking the metrics endpoint
 	require.Eventually(t, func() bool {
-		resp, err := http.DefaultClient.Get("http://localhost:8888/metrics")
+		resp, err := http.DefaultClient.Get("http://localhost:12345")
 		if err != nil {
-			t.Logf("Failed check for prometheus metrics: %s", err)
+			t.Logf("Failed agent healthcheck request: %s", err)
 			return false
 		}
 		require.NoError(t, resp.Body.Close())

cmd/opampsupervisor/supervisor/config/config.go

@@ -121,13 +121,18 @@ type Agent struct {
 	Executable              string
 	OrphanDetectionInterval time.Duration    `mapstructure:"orphan_detection_interval"`
 	Description             AgentDescription `mapstructure:"description"`
+	HealthCheckPort         int              `mapstructure:"health_check_port"`
 }
 
 func (a Agent) Validate() error {
 	if a.OrphanDetectionInterval <= 0 {
 		return errors.New("agent::orphan_detection_interval must be positive")
 	}
 
+	if a.HealthCheckPort < 0 || a.HealthCheckPort > 65535 {
+		return errors.New("agent::health_check_port must be a valid port number")
+	}
+
 	if a.Executable == "" {
 		return errors.New("agent::executable must be specified")
 	}

cmd/opampsupervisor/supervisor/config/config_test.go

@@ -223,6 +223,82 @@ func TestValidate(t *testing.T) {
 			},
 			expectedError: "agent::orphan_detection_interval must be positive",
 		},
+		{
+			name: "Invalid port number",
+			config: Supervisor{
+				Server: OpAMPServer{
+					Endpoint: "wss://localhost:9090/opamp",
+					Headers: http.Header{
+						"Header1": []string{"HeaderValue"},
+					},
+					TLSSetting: configtls.ClientConfig{
+						Insecure: true,
+					},
+				},
+				Agent: Agent{
+					Executable:              "${file_path}",
+					OrphanDetectionInterval: 5 * time.Second,
+					HealthCheckPort:         65536,
+				},
+				Capabilities: Capabilities{
+					AcceptsRemoteConfig: true,
+				},
+				Storage: Storage{
+					Directory: "/etc/opamp-supervisor/storage",
+				},
+			},
+			expectedError: "agent::health_check_port must be a valid port number",
+		},
+		{
+			name: "Zero value port number",
+			config: Supervisor{
+				Server: OpAMPServer{
+					Endpoint: "wss://localhost:9090/opamp",
+					Headers: http.Header{
+						"Header1": []string{"HeaderValue"},
+					},
+					TLSSetting: configtls.ClientConfig{
+						Insecure: true,
+					},
+				},
+				Agent: Agent{
+					Executable:              "${file_path}",
+					OrphanDetectionInterval: 5 * time.Second,
+					HealthCheckPort:         0,
+				},
+				Capabilities: Capabilities{
+					AcceptsRemoteConfig: true,
+				},
+				Storage: Storage{
+					Directory: "/etc/opamp-supervisor/storage",
+				},
+			},
+		},
+		{
+			name: "Normal port number",
+			config: Supervisor{
+				Server: OpAMPServer{
+					Endpoint: "wss://localhost:9090/opamp",
+					Headers: http.Header{
+						"Header1": []string{"HeaderValue"},
+					},
+					TLSSetting: configtls.ClientConfig{
+						Insecure: true,
+					},
+				},
+				Agent: Agent{
+					Executable:              "${file_path}",
+					OrphanDetectionInterval: 5 * time.Second,
+					HealthCheckPort:         29848,
+				},
+				Capabilities: Capabilities{
+					AcceptsRemoteConfig: true,
+				},
+				Storage: Storage{
+					Directory: "/etc/opamp-supervisor/storage",
+				},
+			},
+		},
 	}
 
 	// create some fake files for validating agent config

cmd/opampsupervisor/supervisor/supervisor.go

@@ -179,10 +179,13 @@ func (s *Supervisor) Start() error {
 		return fmt.Errorf("could not get bootstrap info from the Collector: %w", err)
 	}
 
-	healthCheckPort, err := s.findRandomPort()
+	healthCheckPort := s.config.Agent.HealthCheckPort
+	if healthCheckPort == 0 {
+		healthCheckPort, err = s.findRandomPort()
 
-	if err != nil {
-		return fmt.Errorf("could not find port for health check: %w", err)
+		if err != nil {
+			return fmt.Errorf("could not find port for health check: %w", err)
+		}
 	}
 
 	s.agentHealthCheckEndpoint = fmt.Sprintf("localhost:%d", healthCheckPort)

cmd/opampsupervisor/testdata/supervisor/supervisor_healthcheck_port.yaml

@@ -0,0 +1,19 @@
+server:
+  endpoint: ws://{{.url}}/v1/opamp
+  tls:
+    insecure: true
+
+capabilities:
+  reports_effective_config: true
+  reports_own_metrics: true
+  reports_health: true
+  accepts_remote_config: true
+  reports_remote_config: true
+  accepts_restart_command: true
+
+storage:
+  directory: "{{.storage_dir}}"
+
+agent:
+  executable: ../../bin/otelcontribcol_{{.goos}}_{{.goarch}}{{.extension}}
+  health_check_port: "{{ .healthcheck_port }}"