[8.19] (backport #11718) [OTEL] Hide healthcheckv2 from agent status. (#11775)

* [OTEL] Hide healthcheckv2 from agent status. (#11718)

* Hide healthcheckv2 from agent status.

* Add changelog entry.

* Update entry.

* Filter out by specific UUID.

(cherry picked from commit 81d77f5)

# Conflicts:
#	internal/pkg/otel/manager/manager.go

* Fix conflict.

---------

Co-authored-by: Blake Rouse <[email protected]>

Author: mergify[bot]

changelog/fragments/1765377327-hide-healthcheckv2-from-status-output.yaml

@@ -0,0 +1,45 @@
+# REQUIRED
+# Kind can be one of:
+# - breaking-change: a change to previously-documented behavior
+# - deprecation: functionality that is being removed in a later release
+# - bug-fix: fixes a problem in a previous version
+# - enhancement: extends functionality but does not break or fix existing behavior
+# - feature: new functionality
+# - known-issue: problems that we are aware of in a given version
+# - security: impacts on the security of a product or a user’s deployment.
+# - upgrade: important information for someone upgrading from a prior version
+# - other: does not fit into any of the other categories
+kind: bug-fix
+
+# REQUIRED for all kinds
+# Change summary; a 80ish characters long description of the change.
+summary: hide healthcheckv2 from status output
+
+# REQUIRED for breaking-change, deprecation, known-issue
+# Long description; in case the summary is not enough to describe the change
+# this field accommodate a description without length limits.
+# description:
+
+# REQUIRED for breaking-change, deprecation, known-issue
+# impact:
+
+# REQUIRED for breaking-change, deprecation, known-issue
+# action:
+
+# REQUIRED for all kinds
+# Affected component; usually one of "elastic-agent", "fleet-server", "filebeat", "metricbeat", "auditbeat", "all", etc.
+component: elastic-agent
+
+# AUTOMATED
+# OPTIONAL to manually add other PR URLs
+# PR URL: A link the PR that added the changeset.
+# If not present is automatically filled by the tooling finding the PR where this changelog fragment has been added.
+# NOTE: the tooling supports backports, so it's able to fill the original PR number instead of the backport PR number.
+# Please provide it if you are adding a fragment for a different PR.
+# pr: https://github.com/owner/repo/1234
+
+# AUTOMATED
+# OPTIONAL to manually add other issue URLs
+# Issue URL; optional; the GitHub issue related to this changeset (either closes or is part of).
+# If not present is automatically filled by the tooling with the issue linked to the PR number.
+# issue: https://github.com/owner/repo/1234

internal/pkg/otel/manager/execution_subprocess.go

@@ -14,7 +14,6 @@ import (
 	"sync"
 	"time"
 
-	"github.com/gofrs/uuid/v5"
 	"go.opentelemetry.io/collector/component"
 	"gopkg.in/yaml.v3"
 
@@ -41,16 +40,12 @@ const (
 
 // newSubprocessExecution creates a new execution which runs the otel collector in a subprocess. A metricsPort or
 // healthCheckPort of 0 will result in a random port being used.
-func newSubprocessExecution(logLevel logp.Level, collectorPath string, metricsPort int, healthCheckPort int) (*subprocessExecution, error) {
-	nsUUID, err := uuid.NewV4()
-	if err != nil {
-		return nil, fmt.Errorf("cannot generate UUID: %w", err)
-	}
+func newSubprocessExecution(logLevel logp.Level, collectorPath string, uuid string, metricsPort int, healthCheckPort int) (*subprocessExecution, error) {
 	componentType, err := component.NewType(healthCheckExtensionName)
 	if err != nil {
 		return nil, fmt.Errorf("cannot create component type: %w", err)
 	}
-	healthCheckExtensionID := component.NewIDWithName(componentType, nsUUID.String()).String()
+	healthCheckExtensionID := component.NewIDWithName(componentType, uuid).String()
 
 	return &subprocessExecution{
 		collectorPath: collectorPath,

internal/pkg/otel/manager/manager.go

@@ -18,24 +18,21 @@ import (
 	"sync/atomic"
 	"time"
 
+	"github.com/gofrs/uuid/v5"
+	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/status"
+	"go.opentelemetry.io/collector/confmap"
 	"go.uber.org/zap"
 
-	"github.com/elastic/elastic-agent/internal/pkg/agent/configuration"
-
-	componentmonitoring "github.com/elastic/elastic-agent/internal/pkg/agent/application/monitoring/component"
-
 	"github.com/elastic/elastic-agent-client/v7/pkg/client"
+	"github.com/elastic/elastic-agent-libs/logp"
+
 	"github.com/elastic/elastic-agent/internal/pkg/agent/application/info"
+	componentmonitoring "github.com/elastic/elastic-agent/internal/pkg/agent/application/monitoring/component"
 	"github.com/elastic/elastic-agent/internal/pkg/agent/application/paths"
+	"github.com/elastic/elastic-agent/internal/pkg/agent/configuration"
 	"github.com/elastic/elastic-agent/internal/pkg/otel/translate"
 	"github.com/elastic/elastic-agent/pkg/component"
 	"github.com/elastic/elastic-agent/pkg/component/runtime"
-
-	"github.com/open-telemetry/opentelemetry-collector-contrib/pkg/status"
-	"go.opentelemetry.io/collector/confmap"
-
-	"github.com/elastic/elastic-agent-libs/logp"
-
 	"github.com/elastic/elastic-agent/pkg/core/logger"
 )
 
@@ -82,8 +79,9 @@ type OTelManager struct {
 	agentInfo                  info.Agent
 	beatMonitoringConfigGetter translate.BeatMonitoringConfigGetter
 
-	collectorCfg *confmap.Conf
-	components   []component.Component
+	healthCheckExtID string
+	collectorCfg     *confmap.Conf
+	components       []component.Component
 
 	// The current configuration that the OTel collector is using. In the case that
 	// the mergedCollectorCfg is nil then the collector is not running.
@@ -142,6 +140,12 @@ func NewOTelManager(
 	var recoveryTimer collectorRecoveryTimer
 	var err error
 
+	hcUUID, err := uuid.NewV4()
+	if err != nil {
+		return nil, fmt.Errorf("cannot generate UUID: %w", err)
+	}
+	hcUUIDStr := hcUUID.String()
+
 	// determine the otel collector ports
 	collectorMetricsPort, collectorHealthCheckPort := 0, 0
 	if agentCollectorConfig != nil {
@@ -168,7 +172,7 @@ func NewOTelManager(
 			return nil, fmt.Errorf("failed to get the path to the collector executable: %w", err)
 		}
 		recoveryTimer = newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute)
-		exec, err = newSubprocessExecution(logLevel, executable, collectorMetricsPort, collectorHealthCheckPort)
+		exec, err = newSubprocessExecution(logLevel, executable, hcUUIDStr, collectorMetricsPort, collectorHealthCheckPort)
 		if err != nil {
 			return nil, fmt.Errorf("failed to create subprocess execution: %w", err)
 		}
@@ -183,6 +187,7 @@ func NewOTelManager(
 		baseLogger:                 baseLogger,
 		agentInfo:                  agentInfo,
 		beatMonitoringConfigGetter: beatMonitoringConfigGetter,
+		healthCheckExtID:           fmt.Sprintf("extension:healthcheckv2/%s", hcUUIDStr),
 		errCh:                      make(chan error, 1), // holds at most one error
 		collectorStatusCh:          make(chan *status.AggregateStatus, 1),
 		// componentStateCh uses a buffer channel to ensure that no state transitions are missed and to prevent
@@ -534,6 +539,8 @@ func (m *OTelManager) handleOtelStatusUpdate(otelStatus *status.AggregateStatus)
 					delete(extensionsMap.ComponentStatusMap, extensionKey)
 				case strings.HasPrefix(extensionKey, "extension:elastic_diagnostics"):
 					delete(extensionsMap.ComponentStatusMap, extensionKey)
+				case extensionKey == m.healthCheckExtID:
+					delete(extensionsMap.ComponentStatusMap, extensionKey)
 				}
 			}
 

internal/pkg/otel/manager/manager_test.go

@@ -348,7 +348,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector config updates",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter: newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			testFn: func(t *testing.T, m *OTelManager, e *EventListener, exec *testExecution, managerCtxCancel context.CancelFunc, collectorRunErr chan error) {
@@ -376,7 +380,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector stopped gracefully outside manager",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter: newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			testFn: func(t *testing.T, m *OTelManager, e *EventListener, exec *testExecution, managerCtxCancel context.CancelFunc, collectorRunErr chan error) {
@@ -405,7 +413,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector killed outside manager",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter: newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			testFn: func(t *testing.T, m *OTelManager, e *EventListener, exec *testExecution, managerCtxCancel context.CancelFunc, collectorRunErr chan error) {
@@ -448,7 +460,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector panics restarts",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter: newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			testFn: func(t *testing.T, m *OTelManager, e *EventListener, exec *testExecution, managerCtxCancel context.CancelFunc, collectorRunErr chan error) {
@@ -483,7 +499,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector panics reports fatal",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter: newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			testFn: func(t *testing.T, m *OTelManager, e *EventListener, exec *testExecution, managerCtxCancel context.CancelFunc, collectorRunErr chan error) {
@@ -524,7 +544,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector killed if delayed and manager is stopped",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				subprocessExec, err := newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				subprocessExec, err := newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 				if err != nil {
 					return nil, err
 				}
@@ -577,7 +601,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector gracefully exited if delayed a bit and manager is stopped",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				subprocessExec, err := newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				subprocessExec, err := newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 				if err != nil {
 					return nil, err
 				}
@@ -630,7 +658,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess user has healthcheck extension",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter: newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			testFn: func(t *testing.T, m *OTelManager, e *EventListener, exec *testExecution, managerCtxCancel context.CancelFunc, collectorRunErr chan error) {
@@ -665,7 +697,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector empty config",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter:           newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			skipListeningErrors: true,
@@ -712,7 +748,11 @@ func TestOTelManager_Run(t *testing.T) {
 		{
 			name: "subprocess collector failed to start",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 			restarter: newRecoveryBackoff(100*time.Nanosecond, 10*time.Second, time.Minute),
 			testFn: func(t *testing.T, m *OTelManager, e *EventListener, exec *testExecution, managerCtxCancel context.CancelFunc, collectorRunErr chan error) {
@@ -846,7 +886,11 @@ func TestOTelManager_Logging(t *testing.T) {
 		{
 			name: "subprocess execution",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), 0, 0)
 			},
 		},
 	} {
@@ -919,7 +963,11 @@ func TestOTelManager_Ports(t *testing.T) {
 		{
 			name: "subprocess execution",
 			execModeFn: func(collectorRunErr chan error) (collectorExecution, error) {
-				return newSubprocessExecution(logp.DebugLevel, testBinary, metricsPort, healthCheckPort)
+				hcUUID, err := uuid.NewV4()
+				if err != nil {
+					return nil, fmt.Errorf("cannot generate UUID: %w", err)
+				}
+				return newSubprocessExecution(logp.DebugLevel, testBinary, hcUUID.String(), metricsPort, healthCheckPort)
 			},
 			healthCheckEnabled: true,
 		},
@@ -1071,7 +1119,7 @@ func TestOTelManager_PortConflict(t *testing.T) {
 		waitTimeForStop,
 	)
 	require.NoError(t, err, "could not create otel manager")
-	executionMode, err := newSubprocessExecution(logp.DebugLevel, testBinary, 0, 0)
+	executionMode, err := newSubprocessExecution(logp.DebugLevel, testBinary, strings.TrimPrefix(m.healthCheckExtID, "extension:healthcheckv2/"), 0, 0)
 	require.NoError(t, err, "could not create subprocess execution mode")
 	m.execution = executionMode
 
@@ -1288,6 +1336,9 @@ func TestOTelManager_handleOtelStatusUpdate(t *testing.T) {
 							"extension:elastic_diagnostics/test": {
 								Event: componentstatus.NewEvent(componentstatus.StatusOK),
 							},
+							"extension:healthcheckv2/uuid": {
+								Event: componentstatus.NewEvent(componentstatus.StatusOK),
+							},
 						},
 					},
 				},
@@ -1373,6 +1424,7 @@ func TestOTelManager_handleOtelStatusUpdate(t *testing.T) {
 			mgr := &OTelManager{
 				logger:                 newTestLogger(),
 				components:             tt.components,
+				healthCheckExtID:       "extension:healthcheckv2/uuid",
 				currentComponentStates: make(map[string]runtime.ComponentComponentState),
 			}