[cmd/opampsupervisor]: Configure the ppid option in the opamp exten…

…sion (#32875)

**Description:** <Describe what has changed.>
* Configures the PPID of the opamp extension in the supervisor. This
allows the collector to detect if the supervisor exits and shut itself
down.

**Link to tracking Issue:** Closes #32189

**Testing:** <Describe what testing was performed and which tests were
added.>
* Manually tested by starting the supervisor, then kill -9'ing the
supervisor. The collector previously would have still been running, but
now shuts itself down. Doing this you can also see the following log:
```
2024-05-06T14:52:31.010-0400	error	[email protected]/collector.go:278	Asynchronous error received, terminating process	{"error": "collector was orphaned, process with pid 38908 does not exist"}
```

**Documentation:** <Describe the documentation added.>
Added `orphan_detection_interval` to the spec as a configurable option

---------

Co-authored-by: Tiffany Hrabusa <[email protected]>
Co-authored-by: Andrzej Stencel <[email protected]>

.chloggen/feat_opamp-supervisor-specify-ppid.yaml

@@ -0,0 +1,13 @@
+# Use this changelog template to create an entry for release notes.
+
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: bug_fix
+
+# The name of the component, or a single word describing the area of concern, (e.g. filelogreceiver)
+component: cmd/opampsupervisor
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: The OpAMP supervisor now configures the `ppid` parameter of the opamp extension, which allows the collector to shut down if the supervisor is no longer running.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [32189]

cmd/opampsupervisor/specification/README.md

@@ -123,6 +123,9 @@ agent:
   # Path to Collector executable. Required.
   executable: /opt/otelcol/bin/otelcol
 
+  # The interval on which the Collector checks to see if it's been orphaned.
+  orphan_detection_interval: 5s
+
   # Extra command line flags to pass to the Collector executable.
   args:
 

cmd/opampsupervisor/supervisor/config/config.go

@@ -8,6 +8,7 @@ import (
 	"os"
 	"path/filepath"
 	"runtime"
+	"time"
 
 	"go.opentelemetry.io/collector/config/configtls"
 )
@@ -66,8 +67,9 @@ type OpAMPServer struct {
 }
 
 type Agent struct {
-	Executable  string
-	Description AgentDescription `mapstructure:"description"`
+	Executable              string
+	OrphanDetectionInterval time.Duration    `mapstructure:"orphan_detection_interval"`
+	Description             AgentDescription `mapstructure:"description"`
 }
 
 type AgentDescription struct {

cmd/opampsupervisor/supervisor/supervisor.go

@@ -238,9 +238,16 @@ func (s *Supervisor) getBootstrapInfo() (err error) {
 
 	var cfg bytes.Buffer
 
+	orphanPollInterval := 5 * time.Second
+	if s.config.Agent != nil && s.config.Agent.OrphanDetectionInterval > 0 {
+		orphanPollInterval = s.config.Agent.OrphanDetectionInterval
+	}
+
 	err = s.bootstrapTemplate.Execute(&cfg, map[string]any{
-		"InstanceUid":    s.persistentState.InstanceID.String(),
-		"SupervisorPort": supervisorPort,
+		"InstanceUid":      s.persistentState.InstanceID.String(),
+		"SupervisorPort":   supervisorPort,
+		"PID":              os.Getpid(),
+		"PPIDPollInterval": orphanPollInterval,
 	})
 	if err != nil {
 		return err

cmd/opampsupervisor/supervisor/templates/bootstrap.yaml

@@ -11,6 +11,8 @@ extensions:
         endpoint: "ws://localhost:{{.SupervisorPort}}/v1/opamp"
         tls:
           insecure: true
+    ppid: {{.PID}}
+    ppid_poll_interval: {{.PPIDPollInterval}}
 
 service:
   pipelines: