[receiver/zookeeper] Add support for ruok command

.chloggen/support-ruok-4lw-cmd.yaml

@@ -0,0 +1,20 @@
+# Use this changelog template to create an entry for release notes.
+# If your change doesn't affect end users, such as a test fix or a tooling change,
+# you should instead start your pull request title with [chore] or use the "Skip Changelog" label.
+
+# 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: zookeeperreceiver
+
+# A brief description of the change.  Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: Adds an additional health check metric based off of the response from the zookeeper ruok 4lw command.
+
+# Mandatory: One or more tracking issues related to the change. You can use the PR number here if no issue exists.
+issues: [21481]
+
+# (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:

receiver/zookeeperreceiver/documentation.md

@@ -120,6 +120,14 @@ Number of currently executing requests.
 | ---- | ----------- | ---------- | ----------------------- | --------- |
 | {requests} | Sum | Int | Cumulative | false |
 
+### zookeeper.ruok
+
+Response from zookeeper ruok command
+
+| Unit | Metric Type | Value Type |
+| ---- | ----------- | ---------- |
+| 1 | Gauge | Int |
+
 ### zookeeper.sync.pending
 
 The number of pending syncs from the followers. Only exposed by the leader.

receiver/zookeeperreceiver/integration_test.go

@@ -34,7 +34,7 @@ func integrationTest(name string, image string, standalone bool) func(*testing.T
 			testcontainers.ContainerRequest{
 				Image: image,
 				Env: map[string]string{
-					"ZOO_4LW_COMMANDS_WHITELIST": "srvr,mntr",
+					"ZOO_4LW_COMMANDS_WHITELIST": "srvr,mntr,ruok",
 					"ZOO_STANDALONE_ENABLED":     fmt.Sprintf("%t", standalone),
 				},
 				ExposedPorts: []string{zookeeperPort},

receiver/zookeeperreceiver/internal/metadata/testdata/config.yaml

@@ -25,6 +25,8 @@ all_set:
       enabled: true
     zookeeper.request.active:
       enabled: true
+    zookeeper.ruok:
+      enabled: true
     zookeeper.sync.pending:
       enabled: true
     zookeeper.watch.count:
@@ -62,6 +64,8 @@ none_set:
       enabled: false
     zookeeper.request.active:
       enabled: false
+    zookeeper.ruok:
+      enabled: false
     zookeeper.sync.pending:
       enabled: false
     zookeeper.watch.count:

receiver/zookeeperreceiver/metadata.yaml

@@ -145,3 +145,9 @@ metrics:
       value_type: int
       monotonic: true
       aggregation: cumulative
+  zookeeper.ruok:
+    enabled: true
+    description: Response from zookeeper ruok command
+    unit: 1
+    gauge:
+      value_type: int

receiver/zookeeperreceiver/metrics.go

@@ -36,6 +36,8 @@ const (
 
 	serverStateKey = "zk_server_state"
 	zkVersionKey   = "zk_version"
+
+	ruokKey = "ruok"
 )
 
 // metricCreator handles generation of metric and metric recording
@@ -89,6 +91,8 @@ func (m *metricCreator) recordDataPointsFunc(metric string) func(ts pcommon.Time
 		return m.mb.RecordZookeeperFileDescriptorLimitDataPoint
 	case fSyncThresholdExceedCountMetricKey:
 		return m.mb.RecordZookeeperFsyncExceededThresholdCountDataPoint
+	case ruokKey:
+		return m.mb.RecordZookeeperRuokDataPoint
 	case packetsReceivedMetricKey:
 		return func(ts pcommon.Timestamp, val int64) {
 			m.mb.RecordZookeeperPacketCountDataPoint(ts, val, metadata.AttributeDirectionReceived)

receiver/zookeeperreceiver/scraper.go

@@ -25,6 +25,7 @@ var zookeeperFormatRE = regexp.MustCompile(`(^zk_\w+)\s+([\w\.\-]+)`)
 
 const (
 	mntrCommand = "mntr"
+	ruokCommand = "ruok"
 )
 
 type zookeeperMetricsScraper struct {
@@ -77,16 +78,27 @@ func (z *zookeeperMetricsScraper) scrape(ctx context.Context) (pmetric.Metrics,
 	var ctxWithTimeout context.Context
 	ctxWithTimeout, z.cancel = context.WithTimeout(ctx, z.config.Timeout)
 
-	response, err := z.runCommand(ctxWithTimeout, "mntr")
+	responseMntr, err := z.runCommand(ctxWithTimeout, "mntr")
 	if err != nil {
 		return pmetric.NewMetrics(), err
 	}
 
-	return z.processMntr(response)
+	responseRuok, err := z.runCommand(ctxWithTimeout, "ruok")
+	if err != nil {
+		return pmetric.NewMetrics(), err
+	}
+
+	resourceOpts := make([]metadata.ResourceMetricsOption, 0, 2)
+
+	resourceOpts = z.processMntr(responseMntr, resourceOpts)
+	z.processRuok(responseRuok)
+
+	return z.mb.Emit(resourceOpts...), nil
 }
 
 func (z *zookeeperMetricsScraper) runCommand(ctx context.Context, command string) ([]string, error) {
 	conn, err := z.config.Dial()
+
 	if err != nil {
 		z.logger.Error("failed to establish connection",
 			zap.String("endpoint", z.config.Endpoint),
@@ -123,10 +135,9 @@ func (z *zookeeperMetricsScraper) runCommand(ctx context.Context, command string
 	return response, nil
 }
 
-func (z *zookeeperMetricsScraper) processMntr(response []string) (pmetric.Metrics, error) {
+func (z *zookeeperMetricsScraper) processMntr(response []string, resourceOpts []metadata.ResourceMetricsOption) []metadata.ResourceMetricsOption {
 	creator := newMetricCreator(z.mb)
 	now := pcommon.NewTimestampFromTime(time.Now())
-	resourceOpts := make([]metadata.ResourceMetricsOption, 0, 2)
 	for _, line := range response {
 		parts := zookeeperFormatRE.FindStringSubmatch(line)
 		if len(parts) != 3 {
@@ -167,7 +178,29 @@ func (z *zookeeperMetricsScraper) processMntr(response []string) (pmetric.Metric
 
 	// Generate computed metrics
 	creator.generateComputedMetrics(z.logger, now)
-	return z.mb.Emit(resourceOpts...), nil
+	return resourceOpts
+}
+
+func (z *zookeeperMetricsScraper) processRuok(response []string) {
+	creator := newMetricCreator(z.mb)
+	now := pcommon.NewTimestampFromTime(time.Now())
+
+	metricKey := "ruok"
+	metricValue := int64(0)
+
+	if len(response) > 0 {
+		if response[0] == "imok" {
+			metricValue = int64(1)
+		} else {
+			z.logger.Error("invalid response from ruok",
+				zap.String("command", ruokCommand),
+			)
+			return
+		}
+	}
+
+	recordDataPoints := creator.recordDataPointsFunc(metricKey)
+	recordDataPoints(now, metricValue)
 }
 
 func closeConnection(conn net.Conn) error {