rfac: outputAccesslog func to skip accesslog at conn establishment

Signed-off-by: Yash Patel <[email protected]>

Author: yp969803

docs/proposal/tcp_long_connection_metrics.md

@@ -171,7 +171,7 @@ We will update the functions of metric.go for periodic updating the workload and
 
 #### Exposing long connection prometheus metrics 
 
-We will expose metrics for the connections whose duration exceeds 30 seconds. Not exposing metrics for short connection as it can lead to lot of metrics and they are also not suitable for prometheus metrics because prometheus itself has a scrape interval of maximum 15s, and short-lived connections may start and end between scrapes, resulting in incomplete or misleading data. By focusing only on longer-lived connections, we ensure the metrics are stable, meaningful, and better aligned with Prometheus’s time-series data model.
+We will expose metrics for the connections whose duration exceeds 5 seconds. Not exposing metrics for short connection as it can lead to lot of metrics and they are also not suitable for prometheus metrics because prometheus itself has a scrape interval of 5s, and short-lived connections may start and end between scrapes, resulting in incomplete or misleading data. By focusing only on longer-lived connections, we ensure the metrics are stable, meaningful, and better aligned with Prometheus’s time-series data model.
 
 We can have a another component in future which reports realtime information about connections like cilium hubble. 
 

pkg/controller/telemetry/accesslog.go

@@ -79,7 +79,7 @@ func (l *logInfo) withDestinationService(service *workloadapi.Service) *logInfo
 
 func OutputAccesslog(data requestMetric, conn_metrics connMetric, accesslog logInfo) {
 	// Skip output access log on connection establishment
-	if data.state == TCP_ESTABLISHED && data.duration < LONG_CONN_METRIC_THRESHOLD {
+	if data.state == TCP_ESTABLISHED && conn_metrics.totalReports == 1 {
 		return
 	}
 	logStr := buildAccesslog(data, conn_metrics, accesslog)

pkg/controller/telemetry/metric.go

@@ -38,7 +38,7 @@ import (
 
 const (
 	TCP_ESTABLISHED = uint32(1)
-	TCP_CLOSTED     = uint32(7)
+	TCP_CLOSED      = uint32(7)
 
 	connection_success = uint32(1)
 
@@ -512,7 +512,7 @@ func (m *MetricController) Run(ctx context.Context, mapOfTcpInfo *ebpf.Map) {
 				connectionLabels = m.buildConnectionMetric(&data)
 			}
 			if m.EnableAccesslog.Load() {
-				// accesslogs at interval of 5 sec during connection lifecycle and at close of connection
+				// accesslogs at interval of 5 sec during connection lifecycle if connectionMetrics is enabled and at close of connection
 				OutputAccesslog(data, tcpConns[data.conSrcDstInfo], accesslog)
 			}
 
@@ -526,7 +526,7 @@ func (m *MetricController) Run(ctx context.Context, mapOfTcpInfo *ebpf.Map) {
 			}
 			m.mutex.Unlock()
 
-			if data.state == TCP_CLOSTED {
+			if data.state == TCP_CLOSED {
 				delete(tcpConns, data.conSrcDstInfo)
 			}
 		}
@@ -848,7 +848,7 @@ func (m *MetricController) updateWorkloadMetricCache(data requestMetric, labels
 		if data.state == TCP_ESTABLISHED && metric.totalReports == 1 {
 			v.WorkloadConnOpened = v.WorkloadConnOpened + 1
 		}
-		if data.state == TCP_CLOSTED {
+		if data.state == TCP_CLOSED {
 			v.WorkloadConnClosed = v.WorkloadConnClosed + 1
 		}
 		if data.success != connection_success {
@@ -863,7 +863,7 @@ func (m *MetricController) updateWorkloadMetricCache(data requestMetric, labels
 		if data.state == TCP_ESTABLISHED && metric.totalReports == 1 {
 			newWorkloadMetricInfo.WorkloadConnOpened = 1
 		}
-		if data.state == TCP_CLOSTED {
+		if data.state == TCP_CLOSED {
 			newWorkloadMetricInfo.WorkloadConnClosed = 1
 		}
 		if data.success != connection_success {
@@ -883,7 +883,7 @@ func (m *MetricController) updateServiceMetricCache(data requestMetric, labels s
 		if data.state == TCP_ESTABLISHED && metric.totalReports == 1 {
 			v.ServiceConnOpened = v.ServiceConnOpened + 1
 		}
-		if data.state == TCP_CLOSTED {
+		if data.state == TCP_CLOSED {
 			v.ServiceConnClosed = v.ServiceConnClosed + 1
 		}
 		if data.success != connection_success {
@@ -896,7 +896,7 @@ func (m *MetricController) updateServiceMetricCache(data requestMetric, labels s
 		if data.state == TCP_ESTABLISHED && metric.totalReports == 1 {
 			newServiceMetricInfo.ServiceConnOpened = 1
 		}
-		if data.state == TCP_CLOSTED {
+		if data.state == TCP_CLOSED {
 			newServiceMetricInfo.ServiceConnClosed = 1
 		}
 		if data.success != connection_success {
@@ -923,7 +923,7 @@ func (m *MetricController) updateConnectionMetricCache(data requestMetric, connD
 		newConnectionMetricInfo.ConnTotalRetrans = float64(connData.totalRetrans)
 		m.connectionMetricCache[labels] = &newConnectionMetricInfo
 	}
-	if data.state == TCP_CLOSTED {
+	if data.state == TCP_CLOSED {
 		deleteLock.Lock()
 		deleteConnection = append(deleteConnection, &labels)
 		deleteLock.Unlock()

pkg/controller/telemetry/metric_test.go

@@ -535,7 +535,7 @@ func TestBuildConnectionMetricsToPrometheus(t *testing.T) {
 					receivedBytes: 0x0000004,
 					packetLost:    0x0000001,
 					totalRetrans:  0x0000002,
-					state:         TCP_CLOSTED,
+					state:         TCP_CLOSED,
 				},
 				labels: connectionMetricLabels{
 					reporter:                     "source",

pkg/controller/telemetry/utils.go

@@ -245,7 +245,7 @@ var (
 			Help: "The total number of TCP connections failed to a service.",
 		}, serviceLabels)
 
-	// Metrics to track the status of long lived TCP connections (duration > 30s)
+	// Metrics to track the status of long lived TCP connections
 	tcpConnectionTotalSendBytes = prometheus.NewGaugeVec(
 		prometheus.GaugeOpts{
 			Name: "kmesh_tcp_connection_sent_bytes_total",