Skip to content

ROX-29060: Add gauge metrics for collections used in enrichment #16140

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vikin91 merged 3 commits into from
Aug 7, 2025
Merged

ROX-29060: Add gauge metrics for collections used in enrichment #16140

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bd314d6
Implement additional metrics
vikin91 Aug 6, 2025
e76d70d
Use WarnL on rate-limited logger
vikin91 Aug 6, 2025
63d3c95
Fix race discovered in integration tests
vikin91 Aug 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 33 additions & 4 deletions sensor/common/networkflow/manager/manager_impl.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -483,7 +483,34 @@ func (m *networkFlowManager) getCurrentContext() context.Context {
return m.pipelineCtx
}

func (m *networkFlowManager) updateEnrichmentCollectionsSize() {
numConnections := 0
numEndpoints := 0
concurrency.WithRLock(&m.connectionsByHostMutex, func() {
for _, hostConns := range m.connectionsByHost {
concurrency.WithLock(&hostConns.mutex, func() {
numConnections += len(hostConns.connections)
numEndpoints += len(hostConns.endpoints)
})
}
})
flowMetrics.EnrichmentCollectionsSize.WithLabelValues("connectionsInEnrichQueue", "connections").Set(float64(numConnections))
flowMetrics.EnrichmentCollectionsSize.WithLabelValues("endpointsInEnrichQueue", "endpoints").Set(float64(numEndpoints))

concurrency.WithRLock(&m.activeConnectionsMutex, func() {
flowMetrics.EnrichmentCollectionsSize.WithLabelValues("activeConnections", "connections").Set(float64(len(m.activeConnections)))
flowMetrics.EnrichmentCollectionsSize.WithLabelValues("activeEndpoints", "endpoints").Set(float64(len(m.activeEndpoints)))
})

concurrency.WithRLock(&m.lastSentStateMutex, func() {
flowMetrics.EnrichmentCollectionsSize.WithLabelValues("enrichedConnectionsLastSentState", "connections").Set(float64(len(m.enrichedConnsLastSentState)))
flowMetrics.EnrichmentCollectionsSize.WithLabelValues("enrichedEndpointsLastSentState", "endpoints").Set(float64(len(m.enrichedEndpointsLastSentState)))
flowMetrics.EnrichmentCollectionsSize.WithLabelValues("enrichedProcessesLastSentState", "processes").Set(float64(len(m.enrichedProcessesLastSentState)))
})
}

func (m *networkFlowManager) enrichAndSend() {
m.updateEnrichmentCollectionsSize()
// Takes host connections & endpoints and updates them by enriching with additional data.
// Updates m.activeEndpoints and m.activeConnections if lastSeen was reported as null by the Collector.
currentConns, currentEndpoints, currentProcesses := m.currentEnrichedConnsAndEndpoints()
Expand Down Expand Up @@ -636,8 +663,8 @@ func computeUpdatedEndpoints(current map[containerEndpointIndicator]timestamp.Mi
func computeUpdatedProcesses(current map[processListeningIndicator]timestamp.MicroTS, previous map[processListeningIndicator]timestamp.MicroTS, previousMutex *sync.RWMutex) []*storage.ProcessListeningOnPortFromSensor {
if !env.ProcessesListeningOnPort.BooleanSetting() {
if len(current) > 0 {
logging.GetRateLimitedLogger().Warn(loggingRateLimiter,
"Received process while ProcessesListeningOnPort feature is disabled. This may indicate a misconfiguration.", len(current))
logging.GetRateLimitedLogger().WarnL(loggingRateLimiter,
"Received process while ProcessesListeningOnPort feature is disabled. This may indicate a misconfiguration.")
}
return []*storage.ProcessListeningOnPortFromSensor{}
}
Expand Down Expand Up @@ -673,9 +700,11 @@ func (m *networkFlowManager) getAllHostConnections() []*hostConnections {
m.connectionsByHostMutex.RLock()
defer m.connectionsByHostMutex.RUnlock()

allHostConns := make([]*hostConnections, 0, len(m.connectionsByHost))
allHostConns := make([]*hostConnections, len(m.connectionsByHost))
i := 0
for _, hostConns := range m.connectionsByHost {
allHostConns = append(allHostConns, hostConns)
allHostConns[i] = hostConns // avoiding append() here improves the cpu time by 5-19%
i++
}
return allHostConns
}
Expand Down
9 changes: 9 additions & 0 deletions sensor/common/networkflow/metrics/metrics.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ import (

func init() {
prometheus.MustRegister(
EnrichmentCollectionsSize,

// Host Connections
NetworkConnectionInfoMessagesRcvd,
NumUpdated,
Expand Down Expand Up @@ -38,6 +40,13 @@ const (

// Metrics for network flows
var (
EnrichmentCollectionsSize = prometheus.NewGaugeVec(prometheus.GaugeOpts{
Namespace: metrics.PrometheusNamespace,
Subsystem: metrics.SensorSubsystem.String(),
Name: hostConnectionsPrefix + "collections_size_current",
Help: "Current size of given collection involved in enrichment",
}, []string{"Name", "Type"})

// A networkConnectionInfo message arrives from collector

// NetworkConnectionInfoMessagesRcvd - 1. Collector sends NetworkConnection Info messages where each contains endpoints and connections
Expand Down
Loading