From a380ad8bd2329de54386f4176ff8a72c498fed2c Mon Sep 17 00:00:00 2001
From: Kristoffer Dalby <kristoffer@tailscale.com>
Date: Wed, 5 Nov 2025 15:38:42 +0100
Subject: [PATCH] mapper: add generation metrics

Signed-off-by: Kristoffer Dalby <kristoffer@tailscale.com>
---
 hscontrol/mapper/batcher.go | 31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/hscontrol/mapper/batcher.go b/hscontrol/mapper/batcher.go
index f1bec009..e808df7e 100644
--- a/hscontrol/mapper/batcher.go
+++ b/hscontrol/mapper/batcher.go
@@ -8,12 +8,22 @@ import (
 	"github.com/juanfont/headscale/hscontrol/state"
 	"github.com/juanfont/headscale/hscontrol/types"
 	"github.com/juanfont/headscale/hscontrol/types/change"
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promauto"
 	"github.com/puzpuzpuz/xsync/v4"
 	"github.com/rs/zerolog/log"
 	"tailscale.com/tailcfg"
 	"tailscale.com/types/ptr"
 )
 
+var (
+	mapResponseGenerated = promauto.NewCounterVec(prometheus.CounterOpts{
+		Namespace: "headscale",
+		Name:      "mapresponse_generated_total",
+		Help:      "total count of mapresponses generated by response type and change type",
+	}, []string{"response_type", "change_type"})
+)
+
 type batcherFunc func(cfg *types.Config, state *state.State) Batcher
 
 // Batcher defines the common interface for all batcher implementations.
@@ -75,21 +85,32 @@ func generateMapResponse(nodeID types.NodeID, version tailcfg.CapabilityVersion,
 	}
 
 	var (
-		mapResp *tailcfg.MapResponse
-		err     error
+		mapResp      *tailcfg.MapResponse
+		err          error
+		responseType string
 	)
 
+	// Record metric when function exits
+	defer func() {
+		if err == nil && mapResp != nil && responseType != "" {
+			mapResponseGenerated.WithLabelValues(responseType, c.Change.String()).Inc()
+		}
+	}()
+
 	switch c.Change {
 	case change.DERP:
+		responseType = "derp"
 		mapResp, err = mapper.derpMapResponse(nodeID)
 
 	case change.NodeCameOnline, change.NodeWentOffline:
 		if c.IsSubnetRouter {
 			// TODO(kradalby): This can potentially be a peer update of the old and new subnet router.
+			responseType = "full"
 			mapResp, err = mapper.fullMapResponse(nodeID, version)
 		} else {
 			// Trust the change type for online/offline status to avoid race conditions
 			// between NodeStore updates and change processing
+			responseType = "patch"
 			onlineStatus := c.Change == change.NodeCameOnline
 
 			mapResp, err = mapper.peerChangedPatchResponse(nodeID, []*tailcfg.PeerChange{
@@ -105,21 +126,26 @@ func generateMapResponse(nodeID types.NodeID, version tailcfg.CapabilityVersion,
 		// to ensure the node sees changes to its own properties (e.g., hostname/DNS name changes)
 		// without losing its view of peer status during rapid reconnection cycles
 		if c.IsSelfUpdate(nodeID) {
+			responseType = "self"
 			mapResp, err = mapper.selfMapResponse(nodeID, version)
 		} else {
+			responseType = "change"
 			mapResp, err = mapper.peerChangeResponse(nodeID, version, c.NodeID)
 		}
 
 	case change.NodeRemove:
+		responseType = "remove"
 		mapResp, err = mapper.peerRemovedResponse(nodeID, c.NodeID)
 
 	case change.NodeKeyExpiry:
 		// If the node is the one whose key is expiring, we send a "full" self update
 		// as nodes will ignore patch updates about themselves (?).
 		if c.IsSelfUpdate(nodeID) {
+			responseType = "self"
 			mapResp, err = mapper.selfMapResponse(nodeID, version)
 			// mapResp, err = mapper.fullMapResponse(nodeID, version)
 		} else {
+			responseType = "patch"
 			mapResp, err = mapper.peerChangedPatchResponse(nodeID, []*tailcfg.PeerChange{
 				{
 					NodeID:    c.NodeID.NodeID(),
@@ -155,6 +181,7 @@ func generateMapResponse(nodeID types.NodeID, version tailcfg.CapabilityVersion,
 	default:
 		// The following will always hit this:
 		// change.Full, change.Policy
+		responseType = "full"
 		mapResp, err = mapper.fullMapResponse(nodeID, version)
 	}