add README for metrics (#1906)

metrics/README.md

@@ -0,0 +1,43 @@
+# Description
+
+This package configures Prometheus metrics for the node.
+
+# Technical Details
+
+We use a trick to combine our metrics with Geth ones.
+
+The `NewMetricsServer()` function in [`metrics.go`](./metrics.go) calls our own `Handler()` function which in turn calls two handlers:
+
+* `promhttp.HandlerFor()` - Our own custom metrics from this package.
+* `gethprom.Handler(reg)` - Geth metrics defined in [`metrics`](https://github.com/ethereum/go-ethereum/tree/master/metrics)
+
+By calling both we can extend existing metrics.
+
+# Metrics
+
+We add a few extra metrics on top of the normal Geth ones in [`node/metrics.go`](./node/metrics.go):
+
+* `p2p_peers_count` - Current numbers of peers split by name.
+* `p2p_peers_absolute` - Absolute number of connected peers.
+* `p2p_peers_max` - Maximum number of peers that can connect.
+
+The `p2p_peers_count` metrics includes 3 labels:
+
+* `type` - Set to `StatusIM` for mobile and `Statusd` for daemon.
+* `version` - Version of `status-go`, always with the `v` prefix.
+* `platform` - Host platform, like `android-arm64` or `darwin-arm64`
+
+The way this data is acquired is using node names, which look like this:
+```
+StatusIM/vrelease-0.30.1-beta.2/android-arm/go1.11.5
+Statusd/v0.34.0-beta.3/linux-amd64/go1.13.1
+Geth/v1.9.9-stable-5aa131ca/linux-amd64/go1.13.3
+```
+This 4 segment format is standard for Ethereum as you can see on https://ethstats.net/.
+
+We parse the names using `labelsFromNodeName()` from [`node/metrics.go`](./node/metrics.go).
+
+# Links
+
+* https://github.com/status-im/infra-misc/issues/26
+* https://github.com/status-im/status-go/pull/1648

metrics/node/metrics.go

@@ -15,10 +15,6 @@ var (
 		Name: "p2p_peers_count",
 		Help: "Current numbers of peers split by name.",
 	}, []string{"type", "version", "platform"})
-	nodePeersChanges = prom.NewGauge(prom.GaugeOpts{
-		Name: "p2p_peers_changes",
-		Help: "Current changes to connected peers.",
-	})
 	nodePeersAbsolute = prom.NewGauge(prom.GaugeOpts{
 		Name: "p2p_peers_absolute",
 		Help: "Absolute number of connected peers.",
@@ -31,7 +27,6 @@ var (
 
 func init() {
 	prom.MustRegister(nodePeersGauge)
-	prom.MustRegister(nodePeersChanges)
 	prom.MustRegister(nodePeersAbsolute)
 	prom.MustRegister(nodeMaxPeersGauge)
 }
@@ -43,25 +38,12 @@ func updateNodeMetrics(node *node.Node, evType p2p.PeerEventType) error {
 	}
 
 	calculatePeerCounts(server)
-
+	nodePeersAbsolute.Set(float64(server.PeerCount()))
-	change, err := computeMetrics(server, evType)
+	nodeMaxPeersGauge.Set(float64(server.MaxPeers))
-	if err != nil {
-		return err
-	}
-
-	nodePeersChanges.Add(change.Counter)
-	nodePeersAbsolute.Set(change.Absolute)
-	nodeMaxPeersGauge.Set(change.Max)
 
 	return nil
 }
 
-type peersChange struct {
-	Counter  float64
-	Absolute float64
-	Max      float64
-}
-
 func labelsFromNodeName(name string) (prom.Labels, error) {
 	tokens := strings.Split(name, "/")
 	if len(tokens) == 4 {
@@ -95,16 +77,3 @@ func calculatePeerCounts(server *p2p.Server) {
 		nodePeersGauge.With(labels).Inc()
 	}
 }
-
-func computeMetrics(server *p2p.Server, evType p2p.PeerEventType) (result peersChange, err error) {
-	switch evType {
-	case p2p.PeerEventTypeAdd:
-		result.Counter = 1
-	case p2p.PeerEventTypeDrop:
-		result.Counter = -1
-	}
-
-	result.Absolute = float64(server.PeerCount())
-	result.Max = float64(server.MaxPeers)
-	return
-}

metrics/node/metrics_test.go

@@ -43,40 +43,3 @@ func TestParsingLabelsFromNodeName(t *testing.T) {
 			"version":  "unknown",
 		})
 }
-
-func TestUpdateNodeMetricsPeersCounter(t *testing.T) {
-	var err error
-
-	n, err := node.New(&node.Config{
-		P2P: p2p.Config{
-			MaxPeers: 10,
-		},
-		NoUSB: true,
-	})
-	require.NoError(t, err)
-	require.NoError(t, n.Start())
-	defer func() { require.NoError(t, n.Stop()) }()
-	server := n.Server()
-
-	change, err := computeMetrics(server, p2p.PeerEventTypeAdd)
-	require.NoError(t, err)
-	require.Equal(t, float64(1), change.Counter)
-	require.Equal(t, float64(10), change.Max)
-
-	// skip other events
-	change, err = computeMetrics(server, p2p.PeerEventTypeMsgRecv)
-	require.NoError(t, err)
-	require.Equal(t, float64(0), change.Counter)
-	change, err = computeMetrics(server, p2p.PeerEventTypeMsgSend)
-	require.NoError(t, err)
-	require.Equal(t, float64(0), change.Counter)
-
-	change, err = computeMetrics(server, p2p.PeerEventTypeDrop)
-	require.NoError(t, err)
-	require.Equal(t, float64(-1), change.Counter)
-
-	server.MaxPeers = 20
-	change, err = computeMetrics(server, p2p.PeerEventTypeDrop)
-	require.NoError(t, err)
-	require.Equal(t, float64(20), change.Max)
-}