prometheus: Add mgmt_pgraph_start_time_seconds metric

Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>

docs/prometheus.md

@@ -31,6 +31,7 @@ Here is a list of the metrics we provide:
 - `mgmt_checkapply_total`: The number of CheckApply's that mgmt has run
 - `mgmt_failures_total`: The number of resources that have failed
 - `mgmt_failures_current`: The number of resources that have failed
+- `mgmt_graph_start_time_seconds`: Start time of the current graph since unix epoch in seconds
 
 For each metric, you will get some extra labels:
 

lib/main.go

@@ -480,6 +480,12 @@ func (obj *Main) Run() error {
 					log.Printf("Graphviz: Successfully generated graph!")
 				}
 			}
+
+			// Call this here because at this point the graph does not
+			// know anything about the prometheus instance.
+			if err := prom.UpdatePgraphStartTime(); err != nil {
+				log.Printf("Main: Prometheus.UpdatePgraphStartTime() errored: %v", err)
+			}
 			// G.Start(...) needs to be synchronous or wait,
 			// because if half of the nodes are started and
 			// some are not ready yet and the EtcdWatch

pgraph/pgraph.go

@@ -24,6 +24,7 @@ import (
 	"sync"
 
 	"github.com/purpleidea/mgmt/event"
+	"github.com/purpleidea/mgmt/prometheus"
 	"github.com/purpleidea/mgmt/resources"
 
 	errwrap "github.com/pkg/errors"
@@ -58,6 +59,8 @@ type Graph struct {
 	state     graphState
 	mutex     *sync.Mutex // used when modifying graph State variable
 	wg        *sync.WaitGroup
+
+	prometheus *prometheus.Prometheus // the prometheus instance
 }
 
 // Vertex is the primary vertex struct in this library.
@@ -119,6 +122,8 @@ func (g *Graph) Copy() *Graph {
 		state:     g.state,
 		mutex:     g.mutex,
 		wg:        g.wg,
+
+		prometheus: g.prometheus,
 	}
 	for k, v := range g.Adjacency {
 		newGraph.Adjacency[k] = v // copy
@@ -645,6 +650,9 @@ func (g *Graph) GraphMetas() []*resources.MetaParams {
 
 // AssociateData associates some data with the object in the graph in question.
 func (g *Graph) AssociateData(data *resources.Data) {
+	// prometheus needs to be associated to this graph as well
+	g.prometheus = data.Prometheus
+
 	for k := range g.Adjacency {
 		k.Res.AssociateData(data)
 	}

prometheus/prometheus.go

@@ -37,6 +37,7 @@ type Prometheus struct {
 	Listen string // the listen specification for the net/http server
 
 	checkApplyTotal        *prometheus.CounterVec // total of CheckApplies that have been triggered
+	pgraphStartTimeSeconds prometheus.Gauge       // process start time in seconds since unix epoch
 
 }
 
@@ -59,6 +60,14 @@ func (obj *Prometheus) Init() error {
 	)
 	prometheus.MustRegister(obj.checkApplyTotal)
 
+	obj.pgraphStartTimeSeconds = prometheus.NewGauge(
+		prometheus.GaugeOpts{
+			Name: "mgmt_graph_start_time_seconds",
+			Help: "Start time of the current graph since unix epoch in seconds.",
+		},
+	)
+	prometheus.MustRegister(obj.pgraphStartTimeSeconds)
+
 	return nil
 }
 
@@ -88,3 +97,13 @@ func (obj *Prometheus) UpdateCheckApplyTotal(kind string, apply, eventful, error
 	metric.Inc()
 	return nil
 }
+
+// UpdatePgraphStartTime updates the mgmt_graph_start_time_seconds metric
+// to the current timestamp.
+func (obj *Prometheus) UpdatePgraphStartTime() error {
+	if obj == nil {
+		return nil // happens when mgmt is launched without --prometheus
+	}
+	obj.pgraphStartTimeSeconds.SetToCurrentTime()
+	return nil
+}

test/shell/prometheus-3.sh

@@ -14,6 +14,9 @@ curl 127.0.0.1:9233/metrics | grep '^mgmt_checkapply_total{apply="true",errorful
 # One CheckApply for a File ; in noop mode.
 curl 127.0.0.1:9233/metrics | grep '^mgmt_checkapply_total{apply="false",errorful="false",eventful="true",kind="File"} 1$'
 
+# Check mgmt_graph_start_time_seconds
+curl 127.0.0.1:9233/metrics | grep "^mgmt_graph_start_time_seconds [1-9]\+"
+
 killall -SIGINT mgmt	# send ^C to exit mgmt
 wait $pid	# get exit status
 exit $?