mvcc/backend: add "etcd_disk_backend_defrag_duration_seconds"

Signed-off-by: Gyuho Lee <gyuhox@gmail.com>

mvcc/backend/backend.go

@@ -288,6 +288,8 @@ func (b *backend) Defrag() error {
 }
 
 func (b *backend) defrag() error {
+	now := time.Now()
+	
 	// TODO: make this non-blocking?
 	// lock batchTx to ensure nobody is using previous tx, and then
 	// close previous ongoing tx.
@@ -351,6 +353,9 @@ func (b *backend) defrag() error {
 	atomic.StoreInt64(&b.size, size)
 	atomic.StoreInt64(&b.sizeInUse, size-(int64(db.Stats().FreePageN)*int64(db.Info().PageSize)))
 
+	took := time.Since(now)
+	defragDurations.Observe(took.Seconds())
+
 	return nil
 }
 

mvcc/backend/metrics.go

@@ -28,6 +28,18 @@ var (
 		Buckets: prometheus.ExponentialBuckets(0.001, 2, 14),
 	})
 
+	defragDurations = prometheus.NewHistogram(prometheus.HistogramOpts{
+		Namespace: "etcd",
+		Subsystem: "disk",
+		Name:      "backend_defrag_duration_seconds",
+		Help:      "The latency distribution of backend defragmentation.",
+
+		// 100 MB usually takes 1 sec, so start with 10 MB of 100 ms
+		// lowest bucket start of upper bound 0.1 sec (100 ms) with factor 2
+		// highest bucket start of 0.1 sec * 2^12 == 409.6 sec
+		Buckets: prometheus.ExponentialBuckets(.01, 2, 13),
+	})
+
 	snapshotDurations = prometheus.NewHistogram(prometheus.HistogramOpts{
 		Namespace: "etcd",
 		Subsystem: "disk",
@@ -42,5 +54,6 @@ var (
 
 func init() {
 	prometheus.MustRegister(commitDurations)
+	prometheus.MustRegister(defragDurations)
 	prometheus.MustRegister(snapshotDurations)
 }