feat(server): make the RetryInterval of PeerServer tunable

For tests and other environments it would be nice to be able to tune how
long to sleep between retries.

config/config.go

@@ -64,6 +64,7 @@ type Config struct {
 	MaxClusterSize   int      `toml:"max_cluster_size" env:"ETCD_MAX_CLUSTER_SIZE"`
 	MaxResultBuffer  int      `toml:"max_result_buffer" env:"ETCD_MAX_RESULT_BUFFER"`
 	MaxRetryAttempts int      `toml:"max_retry_attempts" env:"ETCD_MAX_RETRY_ATTEMPTS"`
+	RetryInterval    float64  `toml:"retry_interval" env:"ETCD_RETRY_INTERVAL"`
 	Name             string   `toml:"name" env:"ETCD_NAME"`
 	Snapshot         bool     `toml:"snapshot" env:"ETCD_SNAPSHOT"`
 	SnapshotCount    int      `toml:"snapshot_count" env:"ETCD_SNAPSHOTCOUNT"`
@@ -93,6 +94,7 @@ func New() *Config {
 	c.MaxClusterSize = 9
 	c.MaxResultBuffer = 1024
 	c.MaxRetryAttempts = 3
+	c.RetryInterval = 10.0
 	c.Snapshot = true
 	c.SnapshotCount = 10000
 	c.Peer.Addr = "127.0.0.1:7001"
@@ -282,6 +284,7 @@ func (c *Config) LoadFlags(arguments []string) error {
 	f.StringVar(&c.DataDir, "data-dir", c.DataDir, "")
 	f.IntVar(&c.MaxResultBuffer, "max-result-buffer", c.MaxResultBuffer, "")
 	f.IntVar(&c.MaxRetryAttempts, "max-retry-attempts", c.MaxRetryAttempts, "")
+	f.Float64Var(&c.RetryInterval, "retry-interval", c.RetryInterval, "")
 	f.IntVar(&c.MaxClusterSize, "max-cluster-size", c.MaxClusterSize, "")
 	f.IntVar(&c.Peer.HeartbeatTimeout, "peer-heartbeat-timeout", c.Peer.HeartbeatTimeout, "")
 	f.IntVar(&c.Peer.ElectionTimeout, "peer-election-timeout", c.Peer.ElectionTimeout, "")

etcd.go

@@ -122,6 +122,7 @@ func main() {
 		SnapshotCount:  config.SnapshotCount,
 		MaxClusterSize: config.MaxClusterSize,
 		RetryTimes:     config.MaxRetryAttempts,
+		RetryInterval:  config.RetryInterval,
 	}
 	ps := server.NewPeerServer(psConfig, registry, store, &mb, followersStats, serverStats)
 

server/peer_server.go

@@ -20,17 +20,16 @@ import (
 	"github.com/coreos/etcd/store"
 )
 
-const retryInterval = 10
-
 const ThresholdMonitorTimeout = 5 * time.Second
 
 type PeerServerConfig struct {
-	Name		string
+	Name           string
-	Scheme		string
+	Scheme         string
-	URL		string
+	URL            string
-	SnapshotCount	int
+	SnapshotCount  int
-	MaxClusterSize	int
+	MaxClusterSize int
-	RetryTimes	int
+	RetryTimes     int
+	RetryInterval  float64
 }
 
 type PeerServer struct {
@@ -209,8 +208,8 @@ func (s *PeerServer) startAsFollower(cluster []string) {
 		if ok {
 			return
 		}
-		log.Warnf("Unable to join the cluster using any of the peers %v. Retrying in %d seconds", cluster, retryInterval)
+		log.Warnf("Unable to join the cluster using any of the peers %v. Retrying in %.1f seconds", cluster, s.Config.RetryInterval)
-		time.Sleep(time.Second * retryInterval)
+		time.Sleep(time.Second * time.Duration(s.Config.RetryInterval))
 	}
 
 	log.Fatalf("Cannot join the cluster via given peers after %x retries", s.Config.RetryTimes)

server/usage.go

@@ -52,6 +52,7 @@ Peer Communication Options:
 Other Options:
   -max-result-buffer   Max size of the result buffer.
   -max-retry-attempts  Number of times a node will try to join a cluster.
+  -retry-interval      Seconds to wait between cluster join retry attempts.
   -max-cluster-size    Maximum number of nodes in the cluster.
   -snapshot=false      Disable log snapshots
   -snapshot-count      Number of transactions before issuing a snapshot.