-metricsIp cmd flag (#5773)

* Added/Updated:
- Added metrics ip options for all servers;
- Fixed a bug with the selection of the binIp or ip parameter for the metrics handler;

* Fixed cmd flags

weed/command/filer.go

@@ -57,6 +57,7 @@ type FilerOptions struct {
 	disableHttp             *bool
 	cipher                  *bool
 	metricsHttpPort         *int
+	metricsHttpIp           *string
 	saveToFilerLimit        *int
 	defaultLevelDbDirectory *string
 	concurrentUploadLimitMB *int
@@ -90,6 +91,7 @@ func init() {
 	f.disableHttp = cmdFiler.Flag.Bool("disableHttp", false, "disable http request, only gRpc operations are allowed")
 	f.cipher = cmdFiler.Flag.Bool("encryptVolumeData", false, "encrypt data on volume servers")
 	f.metricsHttpPort = cmdFiler.Flag.Int("metricsPort", 0, "Prometheus metrics listen port")
+	f.metricsHttpIp = cmdFiler.Flag.String("metricsIp", "", "metrics listen ip. If empty, default to same as -ip.bind option.")
 	f.saveToFilerLimit = cmdFiler.Flag.Int("saveToFilerLimit", 0, "files smaller than this limit will be saved in filer store")
 	f.defaultLevelDbDirectory = cmdFiler.Flag.String("defaultStoreDir", ".", "if filer.toml is empty, use an embedded filer store in the directory")
 	f.concurrentUploadLimitMB = cmdFiler.Flag.Int("concurrentUploadLimitMB", 128, "limit total concurrent upload size")
@@ -178,7 +180,15 @@ func runFiler(cmd *Command, args []string) bool {
 
 	util.LoadConfiguration("security", false)
 
-	go stats_collect.StartMetricsServer(*f.bindIp, *f.metricsHttpPort)
+	switch {
+	case *f.metricsHttpIp != "":
+		// noting to do, use f.metricsHttpIp
+	case *f.bindIp != "":
+		*f.metricsHttpIp = *f.bindIp
+	case *f.ip != "":
+		*f.metricsHttpIp = *f.ip
+	}
+	go stats_collect.StartMetricsServer(*f.metricsHttpIp, *f.metricsHttpPort)
 
 	filerAddress := pb.NewServerAddress(*f.ip, *f.port, *f.portGrpc).String()
 	startDelay := time.Duration(2)

weed/command/master.go

@@ -53,6 +53,7 @@ type MasterOptions struct {
 	metricsIntervalSec *int
 	raftResumeState    *bool
 	metricsHttpPort    *int
+	metricsHttpIp      *string
 	heartbeatInterval  *time.Duration
 	electionTimeout    *time.Duration
 	raftHashicorp      *bool
@@ -77,6 +78,7 @@ func init() {
 	m.metricsAddress = cmdMaster.Flag.String("metrics.address", "", "Prometheus gateway address <host>:<port>")
 	m.metricsIntervalSec = cmdMaster.Flag.Int("metrics.intervalSeconds", 15, "Prometheus push interval in seconds")
 	m.metricsHttpPort = cmdMaster.Flag.Int("metricsPort", 0, "Prometheus metrics listen port")
+	m.metricsHttpIp = cmdMaster.Flag.String("metricsIp", "", "metrics listen ip. If empty, default to same as -ip.bind option.")
 	m.raftResumeState = cmdMaster.Flag.Bool("resumeState", false, "resume previous state on start master server")
 	m.heartbeatInterval = cmdMaster.Flag.Duration("heartbeatInterval", 300*time.Millisecond, "heartbeat interval of master servers, and will be randomly multiplied by [1, 1.25)")
 	m.electionTimeout = cmdMaster.Flag.Duration("electionTimeout", 10*time.Second, "election timeout of master servers")
@@ -121,7 +123,15 @@ func runMaster(cmd *Command, args []string) bool {
 		glog.Fatalf("volumeSizeLimitMB should be smaller than 30000")
 	}
 
-	go stats_collect.StartMetricsServer(*m.ipBind, *m.metricsHttpPort)
+	switch {
+	case *m.metricsHttpIp != "":
+		// noting to do, use m.metricsHttpIp
+	case *m.ipBind != "":
+		*m.metricsHttpIp = *m.ipBind
+	case *m.ip != "":
+		*m.metricsHttpIp = *m.ip
+	}
+	go stats_collect.StartMetricsServer(*m.metricsHttpIp, *m.metricsHttpPort)
 	startMaster(m, masterWhiteList)
 
 	return true

weed/command/s3.go

@@ -49,6 +49,7 @@ type S3Options struct {
 	tlsCACertificate          *string
 	tlsVerifyClientCert       *bool
 	metricsHttpPort           *int
+	metricsHttpIp             *string
 	allowEmptyFolder          *bool
 	allowDeleteBucketNotEmpty *bool
 	auditLogConfig            *string
@@ -75,6 +76,7 @@ func init() {
 	s3StandaloneOptions.tlsCACertificate = cmdS3.Flag.String("cacert.file", "", "path to the TLS CA certificate file")
 	s3StandaloneOptions.tlsVerifyClientCert = cmdS3.Flag.Bool("tlsVerifyClientCert", false, "whether to verify the client's certificate")
 	s3StandaloneOptions.metricsHttpPort = cmdS3.Flag.Int("metricsPort", 0, "Prometheus metrics listen port")
+	s3StandaloneOptions.metricsHttpIp = cmdS3.Flag.String("metricsIp", "", "metrics listen ip. If empty, default to same as -ip.bind option.")
 	s3StandaloneOptions.allowEmptyFolder = cmdS3.Flag.Bool("allowEmptyFolder", true, "allow empty folders")
 	s3StandaloneOptions.allowDeleteBucketNotEmpty = cmdS3.Flag.Bool("allowDeleteBucketNotEmpty", true, "allow recursive deleting all entries along with bucket")
 	s3StandaloneOptions.localFilerSocket = cmdS3.Flag.String("localFilerSocket", "", "local filer socket path")
@@ -165,7 +167,13 @@ func runS3(cmd *Command, args []string) bool {
 
 	util.LoadConfiguration("security", false)
 
-	go stats_collect.StartMetricsServer(*s3StandaloneOptions.bindIp, *s3StandaloneOptions.metricsHttpPort)
+	switch {
+	case *s3StandaloneOptions.metricsHttpIp != "":
+		// noting to do, use s3StandaloneOptions.metricsHttpIp
+	case *s3StandaloneOptions.bindIp != "":
+		*s3StandaloneOptions.metricsHttpIp = *s3StandaloneOptions.bindIp
+	}
+	go stats_collect.StartMetricsServer(*s3StandaloneOptions.metricsHttpIp, *s3StandaloneOptions.metricsHttpPort)
 
 	return s3StandaloneOptions.startS3Server()
 

weed/command/server.go

@@ -66,6 +66,7 @@ var (
 	volumeMinFreeSpacePercent = cmdServer.Flag.String("volume.minFreeSpacePercent", "1", "minimum free disk space (default to 1%). Low disk space will mark all volumes as ReadOnly (deprecated, use minFreeSpace instead).")
 	volumeMinFreeSpace        = cmdServer.Flag.String("volume.minFreeSpace", "", "min free disk space (value<=100 as percentage like 1, other as human readable bytes, like 10GiB). Low disk space will mark all volumes as ReadOnly.")
 	serverMetricsHttpPort     = cmdServer.Flag.Int("metricsPort", 0, "Prometheus metrics listen port")
+	serverMetricsHttpIp       = cmdServer.Flag.String("metricsIp", "", "metrics listen ip. If empty, default to same as -ip.bind option.")
 
 	// pulseSeconds              = cmdServer.Flag.Int("pulseSeconds", 5, "number of seconds between heartbeats")
 	isStartingMasterServer = cmdServer.Flag.Bool("master", true, "whether to start master server")
@@ -206,6 +207,10 @@ func runServer(cmd *Command, args []string) bool {
 		serverBindIp = serverIp
 	}
 
+	if *serverMetricsHttpIp == "" {
+		*serverMetricsHttpIp = *serverBindIp
+	}
+
 	// ip address
 	masterOptions.ip = serverIp
 	masterOptions.ipBind = serverBindIp
@@ -244,7 +249,7 @@ func runServer(cmd *Command, args []string) bool {
 	webdavOptions.filer = &filerAddress
 	mqBrokerOptions.filerGroup = filerOptions.filerGroup
 
-	go stats_collect.StartMetricsServer(*serverBindIp, *serverMetricsHttpPort)
+	go stats_collect.StartMetricsServer(*serverMetricsHttpIp, *serverMetricsHttpPort)
 
 	folders := strings.Split(*volumeDataFolders, ",")
 

weed/command/volume.go

@@ -65,6 +65,7 @@ type VolumeServerOptions struct {
 	pprof                     *bool
 	preStopSeconds            *int
 	metricsHttpPort           *int
+	metricsHttpIp             *string
 	// pulseSeconds          *int
 	inflightUploadDataTimeout *time.Duration
 	hasSlowRead               *bool
@@ -99,6 +100,7 @@ func init() {
 	v.concurrentDownloadLimitMB = cmdVolume.Flag.Int("concurrentDownloadLimitMB", 256, "limit total concurrent download size")
 	v.pprof = cmdVolume.Flag.Bool("pprof", false, "enable pprof http handlers. precludes --memprofile and --cpuprofile")
 	v.metricsHttpPort = cmdVolume.Flag.Int("metricsPort", 0, "Prometheus metrics listen port")
+	v.metricsHttpIp = cmdVolume.Flag.String("metricsIp", "", "metrics listen ip. If empty, default to same as -ip.bind option.")
 	v.idxFolder = cmdVolume.Flag.String("dir.idx", "", "directory to store .idx files")
 	v.inflightUploadDataTimeout = cmdVolume.Flag.Duration("inflightUploadDataTimeout", 60*time.Second, "inflight upload data wait timeout of volume servers")
 	v.hasSlowRead = cmdVolume.Flag.Bool("hasSlowRead", true, "<experimental> if true, this prevents slow reads from blocking other requests, but large file read P99 latency will increase.")
@@ -131,7 +133,15 @@ func runVolume(cmd *Command, args []string) bool {
 		grace.SetupProfiling(*v.cpuProfile, *v.memProfile)
 	}
 
-	go stats_collect.StartMetricsServer(*v.bindIp, *v.metricsHttpPort)
+	switch {
+	case *v.metricsHttpIp != "":
+		// noting to do, use v.metricsHttpIp
+	case *v.bindIp != "":
+		*v.metricsHttpIp = *v.bindIp
+	case *v.ip != "":
+		*v.metricsHttpIp = *v.ip
+	}
+	go stats_collect.StartMetricsServer(*v.metricsHttpIp, *v.metricsHttpPort)
 
 	minFreeSpaces := util.MustParseMinFreeSpace(*minFreeSpace, *minFreeSpacePercent)
 	v.masters = pb.ServerAddresses(*v.mastersString).ToAddresses()