Handle initial data cases where daemon was initially up but services were not

go.mod

@@ -3,7 +3,7 @@ module github.com/chia-network/chia-exporter
 go 1.21
 
 require (
-	github.com/chia-network/go-chia-libs v0.20.0
+	github.com/chia-network/go-chia-libs v0.20.1
 	github.com/chia-network/go-modules v0.0.8
 	github.com/go-sql-driver/mysql v1.8.1
 	github.com/oschwald/maxminddb-golang v1.13.1

go.sum

@@ -4,8 +4,8 @@ github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/chia-network/go-chia-libs v0.20.0 h1:rdW1Ob/hb32Pl89w4/9SkoGWVhyC+tOkeRqvPr/xuvg=
-github.com/chia-network/go-chia-libs v0.20.0/go.mod h1:npTqaFSjTdMxE7hc0LOmWJmWGqcs+IERarK5fDxXk/I=
+github.com/chia-network/go-chia-libs v0.20.1 h1:uEPrjtxot0oipTuWT63Spw9t9kj56JdhdFBS4ZgYdjc=
+github.com/chia-network/go-chia-libs v0.20.1/go.mod h1:+RMorskgxwYzPGf2gIyW0k7FGDdLrrH4X5ATrrMreb0=
 github.com/chia-network/go-modules v0.0.8 h1:VATMxehRISOhaRwPo/GL735IKWW0G7sUYH2OmBofsfE=
 github.com/chia-network/go-modules v0.0.8/go.mod h1:OdvlWftyJc3+i3QYv5cfQsiQASL7Em7fJnzdmPmj07M=
 github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
@@ -94,8 +94,9 @@ github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
-github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
+github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/subosito/gotenv v1.6.0 h1:9NlTDc1FTs4qu0DDq7AEtTPNw6SVm7uBMsUCUjABIf8=
 github.com/subosito/gotenv v1.6.0/go.mod h1:Dk4QP5c2W3ibzajGcXpNraDfq2IrhjMIvMSWPKKo0FU=
 go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=

internal/metrics/crawler.go

@@ -30,6 +30,7 @@ type CrawlerServiceMetrics struct {
 	metrics *Metrics
 
 	// General Service Metrics
+	gotVersionResponse bool
 	version *prometheus.GaugeVec
 
 	// Current network
@@ -128,6 +129,7 @@ func (s *CrawlerServiceMetrics) SetupPollingMetrics(ctx context.Context) {}
 // Disconnected clears/unregisters metrics when the connection drops
 func (s *CrawlerServiceMetrics) Disconnected() {
 	s.version.Reset()
+	s.gotVersionResponse = false
 	s.totalNodes5Days.Unregister()
 	s.reliableNodes.Unregister()
 	s.ipv4Nodes5Days.Unregister()
@@ -143,9 +145,18 @@ func (s *CrawlerServiceMetrics) Reconnected() {
 
 // ReceiveResponse handles crawler responses that are returned over the websocket
 func (s *CrawlerServiceMetrics) ReceiveResponse(resp *types.WebsocketResponse) {
+	// Sometimes, when we reconnect, or start exporter before chia is running
+	// the daemon is up before the service, and the initial request for the version
+	// doesn't make it to the service
+	// daemon doesn't queue these messages for later, they just get dropped
+	if !s.gotVersionResponse {
+		utils.LogErr(s.metrics.client.FullNodeService.GetVersion(&rpc.GetVersionOptions{}))
+	}
+
 	switch resp.Command {
 	case "get_version":
 		versionHelper(resp, s.version)
+		s.gotVersionResponse = true
 	case "get_peer_counts":
 		fallthrough
 	case "loaded_initial_peers":

internal/metrics/farmer.go

@@ -24,6 +24,7 @@ type FarmerServiceMetrics struct {
 	metrics *Metrics
 
 	// General Service Metrics
+	gotVersionResponse bool
 	version *prometheus.GaugeVec
 
 	// Connection Metrics
@@ -108,6 +109,7 @@ func (s *FarmerServiceMetrics) SetupPollingMetrics(ctx context.Context) {}
 // Disconnected clears/unregisters metrics when the connection drops
 func (s *FarmerServiceMetrics) Disconnected() {
 	s.version.Reset()
+	s.gotVersionResponse = false
 	s.connectionCount.Reset()
 	s.plotFilesize.Reset()
 	s.plotCount.Reset()
@@ -123,9 +125,18 @@ func (s *FarmerServiceMetrics) Reconnected() {
 
 // ReceiveResponse handles crawler responses that are returned over the websocket
 func (s *FarmerServiceMetrics) ReceiveResponse(resp *types.WebsocketResponse) {
+	// Sometimes, when we reconnect, or start exporter before chia is running
+	// the daemon is up before the service, and the initial request for the version
+	// doesn't make it to the service
+	// daemon doesn't queue these messages for later, they just get dropped
+	if !s.gotVersionResponse {
+		utils.LogErr(s.metrics.client.FullNodeService.GetVersion(&rpc.GetVersionOptions{}))
+	}
+
 	switch resp.Command {
 	case "get_version":
 		versionHelper(resp, s.version)
+		s.gotVersionResponse = true
 	case "get_connections":
 		s.GetConnections(resp)
 	case "new_farming_info":

internal/metrics/fullnode.go

@@ -36,7 +36,8 @@ type FullNodeServiceMetrics struct {
 	metrics *Metrics
 
 	// General Service Metrics
-	version *prometheus.GaugeVec
+	gotVersionResponse bool
+	version            *prometheus.GaugeVec
 
 	// GetBlockchainState Metrics
 	difficulty          *wrappedPrometheus.LazyGauge
@@ -187,6 +188,7 @@ func (s *FullNodeServiceMetrics) SetupPollingMetrics(ctx context.Context) {
 // Disconnected clears/unregisters metrics when the connection drops
 func (s *FullNodeServiceMetrics) Disconnected() {
 	s.version.Reset()
+	s.gotVersionResponse = false
 	s.difficulty.Unregister()
 	s.mempoolCost.Unregister()
 	s.mempoolMinFee.Reset()
@@ -228,9 +230,18 @@ func (s *FullNodeServiceMetrics) Reconnected() {
 
 // ReceiveResponse handles full node related responses that are returned over the websocket
 func (s *FullNodeServiceMetrics) ReceiveResponse(resp *types.WebsocketResponse) {
+	// Sometimes, when we reconnect, or start exporter before chia is running
+	// the daemon is up before the service, and the initial request for the version
+	// doesn't make it to the service
+	// daemon doesn't queue these messages for later, they just get dropped
+	if !s.gotVersionResponse {
+		utils.LogErr(s.metrics.client.FullNodeService.GetVersion(&rpc.GetVersionOptions{}))
+	}
+
 	switch resp.Command {
 	case "get_version":
 		versionHelper(resp, s.version)
+		s.gotVersionResponse = true
 	case "get_blockchain_state":
 		s.GetBlockchainState(resp)
 		// Ask for connection info when we get updated blockchain state
@@ -424,6 +435,7 @@ func (s *FullNodeServiceMetrics) RefreshFileSizes() {
 	cfg, err := config.GetChiaConfig()
 	if err != nil {
 		log.Errorf("Error getting chia config: %s\n", err.Error())
+		return
 	}
 	database := cfg.GetFullPath(cfg.FullNode.DatabasePath)
 	databaseWal := fmt.Sprintf("%s-wal", database)

internal/metrics/harvester.go

@@ -25,8 +25,11 @@ type HarvesterServiceMetrics struct {
 	metrics *Metrics
 
 	// General Service Metrics
+	gotVersionResponse bool
 	version *prometheus.GaugeVec
 
+	gotPlotsResponse bool
+
 	// Connection Metrics
 	connectionCount *prometheus.GaugeVec
 
@@ -124,6 +127,8 @@ func (s *HarvesterServiceMetrics) httpGetPlots() {
 // Disconnected clears/unregisters metrics when the connection drops
 func (s *HarvesterServiceMetrics) Disconnected() {
 	s.version.Reset()
+	s.gotVersionResponse = false
+	s.gotPlotsResponse = false
 	s.connectionCount.Reset()
 	s.totalPlots.Unregister()
 	s.plotFilesize.Reset()
@@ -140,15 +145,28 @@ func (s *HarvesterServiceMetrics) Reconnected() {
 
 // ReceiveResponse handles crawler responses that are returned over the websocket
 func (s *HarvesterServiceMetrics) ReceiveResponse(resp *types.WebsocketResponse) {
+	// Sometimes, when we reconnect, or start exporter before chia is running
+	// the daemon is up before the service, and the initial request for the version
+	// doesn't make it to the service
+	// daemon doesn't queue these messages for later, they just get dropped
+	if !s.gotVersionResponse {
+		utils.LogErr(s.metrics.client.FullNodeService.GetVersion(&rpc.GetVersionOptions{}))
+	}
+	if !s.gotPlotsResponse {
+		s.httpGetPlots()
+	}
+
 	switch resp.Command {
 	case "get_version":
 		versionHelper(resp, s.version)
+		s.gotVersionResponse = true
 	case "get_connections":
 		s.GetConnections(resp)
 	case "farming_info":
 		s.FarmingInfo(resp)
 	case "get_plots":
 		s.GetPlots(resp)
+		s.gotPlotsResponse = true
 	case "debug":
 		debugHelper(resp, s.debug)
 	}

internal/metrics/timelord.go

@@ -23,6 +23,7 @@ type TimelordServiceMetrics struct {
 	metrics *Metrics
 
 	// General Service Metrics
+	gotVersionResponse bool
 	version *prometheus.GaugeVec
 
 	// Timelord Metrics
@@ -62,6 +63,7 @@ func (s *TimelordServiceMetrics) SetupPollingMetrics(ctx context.Context) {}
 // Disconnected clears/unregisters metrics when the connection drops
 func (s *TimelordServiceMetrics) Disconnected() {
 	s.version.Reset()
+	s.gotVersionResponse = false
 	s.fastestTimelord.Unregister()
 	s.slowTimelord.Unregister()
 	s.estimatedIPS.Unregister()
@@ -75,10 +77,19 @@ func (s *TimelordServiceMetrics) Reconnected() {
 
 // ReceiveResponse handles crawler responses that are returned over the websocket
 func (s *TimelordServiceMetrics) ReceiveResponse(resp *types.WebsocketResponse) {
+	// Sometimes, when we reconnect, or start exporter before chia is running
+	// the daemon is up before the service, and the initial request for the version
+	// doesn't make it to the service
+	// daemon doesn't queue these messages for later, they just get dropped
+	if !s.gotVersionResponse {
+		utils.LogErr(s.metrics.client.FullNodeService.GetVersion(&rpc.GetVersionOptions{}))
+	}
+
 	//("finished_pot_challenge", "new_compact_proof", "skipping_peak", "new_peak")
 	switch resp.Command {
 	case "get_version":
 		versionHelper(resp, s.version)
+		s.gotVersionResponse = true
 	case "finished_pot":
 		s.FinishedPoT(resp)
 	case "new_compact_proof":

internal/metrics/wallet.go

@@ -25,8 +25,11 @@ type WalletServiceMetrics struct {
 	metrics *Metrics
 
 	// General Service Metrics
+	gotVersionResponse bool
 	version *prometheus.GaugeVec
 
+	gotWalletsResponse bool
+
 	// Connection Metrics
 	connectionCount *prometheus.GaugeVec
 
@@ -93,6 +96,8 @@ func (s *WalletServiceMetrics) SetupPollingMetrics(ctx context.Context) {
 // Disconnected clears/unregisters metrics when the connection drops
 func (s *WalletServiceMetrics) Disconnected() {
 	s.version.Reset()
+	s.gotVersionResponse = false
+	s.gotWalletsResponse = false
 	s.connectionCount.Reset()
 	s.walletSynced.Unregister()
 	s.confirmedBalance.Reset()
@@ -109,9 +114,21 @@ func (s *WalletServiceMetrics) Reconnected() {
 
 // ReceiveResponse handles wallet responses that are returned over the websocket
 func (s *WalletServiceMetrics) ReceiveResponse(resp *types.WebsocketResponse) {
+	// Sometimes, when we reconnect, or start exporter before chia is running
+	// the daemon is up before the service, and the initial request for the version
+	// doesn't make it to the service
+	// daemon doesn't queue these messages for later, they just get dropped
+	if !s.gotVersionResponse {
+		utils.LogErr(s.metrics.client.FullNodeService.GetVersion(&rpc.GetVersionOptions{}))
+	}
+	if !s.gotWalletsResponse {
+		utils.LogErr(s.metrics.client.WalletService.GetWallets(&rpc.GetWalletsOptions{}))
+	}
+
 	switch resp.Command {
 	case "get_version":
 		versionHelper(resp, s.version)
+		s.gotVersionResponse = true
 	case "get_connections":
 		s.GetConnections(resp)
 	case "coin_added":
@@ -124,6 +141,7 @@ func (s *WalletServiceMetrics) ReceiveResponse(resp *types.WebsocketResponse) {
 		s.GetWalletBalance(resp)
 	case "get_wallets":
 		s.GetWallets(resp)
+		s.gotWalletsResponse = true
 	case "debug":
 		debugHelper(resp, s.debug)
 	}