Enhancement: Session Error handling and caching

.gitignore

@@ -47,4 +47,10 @@
 /*.sqlite
 
 ## environment vars
-.env
+.env
+
+## docker compose file
+docker-compose.yml
+
+## MAC
+.DS_Store

README.md

@@ -23,7 +23,7 @@ To onboard the gateway server without having to dig deep, you can follow the [Qu
 Every release candidate is published to https://github.com/pokt-network/gateway-server/pkgs/container/pocket-gateway-server
 
 ## Docker Compose
-There is an all-inclusive docker-compose file available for development [docker-compose.yml](docker-compose.yml)
+There is an all-inclusive docker-compose file available for development [docker-compose.yml](docker-compose.yml.sample)
 
 ## Minimum Hardware Requirements to run
 - 1GB of RAM

cmd/gateway_server/internal/config/dot_env_config_provider.go

@@ -87,45 +87,47 @@ func (c DotEnvGlobalConfigProvider) GetAltruistRequestTimeout() time.Duration {
 func NewDotEnvConfigProvider() *DotEnvGlobalConfigProvider {
 	_ = godotenv.Load()
 
-	poktRPCTimeout, err := time.ParseDuration(getEnvVar(poktRPCTimeoutEnv))
+	poktRPCTimeout, err := time.ParseDuration(getEnvVar(poktRPCTimeoutEnv, ""))
 	if err != nil {
 		panic(fmt.Sprintf("Error parsing %s: %s", poktRPCTimeoutEnv, err))
 	}
 
-	httpServerPort, err := strconv.ParseUint(getEnvVar(httpServerPortEnv), 10, 64)
+	httpServerPort, err := strconv.ParseUint(getEnvVar(httpServerPortEnv, ""), 10, 64)
 	if err != nil {
 		panic(fmt.Sprintf("Error parsing %s: %s", httpServerPortEnv, err))
 	}
 
-	sessionCacheTTLDuration, err := time.ParseDuration(getEnvVar(sessionCacheTTLEnv))
+	sessionCacheTTLDuration, err := time.ParseDuration(getEnvVar(sessionCacheTTLEnv, ""))
 	if err != nil {
 		panic(fmt.Sprintf("Error parsing %s: %s", sessionCacheTTLDuration, err))
 	}
 
-	altruistRequestTimeoutDuration, err := time.ParseDuration(getEnvVar(altruistRequestTimeoutEnv))
+	altruistRequestTimeoutDuration, err := time.ParseDuration(getEnvVar(altruistRequestTimeoutEnv, defaultAltruistRequestTimeout.String()))
 	if err != nil {
 		// Provide a default to prevent any breaking changes with new env variable.
 		altruistRequestTimeoutDuration = defaultAltruistRequestTimeout
 	}
 
 	return &DotEnvGlobalConfigProvider{
-		poktRPCFullHost:               getEnvVar(poktRPCFullHostEnv),
+		poktRPCFullHost:               getEnvVar(poktRPCFullHostEnv, ""),
 		httpServerPort:                uint(httpServerPort),
 		poktRPCRequestTimeout:         poktRPCTimeout,
 		sessionCacheTTL:               sessionCacheTTLDuration,
-		databaseConnectionUrl:         getEnvVar(dbConnectionUrlEnv),
-		environmentStage:              global_config.EnvironmentStage(getEnvVar(environmentStageEnv)),
-		poktApplicationsEncryptionKey: getEnvVar(poktApplicationsEncryptionKeyEnv),
-		apiKey:                        getEnvVar(apiKey),
+		databaseConnectionUrl:         getEnvVar(dbConnectionUrlEnv, ""),
+		environmentStage:              global_config.EnvironmentStage(getEnvVar(environmentStageEnv, "")),
+		poktApplicationsEncryptionKey: getEnvVar(poktApplicationsEncryptionKeyEnv, ""),
+		apiKey:                        getEnvVar(apiKey, ""),
 		altruistRequestTimeout:        altruistRequestTimeoutDuration,
 	}
 }
 
 // getEnvVar retrieves the value of the environment variable with error handling.
-func getEnvVar(name string) string {
-	value, exists := os.LookupEnv(name)
-	if !exists {
-		panic(fmt.Errorf("%s not set", name))
+func getEnvVar(name string, defaultValue string) string {
+	if value, exists := os.LookupEnv(name); exists {
+		return value
 	}
-	return value
+	if defaultValue != "" {
+		return defaultValue
+	}
+	panic(fmt.Errorf("%s not set", name))
 }

cmd/gateway_server/internal/models/qos_node.go

@@ -13,4 +13,5 @@ type PublicQosNode struct {
 	IsHeathy        bool      `json:"is_heathy"`
 	IsSynced        bool      `json:"is_synced"`
 	LastKnownHeight uint64    `json:"last_known_height"`
+	P90Latency      float64   `json:"p90_latency"`
 }

cmd/gateway_server/internal/transform/qos_node.go

@@ -1,21 +1,27 @@
 package transform
 
 import (
+	"math"
 	"pokt_gateway_server/cmd/gateway_server/internal/models"
 	internal_model "pokt_gateway_server/internal/node_selector_service/models"
 )
 
 func ToPublicQosNode(node *internal_model.QosNode) *models.PublicQosNode {
+	latency := node.LatencyTracker.GetP90Latency()
+	if math.IsNaN(latency) {
+		latency = 0.0
+	}
 	return &models.PublicQosNode{
 		ServiceUrl:      node.MorseNode.ServiceUrl,
 		Chain:           node.GetChain(),
-		SessionHeight:   node.PocketSession.SessionHeader.SessionHeight,
-		AppPublicKey:    node.AppSigner.PublicKey,
+		SessionHeight:   node.MorseSession.SessionHeader.SessionHeight,
+		AppPublicKey:    node.MorseSigner.PublicKey,
 		TimeoutReason:   string(node.GetTimeoutReason()),
 		LastKnownErr:    node.GetLastKnownErrorStr(),
 		IsHeathy:        node.IsHealthy(),
 		IsSynced:        node.IsSynced(),
 		LastKnownHeight: node.GetLastKnownHeight(),
 		TimeoutUntil:    node.GetTimeoutUntil(),
+		P90Latency:      latency,
 	}
 }

cmd/gateway_server/main.go

@@ -59,8 +59,8 @@ func main() {
 		ttlcache.WithTTL[string, *session_registry.Session](gatewayConfigProvider.GetSessionCacheTTL()),
 	)
 
-	nodeCache := ttlcache.New[string, []*qos_models.QosNode](
-		ttlcache.WithTTL[string, []*qos_models.QosNode](gatewayConfigProvider.GetSessionCacheTTL()),
+	nodeCache := ttlcache.New[qos_models.SessionChainKey, []*qos_models.QosNode](
+		ttlcache.WithTTL[qos_models.SessionChainKey, []*qos_models.QosNode](gatewayConfigProvider.GetSessionCacheTTL()),
 	)
 
 	poktApplicationRegistry := apps_registry.NewCachedAppsRegistry(client, querier, gatewayConfigProvider, logger.Named("pokt_application_registry"))

docker-compose.yml.sample

@@ -0,0 +1,42 @@
+version: '3'
+
+services:
+  gateway-server:
+    build: .
+    volumes:
+      - .env:/app/.env
+    ports:
+      - "${HTTP_SERVER_PORT}:${HTTP_SERVER_PORT}"
+    env_file:
+      - ./.env
+    networks:
+      - bridged_network
+#    depends_on:
+#       - postgres
+    restart: on-failure
+    logging:
+      driver: json-file
+      options:
+        max-size: 10m
+
+# this postgres database is only to be used for testing. It should not be used in production systems
+# Leverage a production ready postgres database with HA/replicas in prod.
+#  postgres:
+#    image: postgres:latest
+#    environment:
+#      POSTGRES_DB: postgres
+#      POSTGRES_USER: myuser
+#      POSTGRES_PASSWORD: mypassword
+#    ports:
+#      - "5433:5432"
+#    volumes:
+#      - postgres_data:/var/lib/postgresql/data
+#    networks:
+#      - bridged_network
+
+volumes:
+  postgres_data:
+
+networks:
+  bridged_network:
+    driver: bridge

go.mod

@@ -29,6 +29,7 @@ require (
 	github.com/golang/protobuf v1.5.3 // indirect
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/hashicorp/go-multierror v1.1.1 // indirect
+	github.com/influxdata/tdigest v0.0.1 // indirect
 	github.com/jackc/chunkreader/v2 v2.0.1 // indirect
 	github.com/jackc/pgio v1.0.0 // indirect
 	github.com/jackc/pgpassfile v1.0.0 // indirect

go.sum

@@ -46,6 +46,7 @@ github.com/golang/protobuf v1.3.5/go.mod h1:6O5/vntMXwX2lRkT1hjjk0nAC1IDOTvTlVgj
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
 github.com/golang/protobuf v1.5.3 h1:KhyjKVUg7Usr/dYsdSqoFveMYd5ko72D+zANwlG1mmg=
 github.com/golang/protobuf v1.5.3/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
+github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
@@ -55,6 +56,8 @@ github.com/hashicorp/errwrap v1.1.0 h1:OxrOeh75EUXMY8TBjag2fzXGZ40LB6IKw45YeGUDY
 github.com/hashicorp/errwrap v1.1.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
 github.com/hashicorp/go-multierror v1.1.1 h1:H5DkEtf6CXdFp0N0Em5UCwQpXMWke8IA0+lD48awMYo=
 github.com/hashicorp/go-multierror v1.1.1/go.mod h1:iw975J/qwKPdAO1clOe2L8331t/9/fmwbPZ6JB6eMoM=
+github.com/influxdata/tdigest v0.0.1 h1:XpFptwYmnEKUqmkcDjrzffswZ3nvNeevbUSLPP/ZzIY=
+github.com/influxdata/tdigest v0.0.1/go.mod h1:Z0kXnxzbTC2qrx4NaIzYkE1k66+6oEDQTvL95hQFh5Y=
 github.com/jackc/chunkreader v1.0.0/go.mod h1:RT6O25fNZIuasFJRyZ4R/Y2BbhasbmZXF9QQ7T3kePo=
 github.com/jackc/chunkreader/v2 v2.0.0/go.mod h1:odVSm741yZoC3dpHEUXIqA9tQRhFrgOHwnPIn9lDKlk=
 github.com/jackc/chunkreader/v2 v2.0.1 h1:i+RDz65UE+mmpjTfyz0MoVTnzeYxroil2G82ki7MGG8=
@@ -227,6 +230,7 @@ golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5y
 golang.org/x/crypto v0.6.0/go.mod h1:OFC/31mSvZgRz0V1QTNCzfAI1aIRzbiufJtkMIlEp58=
 golang.org/x/crypto v0.17.0 h1:r8bRNjWL3GshPW3gkd+RpvzWrZAwPS49OmTGZ/uhM4k=
 golang.org/x/crypto v0.17.0/go.mod h1:gCAAfMLgwOJRpTjQ2zCCt2OcSfYMTeZVSRtQlPC7Nq4=
+golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
 golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa h1:FRnLl4eNAQl8hwxVVC17teOw8kdjVDVAiFMtgUdTSRQ=
 golang.org/x/exp v0.0.0-20231110203233-9a3e6036ecaa/go.mod h1:zk2irFbV9DP96SEBUUAy67IdHUaZuSnrz1n472HUCLE=
 golang.org/x/lint v0.0.0-20190930215403-16217165b5de/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
@@ -279,6 +283,7 @@ golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
 golang.org/x/text v0.14.0 h1:ScX5w1eTa3QqT8oi6+ziP7dTV1S2+ALU0bI+0zXKWiQ=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
+golang.org/x/tools v0.0.0-20180525024113-a5b4c53f6e8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
 golang.org/x/tools v0.0.0-20190425163242-31fd60d6bfdc/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
@@ -297,8 +302,10 @@ golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8T
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+gonum.org/v1/gonum v0.0.0-20181121035319-3f7ecaa7e8ca/go.mod h1:Y+Yx5eoAFn32cQvJDxZx5Dpnq+c3wtXuadVZAcxbbBo=
 gonum.org/v1/gonum v0.15.0 h1:2lYxjRbTYyxkJxlhC+LvJIx3SsANPdRybu1tGj9/OrQ=
 gonum.org/v1/gonum v0.15.0/go.mod h1:xzZVBJBtS+Mz4q0Yl2LJTk+OxOg4jiXZ7qBoM0uISGo=
+gonum.org/v1/netlib v0.0.0-20181029234149-ec6d1f5cefe6/go.mod h1:wa6Ws7BG/ESfp6dHfk7C6KdzKA7wR7u/rKwOGE66zvw=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
 google.golang.org/protobuf v1.31.0 h1:g0LDEJHgrBl9N9r17Ru3sqWhkIx2NB67okBHPwC7hs8=

internal/node_selector_service/checks/async_relay_handler.go

@@ -26,7 +26,7 @@ func SendRelaysAsync(relayer pokt_v0.PocketRelayer, nodes []*models.QosNode, pay
 			Payload:            &relayer_models.Payload{Data: payload, Method: method},
 			Chain:              node.GetChain(),
 			SelectedNodePubKey: node.GetPublicKey(),
-			Session:            node.PocketSession,
+			Session:            node.MorseSession,
 		})
 		relayResponses <- &nodeRelayResponse{
 			Node:  node,

internal/node_selector_service/checks/error_handler.go

@@ -15,18 +15,23 @@ const timeoutErrorPenalty = time.Second * 15
 // 24 hours is analogous to indefinite
 const kickOutSessionPenalty = time.Hour * 24
 
-const (
-	errPocketInvalidServicerMsg       = "failed to find correct servicer PK"
-	errPocketInvalidBlockHeightMsg    = "the block height passed is invalid"
-	errPocketRequestTimeoutMsg        = "request timeout"
-	errPocketOverServiceMsg           = "the max number of relays serviced for this node is exceeded"
-	errPocketMaximumEvidenceSealedMsg = "the evidence is sealed, either max relays reached or claim already submitted"
+var (
+	errsKickSession = []string{"failed to find correct servicer PK", "the max number of relays serviced for this node is exceeded", "the evidence is sealed, either max relays reached or claim already submitted"}
+	errsTimeout     = []string{"connection refused", "the request block height is out of sync with the current block height", "no route to host", "unexpected EOF", "i/o timeout", "tls: failed to verify certificate", "no such host", "the block height passed is invalid", "request timeout"}
 )
 
-const (
-	errHttpSSLExpired    = "tls: failed to verify certificate"
-	errHttpNoSuchHostMsg = "no such host"
-)
+func doesErrorContains(errsSubString []string, err error) bool {
+	if err == nil {
+		return false
+	}
+	errStr := err.Error()
+	for _, errSubString := range errsSubString {
+		if strings.Contains(errStr, errSubString) {
+			return true
+		}
+	}
+	return false
+}
 
 // isKickableSessionErr - determines if a node should be kicked from a session to send relays
 func isKickableSessionErr(err error) bool {
@@ -36,23 +41,22 @@ func isKickableSessionErr(err error) bool {
 	}
 	// Fallback in the event the error is not parsed correctly due to node operator configurations / custom clients, resort to a simple string check
 	// node runner cannot serve with expired ssl
-	if err != nil && (strings.Contains(err.Error(), errHttpSSLExpired) || strings.Contains(err.Error(), errPocketOverServiceMsg) || strings.Contains(err.Error(), errPocketMaximumEvidenceSealedMsg) || strings.Contains(err.Error(), errPocketInvalidServicerMsg)) {
-		return true
-	}
-	return false
+	return doesErrorContains(errsKickSession, err)
 }
 
 func isTimeoutError(err error) bool {
 	// If Invalid block height, pocket  is not caught up to latest session
 	if err == relayer_models.ErrPocketCoreInvalidBlockHeight {
 		return true
 	}
+
+	// Check if pocket error returns 500
 	pocketError, ok := err.(relayer_models.PocketRPCError)
-	if ok {
-		return pocketError.HttpCode >= 500
+	if ok && pocketError.HttpCode >= 500 {
+		return true
 	}
 	// Fallback in the event the error is not parsed correctly due to node operator configurations / custom clients, resort to a simple string check
-	return err == fasthttp.ErrTimeout || err == fasthttp.ErrDialTimeout || err == fasthttp.ErrTLSHandshakeTimeout || err != nil && (strings.Contains(err.Error(), errHttpNoSuchHostMsg) || strings.Contains(err.Error(), errPocketRequestTimeoutMsg) || strings.Contains(err.Error(), errPocketInvalidBlockHeightMsg))
+	return err == fasthttp.ErrConnectionClosed || err == fasthttp.ErrTimeout || err == fasthttp.ErrDialTimeout || err == fasthttp.ErrTLSHandshakeTimeout || doesErrorContains(errsTimeout, err)
 }
 
 // DefaultPunishNode generic punisher for whenever a node returns an error independent of a specific check