Joseph Doherty
103f2f1931
The row read 'central nodes expose no Prometheus endpoint'. That is not quite
what was wrong, and the difference matters. Central already maps /metrics
(Program.cs central branch) and telemetry is registered for both roles through
the shared BindSharedOptions, so the endpoint rides endpoint routing and has
always been served on central's web port (:5000 on the rig, anonymous — there
is no FallbackPolicy). What central lacked was the site branch's dedicated
MetricsPort, which is the port the established live-scrape recipe probes:
docker exec <node> bash -c 'exec 3<>/dev/tcp/localhost/8084 ...'
So a probe of central on 8084 failed and central-only series (KPI/outbox
counters, the bundle-import session gauge + its new rejection counter,
alarm-cache gauges) read as unscrapeable while they were in fact being
exported on a different port.
Central now binds a dedicated HTTP/1.1 listener on ScadaBridge:Node:MetricsPort,
so one probe recipe covers all eight rig nodes. HTTP/1.1-capable because a
standard Prometheus scraper cannot negotiate h2c, which is why this cannot
share the gRPC port.
Read as a PRESENCE check, not GetValue's defaulted read. NodeOptions defaults
MetricsPort to 8084, so a defaulted read would make every existing central node
start binding a new port on upgrade — and a port already in use is a hard boot
failure, not a degraded one. Central gains the listener only where an operator
asked for it; site nodes are unchanged and still bind theirs unconditionally.
The bind is also skipped when the port would collide with the gRPC port or an
ASPNETCORE_URLS port, since Kestrel throws on a duplicate ListenAnyIP and
/metrics is reachable on those ports anyway.
Config only — no host port mapping added, because the probe runs inside the
container. Applied to both docker/ centrals and both docker-env2/ centrals.
FILE EDITS ONLY: no docker command was run, and deploy.sh was not invoked.
90 lines
3.2 KiB
JSON
90 lines
3.2 KiB
JSON
{
|
|
"ScadaBridge": {
|
|
"Node": {
|
|
"Role": "Central",
|
|
"NodeName": "central-a",
|
|
"NodeHostname": "scadabridge-env2-central-a",
|
|
"RemotingPort": 8081,
|
|
"_metricsPort": "Register row 56 — mirrors docker/central-node-a. Dedicated HTTP/1.1 Prometheus scrape listener; central binds it only when this key is present. In-container port only, no host mapping.",
|
|
"MetricsPort": 8084
|
|
},
|
|
"Cluster": {
|
|
"SeedNodes": [
|
|
"akka.tcp://scadabridge@scadabridge-env2-central-a:8081",
|
|
"akka.tcp://scadabridge@scadabridge-env2-central-b:8081"
|
|
],
|
|
"SplitBrainResolverStrategy": "auto-down",
|
|
"StableAfter": "00:00:15",
|
|
"HeartbeatInterval": "00:00:02",
|
|
"FailureDetectionThreshold": "00:00:10",
|
|
"MinNrOfMembers": 1
|
|
},
|
|
"Database": {
|
|
"ConfigurationDb": "Server=scadabridge-mssql,1433;Database=ScadaBridgeConfig2;User Id=scadabridge_app;Password=ScadaBridge_Dev1#;TrustServerCertificate=true",
|
|
"MachineDataDb": "Server=scadabridge-mssql,1433;Database=ScadaBridgeMachineData2;User Id=scadabridge_app;Password=ScadaBridge_Dev1#;TrustServerCertificate=true"
|
|
},
|
|
"Security": {
|
|
"Ldap": {
|
|
"Server": "10.100.0.35",
|
|
"Port": 3893,
|
|
"Transport": "None",
|
|
"AllowInsecure": true,
|
|
"SearchBase": "dc=zb,dc=local",
|
|
"ServiceAccountDn": "cn=serviceaccount,dc=zb,dc=local",
|
|
"ServiceAccountPassword": "serviceaccount123"
|
|
},
|
|
"JwtSigningKey": "scadabridge-env2-dev-jwt-signing-key-must-be-at-least-32-characters-long",
|
|
"JwtExpiryMinutes": 15,
|
|
"IdleTimeoutMinutes": 30,
|
|
"RequireHttpsCookie": false,
|
|
"CookieName": "ZB.MOM.WW.ScadaBridge.Auth.env2",
|
|
"ForwardedHeaders": {
|
|
"_comment": "Traefik fronts this node on the external scadabridge-net docker network. Trust X-Forwarded-For from the docker bridge address pool so LoginThrottle keys on the real client IP (arch-review R2 N2). Narrow to the Traefik container IP if the network is pinned.",
|
|
"Enabled": true,
|
|
"KnownNetworks": [ "172.16.0.0/12" ]
|
|
}
|
|
},
|
|
"Communication": {
|
|
"DeploymentTimeout": "00:02:00",
|
|
"LifecycleTimeout": "00:00:30",
|
|
"QueryTimeout": "00:00:30",
|
|
"TransportHeartbeatInterval": "00:00:05",
|
|
"TransportFailureThreshold": "00:00:15",
|
|
"CentralFetchBaseUrl": "http://scadabridge-env2-traefik"
|
|
},
|
|
"ManagementService": {
|
|
"CommandTimeout": "00:00:30",
|
|
"LongRunningCommandTimeout": "00:05:00"
|
|
},
|
|
"HealthMonitoring": {
|
|
"ReportInterval": "00:00:30",
|
|
"OfflineTimeout": "00:01:00"
|
|
},
|
|
"InboundApi": {
|
|
"DefaultMethodTimeout": "00:00:30"
|
|
},
|
|
"Notification": {
|
|
"SmtpServer": "scadabridge-smtp",
|
|
"SmtpPort": 1025,
|
|
"AuthMode": "None",
|
|
"FromAddress": "scada-notifications-env2@company.com"
|
|
},
|
|
"NotificationOutbox": {
|
|
"DispatchInterval": "00:00:05",
|
|
"DispatchBatchSize": 1000
|
|
},
|
|
"KpiHistory": {
|
|
"SampleInterval": "00:01:00",
|
|
"RetentionDays": 90,
|
|
"PurgeInterval": "1.00:00:00",
|
|
"DefaultMaxSeriesPoints": 200
|
|
},
|
|
"Transport": {
|
|
"SourceEnvironment": "docker-cluster-env2"
|
|
},
|
|
"Logging": {
|
|
"MinimumLevel": "Information"
|
|
}
|
|
}
|
|
}
|