Files
ScadaBridge/docker/site-c-node-b/appsettings.Site.json
T
Joseph Doherty b8f91bab2d feat(cluster): enable the #33 bootstrap guard on the docker rig — live gate PASS
deploy.sh's simultaneous recreate split site pairs twice on 2026-08-01 with
the guard off (mutual InitJoinNack, each node forming its own 1-node
cluster; a per-pair coin flip compose depends_on does not prevent). Guard
enabled on all 8 rig nodes: two consecutive simultaneous-start trials (full
redeploy + full-topology compose restart) converged all four pairs
deterministically — founder self-first on every lower address, peer-first
join on every higher, zero splits. This closes the deferred issue-acceptance
live gate; the switch stays default-off everywhere else.
2026-08-02 01:04:55 -04:00

91 lines
3.6 KiB
JSON

{
"ScadaBridge": {
"Node": {
"Role": "Site",
"NodeName": "node-b",
"NodeHostname": "scadabridge-site-c-b",
"SiteId": "site-c",
"RemotingPort": 8082,
"GrpcPort": 8083,
"MetricsPort": 8084
},
"Cluster": {
"SeedNodes": [
"akka.tcp://scadabridge@scadabridge-site-c-b:8082",
"akka.tcp://scadabridge@scadabridge-site-c-a:8082"
],
"SplitBrainResolverStrategy": "auto-down",
"StableAfter": "00:00:15",
"HeartbeatInterval": "00:00:02",
"FailureDetectionThreshold": "00:00:10",
"MinNrOfMembers": 1,
"_bootstrapGuard": "Gitea #33 guard ENABLED on the docker rig (2026-08-02): deploy.sh recreates all containers simultaneously, which twice split site pairs into two 1-node clusters on 2026-08-01. Lower host:port founds self-first; the higher node TCP-probes then joins peer-first.",
"BootstrapGuard": {
"Enabled": true,
"PartnerProbeSeconds": 25,
"PartnerProbeIntervalMs": 500,
"ProbeConnectTimeoutMs": 1000
}
},
"Database": {
// Migration-only as of LocalDb Phase 2. The site config tables now live in the
// consolidated LocalDb database (LocalDb:Path). SiteDbPath is read once at boot to drain
// a pre-Phase-2 scadabridge.db, and is unused after that - keep it until this node has
// started once.
"SiteDbPath": "/app/data/scadabridge.db"
},
"DataConnection": {
"ReconnectInterval": "00:00:05",
"TagResolutionRetryInterval": "00:00:10",
"WriteTimeout": "00:00:30",
"SeedReadTimeout": "00:00:30"
},
"StoreAndForward": {
// Migration-only as of LocalDb Phase 2. The store-and-forward buffer now lives in the
// consolidated LocalDb database (LocalDb:Path) as the replicated sf_messages table.
// SqliteDbPath is read once at boot by SiteLocalDbLegacyMigrator to drain a pre-Phase-2
// file, and is unused after that - keep it until this node has started once.
"SqliteDbPath": "/app/data/store-and-forward.db"
},
"Communication": {
// DEV-ONLY control-plane preshared key — NOT a real secret. Must be
// IDENTICAL on both nodes of the pair and match the central-side entry in
// ScadaBridge__Communication__SitePsks__<siteId> (docker-compose.yml).
// Production supplies this as ${secret:SB-GRPC-PSK-<siteId>}. Without it the
// node fails StartupValidator: the gate is fail-closed, so an unset key would
// refuse every SiteStream call while the node still looked healthy.
"GrpcPsk": "dev-grpc-psk-docker-site-c",
"CentralGrpcEndpoints": [
"http://scadabridge-central-a:8083",
"http://scadabridge-central-b:8083"
],
"DeploymentTimeout": "00:02:00",
"LifecycleTimeout": "00:00:30",
"QueryTimeout": "00:00:30",
"TransportHeartbeatInterval": "00:00:05",
"TransportFailureThreshold": "00:00:15"
},
"HealthMonitoring": {
"ReportInterval": "00:00:30",
"OfflineTimeout": "00:01:00"
},
"SiteEventLog": {
"RetentionDays": 30,
"MaxStorageMb": 1024,
"PurgeScheduleCron": "0 2 * * *"
},
"Notification": {},
"Logging": {
"MinimumLevel": "Information"
}
},
// Consolidated site database (LocalDb Phase 1): OperationTracking + site_events.
// On the mounted /app/data volume so it survives container recreate - unlike the
// legacy site-tracking.db / site_events.db, which defaulted to CWD-relative paths
// outside the volume and were lost on every recreate.
// Replication is opt-in and configured separately; absent = local-only.
"LocalDb": {
"Path": "/app/data/site-localdb.db"
}
}