efade2eab0
SplitBrainResolverStrategy now defaults to leader-auto-down (the in-repo LeaderAutoDowningProvider, #106, with the #132 shut-out restart on). auto-down and keep-oldest stay supported. Drilled on the docker rig, docker-env2 and the QA pair (central + site, kill and stop-and-hold) before the flip. - ClusterOptions default + validator/HOCON comments updated. - Shipped Host appsettings.Central/Site.json and every docker/ and docker-env2/ node appsettings now say leader-auto-down. The leader-auto-down overlays are kept as no-ops (drill records reference them); new docker-compose.auto-down.yml overlays keep Akka AutoDowning available for comparison drills. - Tests: default asserts leader-auto-down; new HOCON test for an unset strategy; TwoNodeClusterFixture defaults to the production posture. - Docs: CLAUDE.md, Component-ClusterInfrastructure, components/Host + Cluster, README, failover procedures, Traefik, docker + env2 READMEs; register row 70 closed. No deploy needed: DEV, QA and both rigs set the key explicitly. Claude-Session: https://claude.ai/code/session_01GT67AFKC45MBz1wPZnVbX8
95 lines
3.8 KiB
JSON
95 lines
3.8 KiB
JSON
{
|
|
"ScadaBridge": {
|
|
"Node": {
|
|
"Role": "Site",
|
|
"NodeName": "node-a",
|
|
"NodeHostname": "scadabridge-site-c-a",
|
|
"SiteId": "site-c",
|
|
"RemotingPort": 8082,
|
|
"GrpcPort": 8083,
|
|
"MetricsPort": 8084
|
|
},
|
|
"Cluster": {
|
|
"SeedNodes": [
|
|
"akka.tcp://scadabridge@scadabridge-site-c-a:8082",
|
|
"akka.tcp://scadabridge@scadabridge-site-c-b:8082"
|
|
],
|
|
"SplitBrainResolverStrategy": "leader-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
|
|
}
|
|
},
|
|
"OpcUa": {
|
|
"ApplicationUri": "urn:scadabridge-site-c-node-a:ScadaBridge-DCL",
|
|
"OwnCertificateStorePath": "/app/data/pki/own",
|
|
"TrustedPeerStorePath": "/app/data/pki/trusted",
|
|
"TrustedIssuerStorePath": "/app/data/pki/issuers",
|
|
"RejectedCertificateStorePath": "/app/data/pki/rejected"
|
|
},
|
|
"DataConnection": {
|
|
"ReconnectInterval": "00:00:05",
|
|
"TagResolutionRetryInterval": "00:00:10",
|
|
"WriteTimeout": "00:00:30",
|
|
"SeedReadTimeout": "00:00:30"
|
|
},
|
|
"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,
|
|
"_comment": "Retention uses the configured PurgeInterval delay after each purge; no wall-clock cron schedule is supported."
|
|
},
|
|
"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"
|
|
},
|
|
// arch-review remediation WP1.2: the site hot-path audit writer's SQLite file has no
|
|
// default path (mirrors LocalDb:Path above) and StartupValidator now requires it for
|
|
// Site nodes — an unset value used to fall back to a bare "auditlog.db" resolved
|
|
// relative to CWD, i.e. the container's ephemeral overlayfs, so the pending audit
|
|
// backlog was silently discarded on every recreate. On the mounted /app/data volume,
|
|
// same as LocalDb:Path, so it survives container recreate.
|
|
"AuditLog": {
|
|
"SiteWriter": {
|
|
"DatabasePath": "/app/data/auditlog.db"
|
|
}
|
|
}
|
|
}
|