Joseph Doherty
7fd5cb2b56
ClusterClient→gRPC migration Phase 4 (docs/plans/2026-07-22-clusterclient-to-grpc-plan.md). Phases 2/3 proved both directions on gRPC; this removes the Akka transport underneath. Deleted: - AkkaCentralTransport, AkkaSiteTransport (+ their dedicated tests) - ISiteClientFactory + DefaultSiteClientFactory; CentralCommunicationActor legacy ctor + SelectTransport (Host now builds GrpcSiteTransport and injects it) - ClusterClient creation + both ClusterClientReceptionist.RegisterService calls in AkkaHostedService; the RegisterCentralClient message + receive block - CommunicationOptions.CentralContactPoints; the CentralTransport/SiteTransport coexistence flags; the CentralTransportMode/SiteTransportKind enums gRPC is now the only site↔central transport (site→central CentralControlService via GrpcCentralTransport; central→site SiteCommandService via GrpcSiteTransport), both built unconditionally by the Host. NoOpCentralTransport is the fail-loud null-default so TestKit command-dispatch suites still construct the site actor without a wired transport; production always injects GrpcCentralTransport. Config: CentralGrpcEndpoints is now unconditional — CommunicationOptionsValidator rejects blank entries (role-agnostic), and StartupValidator requires a Site node to list >=1 endpoint (fail-fast, mirrors GrpcPsk). Rig configs moved CentralContactPoints -> CentralGrpcEndpoints (docker x6, docker-env2 x2, Host default, deploy/wonder-app-vd03). Kept Akka.Cluster.Tools (ClusterSingleton still used). Tests: build 0/0; Communication.Tests 640, Host.Tests 421 green. Removed the ClusterClient.Send per-site-routing tests (covered by the transport suites), swapped the ISiteClientFactory-based ctors to a substitute ISiteCommandTransport, converted the audit-push integration relay to an in-process bridge transport. Docs: Component-Communication/Host/StoreAndForward, components/Communication, topology-guide, grpc_streams (SUPERSEDED note), the frame-size known-issue (retired amendment), and CLAUDE.md transport decisions. Not included: the dead IntegrationCallRequest path (#32) is a separate user-owned behavioral decision — SiteEnvelope routing is transport-agnostic so it still compiles.
84 lines
3.2 KiB
JSON
84 lines
3.2 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
|
|
},
|
|
"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"
|
|
}
|
|
}
|