Phase 3B: Site I/O & Observability — Communication, DCL, Script/Alarm actors, Health, Event Logging

Communication Layer (WP-1–5):
- 8 message patterns with correlation IDs, per-pattern timeouts
- Central/Site communication actors, transport heartbeat config
- Connection failure handling (no central buffering, debug streams killed)

Data Connection Layer (WP-6–14, WP-34):
- Connection actor with Become/Stash lifecycle (Connecting/Connected/Reconnecting)
- OPC UA + LmxProxy adapters behind IDataConnection
- Auto-reconnect, bad quality propagation, transparent re-subscribe
- Write-back, tag path resolution with retry, health reporting
- Protocol extensibility via DataConnectionFactory

Site Runtime (WP-15–25, WP-32–33):
- ScriptActor/ScriptExecutionActor (triggers, concurrent execution, blocking I/O dispatcher)
- AlarmActor/AlarmExecutionActor (ValueMatch/RangeViolation/RateOfChange, in-memory state)
- SharedScriptLibrary (inline execution), ScriptRuntimeContext (API)
- ScriptCompilationService (Roslyn, forbidden API enforcement, execution timeout)
- Recursion limit (default 10), call direction enforcement
- SiteStreamManager (per-subscriber bounded buffers, fire-and-forget)
- Debug view backend (snapshot + stream), concurrency serialization
- Local artifact storage (4 SQLite tables)

Health Monitoring (WP-26–28):
- SiteHealthCollector (thread-safe counters, connection state)
- HealthReportSender (30s interval, monotonic sequence numbers)
- CentralHealthAggregator (offline detection 60s, online recovery)

Site Event Logging (WP-29–31):
- SiteEventLogger (SQLite, 6 event categories, ISO 8601 UTC)
- EventLogPurgeService (30-day retention, 1GB cap)
- EventLogQueryService (filters, keyword search, keyset pagination)

541 tests pass, zero warnings.
This commit is contained in:
Joseph Doherty
2026-03-16 20:57:25 -04:00
parent a3bf0c43f3
commit 389f5a0378
97 changed files with 8308 additions and 127 deletions

View File

@@ -4,10 +4,14 @@ using Akka.Cluster.Tools.Singleton;
using Akka.Configuration;
using Microsoft.Extensions.Options;
using ScadaLink.ClusterInfrastructure;
using ScadaLink.Communication;
using ScadaLink.Communication.Actors;
using ScadaLink.Host.Actors;
using ScadaLink.SiteRuntime;
using ScadaLink.SiteRuntime.Actors;
using ScadaLink.SiteRuntime.Persistence;
using ScadaLink.SiteRuntime.Scripts;
using ScadaLink.SiteRuntime.Streaming;
namespace ScadaLink.Host.Actors;
@@ -15,12 +19,15 @@ namespace ScadaLink.Host.Actors;
/// Hosted service that manages the Akka.NET actor system lifecycle.
/// Creates the actor system on start, registers actors, and triggers
/// CoordinatedShutdown on stop.
///
/// WP-3: Transport heartbeat is explicitly configured in HOCON from CommunicationOptions.
/// </summary>
public class AkkaHostedService : IHostedService
{
private readonly IServiceProvider _serviceProvider;
private readonly NodeOptions _nodeOptions;
private readonly ClusterOptions _clusterOptions;
private readonly CommunicationOptions _communicationOptions;
private readonly ILogger<AkkaHostedService> _logger;
private ActorSystem? _actorSystem;
@@ -28,11 +35,13 @@ public class AkkaHostedService : IHostedService
IServiceProvider serviceProvider,
IOptions<NodeOptions> nodeOptions,
IOptions<ClusterOptions> clusterOptions,
IOptions<CommunicationOptions> communicationOptions,
ILogger<AkkaHostedService> logger)
{
_serviceProvider = serviceProvider;
_nodeOptions = nodeOptions.Value;
_clusterOptions = clusterOptions.Value;
_communicationOptions = communicationOptions.Value;
_logger = logger;
}
@@ -50,6 +59,10 @@ public class AkkaHostedService : IHostedService
var roles = BuildRoles();
var rolesStr = string.Join(",", roles.Select(r => $"\"{r}\""));
// WP-3: Transport heartbeat explicitly configured from CommunicationOptions (not framework defaults)
var transportHeartbeatSec = _communicationOptions.TransportHeartbeatInterval.TotalSeconds;
var transportFailureSec = _communicationOptions.TransportFailureThreshold.TotalSeconds;
var hocon = $@"
akka {{
actor {{
@@ -60,6 +73,10 @@ akka {{
hostname = ""{_nodeOptions.NodeHostname}""
port = {_nodeOptions.RemotingPort}
}}
transport-failure-detector {{
heartbeat-interval = {transportHeartbeatSec:F0}s
acceptable-heartbeat-pause = {transportFailureSec:F0}s
}}
}}
cluster {{
seed-nodes = [{seedNodesStr}]
@@ -87,11 +104,14 @@ akka {{
_actorSystem = ActorSystem.Create("scadalink", config);
_logger.LogInformation(
"Akka.NET actor system 'scadalink' started. Role={Role}, Roles={Roles}, Hostname={Hostname}, Port={Port}",
"Akka.NET actor system 'scadalink' started. Role={Role}, Roles={Roles}, Hostname={Hostname}, Port={Port}, " +
"TransportHeartbeat={TransportHeartbeat}s, TransportFailure={TransportFailure}s",
_nodeOptions.Role,
string.Join(", ", roles),
_nodeOptions.NodeHostname,
_nodeOptions.RemotingPort);
_nodeOptions.RemotingPort,
transportHeartbeatSec,
transportFailureSec);
// Register the dead letter monitor actor
var loggerFactory = _serviceProvider.GetRequiredService<ILoggerFactory>();
@@ -100,8 +120,12 @@ akka {{
Props.Create(() => new DeadLetterMonitorActor(dlmLogger)),
"dead-letter-monitor");
// For site nodes, register the Deployment Manager as a cluster singleton
if (_nodeOptions.Role.Equals("Site", StringComparison.OrdinalIgnoreCase))
// Register role-specific actors
if (_nodeOptions.Role.Equals("Central", StringComparison.OrdinalIgnoreCase))
{
RegisterCentralActors();
}
else if (_nodeOptions.Role.Equals("Site", StringComparison.OrdinalIgnoreCase))
{
RegisterSiteActors();
}
@@ -138,7 +162,25 @@ akka {{
}
/// <summary>
/// Registers site-specific actors including the Deployment Manager cluster singleton.
/// Registers central-side actors including the CentralCommunicationActor.
/// WP-4: Central communication actor routes all 8 message patterns to sites.
/// </summary>
private void RegisterCentralActors()
{
var centralCommActor = _actorSystem!.ActorOf(
Props.Create(() => new CentralCommunicationActor()),
"central-communication");
// Wire up the CommunicationService with the actor reference
var commService = _serviceProvider.GetService<CommunicationService>();
commService?.SetCommunicationActor(centralCommActor);
_logger.LogInformation("Central actors registered. CentralCommunicationActor created.");
}
/// <summary>
/// Registers site-specific actors including the Deployment Manager cluster singleton
/// and the SiteCommunicationActor.
/// The singleton is scoped to the site-specific cluster role so it runs on exactly
/// one node within this site's cluster.
/// </summary>
@@ -146,6 +188,9 @@ akka {{
{
var siteRole = $"site-{_nodeOptions.SiteId}";
var storage = _serviceProvider.GetRequiredService<SiteStorageService>();
var compilationService = _serviceProvider.GetRequiredService<ScriptCompilationService>();
var sharedScriptLibrary = _serviceProvider.GetRequiredService<SharedScriptLibrary>();
var streamManager = _serviceProvider.GetService<SiteStreamManager>();
var siteRuntimeOptionsValue = _serviceProvider.GetService<IOptions<SiteRuntimeOptions>>()?.Value
?? new SiteRuntimeOptions();
var dmLogger = _serviceProvider.GetRequiredService<ILoggerFactory>()
@@ -155,6 +200,9 @@ akka {{
var singletonProps = ClusterSingletonManager.Props(
singletonProps: Props.Create(() => new DeploymentManagerActor(
storage,
compilationService,
sharedScriptLibrary,
streamManager,
siteRuntimeOptionsValue,
dmLogger)),
terminationMessage: PoisonPill.Instance,
@@ -171,10 +219,18 @@ akka {{
.WithRole(siteRole)
.WithSingletonName("deployment-manager"));
_actorSystem.ActorOf(proxyProps, "deployment-manager-proxy");
var dmProxy = _actorSystem.ActorOf(proxyProps, "deployment-manager-proxy");
// WP-4: Create SiteCommunicationActor for receiving messages from central
_actorSystem.ActorOf(
Props.Create(() => new SiteCommunicationActor(
_nodeOptions.SiteId!,
_communicationOptions,
dmProxy)),
"site-communication");
_logger.LogInformation(
"Site actors registered. DeploymentManager singleton scoped to role={SiteRole}",
"Site actors registered. DeploymentManager singleton scoped to role={SiteRole}, SiteCommunicationActor created.",
siteRole);
}
}