dohertj2/lmxopcua
1
0
Fork 0
Code Issues 16 Pull Requests 1 Actions 1 Packages Projects Releases Wiki Activity

feat(mesh-phase4): retire DB-reachability from ServiceLevel on DB-less nodes

Browse Source 
Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW
This commit is contained in:
Joseph Doherty
2026-07-23 11:55:43 -04:00
parent 5c40908a55
commit 9565827275
4 changed files with 223 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/Server/ZB.MOM.WW.OtOpcUa.Runtime/OpcUa/OpcUaPublishActor.cs
+47 -5
View File
@@ -103,6 +103,11 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
private readonly IDbContextFactory<OtOpcUaConfigDbContext>? _dbFactory;
private readonly AddressSpaceApplier? _applier;
private readonly IActorRef? _dbHealthProbe;
/// <summary>Per-cluster mesh Phase 4: this is a driver-only node with NO ConfigDb (LocalDb is its
/// config store). There is no DB to probe, so the ServiceLevel DB-reachability input is retired —
/// <c>DbReachable</c> is fed constant <c>true</c> and only snapshot staleness can demote. See
/// <see cref="RecomputeServiceLevel"/>.</summary>
private readonly bool _dbLess;
private readonly TimeSpan _staleWindow;
private readonly TimeSpan _probeFreshnessWindow;
private readonly TimeSpan _healthTickInterval;
@@ -153,6 +158,9 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
/// <param name="healthTickInterval">The period between self-driven DB-health refresh ticks (each
/// Asks <paramref name="dbHealthProbe"/> for its cached status); defaults to 5 seconds. No timer is
/// started when <paramref name="dbHealthProbe"/> is null.</param>
/// <param name="dbLess">Per-cluster mesh Phase 4: this is a driver-only node with no ConfigDb, so the
/// ServiceLevel DB-reachability input is retired (<c>DbReachable</c> treated constant-true, only
/// staleness demotes). No <paramref name="dbHealthProbe"/> is wired on such a node.</param>
/// <returns>The configured <see cref="Props"/> for creating this actor, pinned to the
/// <see cref="DispatcherId"/> dispatcher.</returns>
public static Props Props(
@@ -164,7 +172,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
IActorRef? dbHealthProbe = null,
TimeSpan? staleWindow = null,
TimeSpan? probeFreshnessWindow = null,
TimeSpan? healthTickInterval = null) =>
TimeSpan? healthTickInterval = null,
bool dbLess = false) =>
Akka.Actor.Props.Create(() => new OpcUaPublishActor(
sink ?? NullOpcUaAddressSpaceSink.Instance,
serviceLevel ?? NullServiceLevelPublisher.Instance,
@@ -175,7 +184,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
dbHealthProbe,
staleWindow,
probeFreshnessWindow,
healthTickInterval)).WithDispatcher(DispatcherId);
healthTickInterval,
dbLess)).WithDispatcher(DispatcherId);
/// <summary>Test-only Props that omits the pinned-dispatcher requirement and skips the
/// DPS subscribe so unit tests can spin up the actor on a vanilla TestKit cluster.</summary>
@@ -195,6 +205,9 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
/// <param name="healthTickInterval">The period between self-driven DB-health refresh ticks (each
/// Asks <paramref name="dbHealthProbe"/> for its cached status); defaults to 5 seconds. No timer is
/// started when <paramref name="dbHealthProbe"/> is null.</param>
/// <param name="dbLess">Per-cluster mesh Phase 4: this is a driver-only node with no ConfigDb, so the
/// ServiceLevel DB-reachability input is retired (<c>DbReachable</c> treated constant-true, only
/// staleness demotes). No <paramref name="dbHealthProbe"/> is wired on such a node.</param>
/// <returns>The configured <see cref="Props"/> for creating this actor in tests, without dispatcher
/// pinning or the DPS subscribe.</returns>
public static Props PropsForTests(
@@ -207,7 +220,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
IActorRef? dbHealthProbe = null,
TimeSpan? staleWindow = null,
TimeSpan? probeFreshnessWindow = null,
TimeSpan? healthTickInterval = null) =>
TimeSpan? healthTickInterval = null,
bool dbLess = false) =>
Akka.Actor.Props.Create(() => new OpcUaPublishActor(
sink ?? NullOpcUaAddressSpaceSink.Instance,
serviceLevel ?? NullServiceLevelPublisher.Instance,
@@ -218,7 +232,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
dbHealthProbe,
staleWindow,
probeFreshnessWindow,
healthTickInterval));
healthTickInterval,
dbLess));
/// <summary>Initializes a new instance of the <see cref="OpcUaPublishActor"/> class.</summary>
/// <param name="sink">The OPC UA address space sink.</param>
@@ -237,6 +252,9 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
/// <param name="healthTickInterval">The period between self-driven DB-health refresh ticks (each
/// Asks <paramref name="dbHealthProbe"/> for its cached status); defaults to 5 seconds. No timer is
/// started when <paramref name="dbHealthProbe"/> is null.</param>
/// <param name="dbLess">Per-cluster mesh Phase 4: this is a driver-only node with no ConfigDb, so the
/// ServiceLevel DB-reachability input is retired (<c>DbReachable</c> treated constant-true, only
/// staleness demotes). No <paramref name="dbHealthProbe"/> is wired on such a node.</param>
public OpcUaPublishActor(
IOpcUaAddressSpaceSink sink,
IServiceLevelPublisher serviceLevel,
@@ -247,7 +265,8 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
IActorRef? dbHealthProbe = null,
TimeSpan? staleWindow = null,
TimeSpan? probeFreshnessWindow = null,
TimeSpan? healthTickInterval = null)
TimeSpan? healthTickInterval = null,
bool dbLess = false)
{
_sink = sink;
_serviceLevel = serviceLevel;
@@ -256,6 +275,7 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
_dbFactory = dbFactory;
_applier = applier;
_dbHealthProbe = dbHealthProbe;
_dbLess = dbLess;
_staleWindow = staleWindow ?? TimeSpan.FromSeconds(30);
_probeFreshnessWindow = probeFreshnessWindow ?? TimeSpan.FromSeconds(30);
_healthTickInterval = healthTickInterval ?? TimeSpan.FromSeconds(5);
@@ -635,6 +655,28 @@ public sealed class OpcUaPublishActor : ReceiveActor, IWithTimers
return;
}
// Per-cluster mesh Phase 4: on a driver-only (DB-less) node there is no ConfigDb to probe —
// LocalDb IS the config store and is in-process, so it can never be "unreachable". Retire the
// DB-reachability input by feeding DbReachable=true CONSTANT and deriving staleness from the
// snapshot age ALONE (no DB-health term). This is the survive-alone posture and it is
// client-visible: a healthy DB-less node must publish 240 (240+10=250 as Primary) even with
// central down, so clients keep steering to it — the old DbReachable=false would have computed
// the (false,true,false) → 0 arm and driven clients AWAY from a node serving perfectly.
// Staleness ("running behind on config") still demotes to 200. The Detached guard above still
// wins, so a DB-less Detached node stays 0.
if (_dbLess)
{
var utcNow = DateTime.UtcNow;
var dbLessInputs = new NodeHealthInputs(
MemberState: SafeSelfStatus(),
DbReachable: true,
OpcUaProbeOk: OpcUaProbeOk(),
Stale: (utcNow - entry.AsOfUtc) > _staleWindow,
IsDriverPrimary: entry.IsDriverPrimary);
Self.Tell(new ServiceLevelChanged(ServiceLevelCalculator.Compute(dbLessInputs)));
return;
}
// Legacy / back-compat seam: with no DB-health probe wired (or before the first sample
// arrives) fall back to the old role-only switch. This preserves historical behaviour and
// is the bootstrap value until the first DbHealthStatus lands.
src/Server/ZB.MOM.WW.OtOpcUa.Runtime/ServiceCollectionExtensions.cs
+23 -6
View File
@@ -326,10 +326,19 @@ public static class ServiceCollectionExtensions
// (durable AVEVA sink is infra-gated); a deployment binding a real IHistoryWriter overrides.
var historyWriter = resolver.GetService<IHistoryWriter>() ?? NullHistoryWriter.Instance;
var dbHealth = system.ActorOf(
DbHealthProbeActor.Props(dbFactory),
DbHealthProbeActorName);
registry.Register<DbHealthProbeActorKey>(dbHealth);
// Per-cluster mesh Phase 4: a driver-only node has NO ConfigDb (LocalDb is its config
// store), so dbFactory is null and there is nothing to probe. Skip spawning the probe
// entirely — spawning it with a null factory would NRE on the first SELECT 1 — and do not
// register its marker key. OpcUaPublishActor then runs in dbLess mode (DbReachable retired,
// treated constant-true) so a healthy DB-less node still publishes full ServiceLevel.
IActorRef? dbHealth = null;
if (dbFactory is not null)
{
dbHealth = system.ActorOf(
DbHealthProbeActor.Props(dbFactory),
DbHealthProbeActorName);
registry.Register<DbHealthProbeActorKey>(dbHealth);
}
// Dependency mux must be spawned before DriverHostActor so the host can forward
// AttributeValuePublished into it from the very first driver spawn.
@@ -436,7 +445,8 @@ public static class ServiceCollectionExtensions
localNode: roleInfo.LocalNode,
dbFactory: dbFactory,
applier: applier,
dbHealthProbe: dbHealth),
dbHealthProbe: dbHealth,
dbLess: dbFactory is null),
OpcUaPublishActorName);
registry.Register<OpcUaPublishActorKey>(publishActor);
@@ -452,7 +462,14 @@ public static class ServiceCollectionExtensions
// ackRouter: under ClusterClient mode the node comm actor relays ApplyAcks across
// the boundary; under Dps it stays null and the host publishes on the
// deployment-acks topic exactly as before.
DriverHostActor.Props(dbFactory, roleInfo.LocalNode,
// dbFactory! — KNOWN INTERIM. A driver-only node genuinely passes a null factory here
// (ConfigDb is now gated on hasAdmin, and driver-only nodes are forced to FetchAndCache),
// so DriverHostActor's ConfigDb-touching paths — scripted-alarm state persistence
// (EfAlarmConditionStateStore) and UpsertNodeDeploymentState — fault-and-swallow until
// Task 4 makes the factory nullable + guards those sites (and removes this !) and Task 6
// re-homes the alarm store to LocalDb. Inert in practice: no driver-only node is
// configured to boot until the Task 10 rig change.
DriverHostActor.Props(dbFactory!, roleInfo.LocalNode,
ackRouter: useClusterClient ? nodeComm : null,
driverFactory: driverFactory, localRoles: roleInfo.LocalRoles,
dependencyMux: mux,