From 7f2108dcf24786d1edab49d8b57cbf578102f8e8 Mon Sep 17 00:00:00 2001 From: Joseph Doherty Date: Fri, 31 Jul 2026 07:17:17 -0400 Subject: [PATCH] feat(mqtt): Sparkplug primary-host STATE publishing, Primary-gated (#511) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit `ActAsPrimaryHost` was accepted by config and by the AdminUI form and did nothing but log a warning. It now delivers the whole three-part contract or none of it: a retained `ONLINE` on `spBv1.0/STATE/{hostId}`, a matching retained `OFFLINE` armed as the MQTT Last Will, and an explicit `OFFLINE` on a clean stand-down. **The claim is a dedicated connection, not a message.** A Will can only be registered in the CONNECT packet — it cannot be added to a live session, changed, or withdrawn. So a claim that is acquired and released at runtime cannot ride the long-lived ingest session. `SparkplugPrimaryHost` opens its own connection (client id `{clientId}-spbhost`, forced clean-session) when the node gains Primary and closes it when the node loses Primary; the connection's lifetime *is* the claim, so every leg follows from its lifecycle. Ingest is untouched by a role change — no dropped subscriptions, no lost birth cache, no data gap at the Secondary->Primary transition. **Primary-gated** (owner decision, recorded on the issue). Both pair nodes subscribe independently, so an ungated claim means both claim the same host id — and the sharp failure is not the two fighting over the retained STATE, it is that the SECONDARY's death fires its Will and publishes OFFLINE while the Primary is healthy, stopping every edge node in the group. Registering the Will only on whichever node is Primary at connect time fails the other way: a node that later gains Primary would publish ONLINE with no Will behind it. New seam: `IDriverPrimaryRoleSource` (`Core.Abstractions`) carrying the *data-plane* verdict (`PrimaryGatePolicy.ShouldServiceAsPrimary`), not the alarm-drain verdict — an unknown role with a driver peer present must deny. Registered unconditionally by `AddOtOpcUaRuntime`, deliberately NOT alongside `IRedundancyRoleView`, which `AddAlarmHistorian` registers only when that section is enabled: piggybacking would leave a pair with no alarm historian falling back to "claim unconditionally". Polled on a 1s timer rather than evented — a process singleton raising events at per-instance drivers outlives every driver it holds. Accepted trade: a brief edge-visible OFFLINE window during failover. That is a genuine state transition, not a glitch to hide. Live-gated 5/5 against the Mosquitto fixture, including the Will leg — `AbandonForTests` drops the socket with no DISCONNECT, because a clean disconnect makes the broker discard the Will by protocol rule, so a test driven through `StopAsync` would observe the stand-down OFFLINE and pass against an implementation that never armed a Will. Falsified: removing the Will turns that leg and only that leg red. Also corrects two stale claims found en route: the AdminUI form still said MQTT tags are read-only (#508 shipped), and the driver doc still said nothing consumes `IRediscoverable`. Claude-Session: https://claude.ai/code/session_015p7wGqy3YpZNCpDzTpGMKo --- docs/drivers/Mqtt.md | 114 ++++- .../IDriverPrimaryRoleSource.cs | 90 ++++ .../MqttDriverOptions.cs | 6 + .../MqttLastWill.cs | 37 ++ .../Sparkplug/SparkplugStatePayload.cs | 141 ++++++ .../MqttClientOptionsFactory.cs | 35 +- .../MqttConnection.cs | 78 ++- .../MqttDriver.cs | 91 +++- .../MqttDriverFactoryExtensions.cs | 24 +- .../Sparkplug/SparkplugIngestor.cs | 31 +- .../Sparkplug/SparkplugPrimaryHost.cs | 470 ++++++++++++++++++ .../ZB.MOM.WW.OtOpcUa.Driver.Mqtt.csproj | 4 + .../Shared/Drivers/Forms/MqttDriverForm.razor | 44 +- .../Drivers/Forms/MqttDriverFormModel.cs | 18 +- .../Forms/SparkplugPrimaryHostAdvice.cs | 35 ++ .../Drivers/DriverFactoryBootstrap.cs | 14 +- .../Drivers/DriverHostActor.cs | 34 +- .../Redundancy/IRedundancyRoleView.cs | 32 +- .../ServiceCollectionExtensions.cs | 28 +- .../MqttPrimaryHostLiveTests.cs | 379 ++++++++++++++ .../SparkplugPrimaryHostTests.cs | 263 ++++++++++ 21 files changed, 1881 insertions(+), 87 deletions(-) create mode 100644 src/Core/ZB.MOM.WW.OtOpcUa.Core.Abstractions/IDriverPrimaryRoleSource.cs create mode 100644 src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttLastWill.cs create mode 100644 src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/Sparkplug/SparkplugStatePayload.cs create mode 100644 src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugPrimaryHost.cs create mode 100644 src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/SparkplugPrimaryHostAdvice.cs create mode 100644 tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.IntegrationTests/MqttPrimaryHostLiveTests.cs create mode 100644 tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Tests/SparkplugPrimaryHostTests.cs diff --git a/docs/drivers/Mqtt.md b/docs/drivers/Mqtt.md index 6d1b921e..76be2763 100644 --- a/docs/drivers/Mqtt.md +++ b/docs/drivers/Mqtt.md @@ -2,7 +2,8 @@ In-process MQTT **broker-subscribe** driver. It holds one MQTTnet 5 client against one broker, subscribes to the topics its authored tags name, and forwards each PUBLISH straight to -`ISubscribable.OnDataChange`. Ingest is **push, not poll**, and **one-way** — there is no `IWritable`. +`ISubscribable.OnDataChange`. Ingest is **push, not poll**; writes go back out as ordinary publishes +(see [Write-through](#write-through)). **Two ingest shapes, selected by the driver's `Mode`:** `Plain` binds a tag to a concrete MQTT topic; `SparkplugB` binds it to a `group / edge node / device? / metric` tuple and decodes Eclipse-Tahu @@ -12,18 +13,18 @@ See [Mqtt-Test-Fixture.md](Mqtt-Test-Fixture.md) for the harness and [`../plans/2026-07-15-mqtt-sparkplug-driver-design.md`](../plans/2026-07-15-mqtt-sparkplug-driver-design.md) for the design. -> **Status.** P1 (plain MQTT) and P2 (Sparkplug B ingest) are both shipped and live-gated against the -> Mosquitto + Sparkplug-simulator fixture. Write-through (`IWritable` — NCMD/DCMD/plain publish) is -> **deferred** ([#508](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/508)); every MQTT node -> materializes read-only. See [Known gaps](#known-gaps) — every entry there carries a tracking issue -> (#507–#515). +> **Status.** P1 (plain MQTT), P2 (Sparkplug B ingest), write-through +> ([#508](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/508)) and the Sparkplug primary-host +> claim ([#511](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/511)) are all shipped and +> live-gated against the Mosquitto + Sparkplug-simulator fixture. See +> [Known gaps](#known-gaps) — every entry there carries a tracking issue. ## Project Layout | Project | Holds | |---|---| | `Driver.Mqtt.Contracts` | Config records, enums, `MqttTagDefinition` + the pure `MqttTagDefinitionFactory`, and the one shared `MqttJson.Options`. **Deliberately transport-free** — no MQTTnet reference | -| `Driver.Mqtt` | Runtime: `MqttDriver`, `MqttConnection` (connect + reconnect supervisor), `MqttSubscriptionManager`, `LastValueCache`, factory registration, `MqttDriverProbe` | +| `Driver.Mqtt` | Runtime: `MqttDriver`, `MqttConnection` (connect + reconnect supervisor), `MqttSubscriptionManager`, `LastValueCache`, `SparkplugIngestor`, `SparkplugPrimaryHost`, factory registration, `MqttDriverProbe` | | `Driver.Mqtt.Transport` | `MqttClientOptionsFactory` — TLS posture, PEM CA-pin chain validator, credentials, protocol mapping. Connection **policy** only; nothing here connects | | `Driver.Mqtt.Browser` | `MqttDriverBrowser` + `MqttBrowseSession` — the AdminUI address picker's `#`-observation session | @@ -113,8 +114,8 @@ driver are pure organisational grouping in the RawPath. "Mode": "SparkplugB", "Sparkplug": { "GroupId": "OtOpcUaSim", // REQUIRED — the driver's whole subscription scope - "HostId": "", // Host Application identity; receive-only (see below) - "ActAsPrimaryHost": false, // NOT IMPLEMENTED — logs a warning when true + "HostId": "", // Host Application identity — spBv1.0/STATE/{HostId} + "ActAsPrimaryHost": false, // claim the primary host id (Primary-gated; see below) "RequestRebirthOnGap": true, // a seq gap asks the edge node to re-announce (NCMD) "BirthObservationWindowSeconds": 15 // how long discovery collects births before calling it stable } @@ -124,8 +125,8 @@ driver are pure organisational grouping in the RawPath. | Key | Default | Notes | |---|---|---| | `GroupId` | `""` | **Required.** The driver subscribes exactly `spBv1.0/{GroupId}/#`. Blank ⇒ it connects, reports `Healthy`, and ingests **nothing**. It is a literal topic segment, so `/`, `+`, `#` are refused by the form | -| `HostId` | `""` | Sparkplug Host Application identity. **Receive-only** — the driver observes `STATE` and never publishes one | -| `ActAsPrimaryHost` | `false` | **Not implemented.** Setting it logs a startup **warning** rather than being silently inert — being a primary host is a three-part contract (retained `ONLINE`, a matching `OFFLINE` registered as the MQTT Will *at connect time*, an explicit `OFFLINE` on clean shutdown), and shipping the `ONLINE` half without the Will is strictly worse than shipping neither: a crashed node would leave a retained `ONLINE` asserting forever that a dead host is alive | +| `HostId` | `""` | Sparkplug Host Application identity — the `spBv1.0/STATE/{HostId}` topic. Optional for observation; **required** to claim. Set without `ActAsPrimaryHost`, the driver only observes | +| `ActAsPrimaryHost` | `false` | Claim the Sparkplug Primary Host Application identity. **Primary-gated** — only the node holding the redundancy Primary role claims it. See [Primary host](#primary-host-actasprimaryhost) | | `RequestRebirthOnGap` | `true` | On a detected sequence-number gap, publish a rebirth-request NCMD instead of running on stale metric state | | `BirthObservationWindowSeconds` | `15` | Discovery's birth-collection window. Must be ≥ 1 | @@ -252,12 +253,80 @@ One subscription (`spBv1.0/{GroupId}/#`) feeds a per-edge-node state machine anti-storm, not optimisations: rediscovery triggers an address-space rebuild, and an edge node re-births freely — on its own schedule, on every reconnect, and once per rebirth NCMD. -> ⚠️ **Nothing consumes the signal today.** No runtime component subscribes to -> `IRediscoverable.OnRediscoveryNeeded`, and `DriverHostActor.HandleDiscoveredNodes` hard-returns — -> discovered-node injection is dormant in v3. The served address space comes from the deploy artifact, -> so **a DBIRTH introducing a new metric does not change the OPC UA tree**; you must redeploy. The -> driver's decision is observable only as an Information log line -> (`… requesting rediscovery.`). This is a v3 platform gap, not an MQTT one. +> ⚠️ **The signal is an operator prompt, not a rebuild.** `DriverInstanceActor` subscribes and the +> raise rides the driver-health snapshot to the AdminUI `/hosts` page as a **re-browse chip** — but the +> served address space still comes from the deploy artifact, so **a DBIRTH introducing a new metric does +> not change the OPC UA tree**. Re-browse the device and commit. That is deliberate: v3 authors raw tags +> through the `/raw` browse-commit flow, and grafting nodes at runtime would materialise ones nobody +> approved and no deployment artifact records. + +## Primary host (`actAsPrimaryHost`) + +A Sparkplug **Primary Host Application** is the thing edge nodes watch to decide whether anyone is +listening — many stop publishing while their host is offline. Claiming it is a three-part contract, +and this driver ships all three or none of it +([#511](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/511)): + +1. a **retained** `{"online":true,"timestamp":…}` on `spBv1.0/STATE/{hostId}`, QoS 1, published after CONNACK; +2. a matching **retained `OFFLINE` armed as the MQTT Last Will**, so a crash still reports the truth; +3. an explicit `OFFLINE` on a clean stand-down, so edge nodes do not wait out a keep-alive timeout. + +Set `Sparkplug.HostId` and `Sparkplug.ActAsPrimaryHost: true`. A blank host id is **refused** with a +warning — the driver does not publish to `spBv1.0/STATE/`, which is a legal topic reaching nobody. + +### The claim is a whole connection, not a message + +A Will can only be registered in the **CONNECT packet**. It cannot be added to a live session, changed, +or withdrawn. So the claim gets its **own** broker connection (client id `{clientId}-spbhost`, forced +clean-session) whose lifetime *is* the claim: opened on gaining Primary, closed on losing it. Every leg +then follows from the connection's lifecycle rather than from bookkeeping that could drift. + +The ingest session is untouched by a role change — no dropped subscriptions, no lost birth cache, and +no data gap at the Secondary→Primary transition, which is the moment a plant most needs values flowing. + +### Primary-gated — and why the obvious alternatives are wrong + +Both nodes of a redundant pair subscribe independently (MQTT fan-out is per-connection, and the Primary +gate applies downstream of ingest), so an ungated claim means both claim the same host id. The sharp +failure is not the two fighting over the retained `STATE`. It is that the **Secondary's** death fires +*its* Will, publishing `OFFLINE` while the Primary is perfectly healthy — every edge node in the group +stops publishing, and redundancy has caused the outage the mechanism exists to prevent. + +Registering the Will only on whichever node is Primary *at connect time* fails the other way: a node +that later gains Primary would publish `ONLINE` with no Will behind it, and a crash would leave a +retained `ONLINE` asserting forever that a dead host is alive. + +Hence: bind the claim to a connection, and rebuild the connection on role change. + +| Node state | STATE connection | Retained `STATE` | +|---|---|---| +| Primary | open, Will armed | `ONLINE` | +| Secondary / Detached | **never opened** | — (whatever the Primary published) | +| Role unknown, driver peer present | not opened (fail closed) | — | +| Role unknown, no driver peer (single node) | open | `ONLINE` | + +The verdict comes from `PrimaryGatePolicy.ShouldServiceAsPrimary` via `IDriverPrimaryRoleSource` +(`Core.Abstractions`), published by `DriverHostActor` on every redundancy snapshot and **sampled on a +1-second timer** rather than evented — a process-singleton raising events at per-instance drivers +outlives every driver it holds a reference to. + +> **Accepted trade: a brief edge-visible `OFFLINE` during failover**, while the old Primary stands down +> and the new one connects and republishes. That is a genuine state transition — for that window there +> really is no host — not a glitch worth hiding. + +### Operational notes + +- **At most one primary host per host id per broker.** Two separate OtOpcUa deployments pointing at one + broker with the same `hostId` will fight, and nothing in either can detect the other. The gate covers + a redundant *pair*, not two independent deployments. +- **A reconnect republishes the birth.** A broker restart drops retained messages; without the + republish the host would be connected and believed offline by everyone, silently. +- **A failed claim never faults the driver.** A broker whose ACL denies `spBv1.0/STATE/#` costs a + warning and a plant-visible missing host, not every tag's value. Ingest is the data plane; the claim + is an assertion to other applications. +- **The driver still observes its own `STATE`.** The ingestor subscribes the configured host id + regardless, so a claiming node sees its own retained `ONLINE` come back. Nothing gates on it, so the + echo costs one log line. ## Connection + Failure Semantics @@ -446,9 +515,14 @@ identical words. See [TestConnectProbes.md](TestConnectProbes.md). reconnect/rebuild branches, CONNACK classification, and the Sparkplug half — golden-payload decode, topic parse/format, datatype map, alias/birth-cache rebuild, sequence + bdSeq-death ties, the rediscovery change gate, and the browse session's "publishes nothing" assertion. -- **Live (env-gated)** — `tests/Drivers/…Driver.Mqtt.IntegrationTests` (**15 tests**) against the +- **Live (env-gated)** — `tests/Drivers/…Driver.Mqtt.IntegrationTests` (**26 tests**) against the Mosquitto broker + the C# Sparkplug edge-node simulator; skips cleanly when `MQTT_FIXTURE_ENDPOINT` is unset. See [Mqtt-Test-Fixture.md](Mqtt-Test-Fixture.md) and `infra/README.md` §3. +
The primary-host legs (`MqttPrimaryHostLiveTests`) include the one the ordinary lifecycle cannot + reach: `AbandonClaimForTests` drops the socket with **no** `DISCONNECT`, because a clean disconnect + makes the broker *discard* the Will by protocol rule — so a test driven through `StopAsync` would + observe the explicit stand-down `OFFLINE` and pass against an implementation that never armed a Will + at all. - **AdminUI** — `MqttDriverFormModelTests` / `MqttTagConfigModelTests` cover both editors' round-trip, mode inference and validation. AdminUI has no bUnit, so the razor shells themselves are only ever proven by a live `/run` gate. @@ -466,7 +540,8 @@ identical words. See [TestConnectProbes.md](TestConnectProbes.md). Every row is tracked. None is a silent failure — each either refuses in words or logs. -**Closed 2026-07-31:** write-through ([#508](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/508), live-gated), the slashed-metric browse-commit +**Closed 2026-07-31:** write-through ([#508](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/508), live-gated), primary-host STATE publishing +([#511](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/511), live-gated), the slashed-metric browse-commit ([#509](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/509)), the stale rebirth affordance ([#510](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/510)), the `.Browser` layering exception ([#512](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/512)), the stray Sparkplug `payloadFormat` ([#513](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/513)) and rebirth on a not-yet-birthed plant ([#514](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/514)). @@ -474,5 +549,4 @@ not-yet-birthed plant ([#514](https://gitea.dohertylan.com/dohertj2/lmxopcua/iss | Gap | Issue | Effect | Notes | |---|:---:|---|---| | **Rediscovery is advisory, not a rebuild** | [#507](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/507) (closed, superseded) | A DBIRTH introducing a metric does not change the served OPC UA tree; an operator must re-browse the device and commit | **No longer "inert".** `DriverInstanceActor` now subscribes to `OnRediscoveryNeeded` and the raise rides the driver-health snapshot to the AdminUI `/hosts` page as a **re-browse chip**. It deliberately does not inject nodes: v3 authors raw tags through the `/raw` browse-commit flow, and grafting nodes at runtime would materialise ones nobody approved and no deployment artifact records. #507's injection path was deleted rather than revived | -| **Primary-host STATE publishing** | [#511](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/511) | `ActAsPrimaryHost` does nothing | Logs a startup warning rather than being silently inert — see the `Sparkplug` sub-object table | | **`DataSet` / `Template` / `PropertySet` metrics** | [#515](https://gitea.dohertylan.com/dohertj2/lmxopcua/issues/515) | Skipped with a warning | v1-unsupported; never coerced into a guessed type | diff --git a/src/Core/ZB.MOM.WW.OtOpcUa.Core.Abstractions/IDriverPrimaryRoleSource.cs b/src/Core/ZB.MOM.WW.OtOpcUa.Core.Abstractions/IDriverPrimaryRoleSource.cs new file mode 100644 index 00000000..b2780389 --- /dev/null +++ b/src/Core/ZB.MOM.WW.OtOpcUa.Core.Abstractions/IDriverPrimaryRoleSource.cs @@ -0,0 +1,90 @@ +namespace ZB.MOM.WW.OtOpcUa.Core.Abstractions; + +/// +/// A driver-facing snapshot of "should this node be the one asserting an exclusive identity on a +/// shared external system right now?". +/// +/// +/// +/// Why drivers need this at all. The driver layer has no notion of redundancy, by +/// design — a driver talks to a device and the Primary gate is applied above it, in +/// DriverHostActor, on the way in. That works because every gated operation is +/// inbound: a write, an alarm ack, an alerts publish. A Sparkplug primary-host claim is +/// not inbound. It is a standing assertion the driver makes to the broker, on its own +/// connection, for as long as it holds one — there is no message for the host actor to +/// intercept. So the decision has to reach the driver instead (Gitea #511). +/// +/// +/// The decision, not the role. Same discipline as the alarm-drain view in +/// Runtime: this publishes the verdict a single policy produced, so the policy stays the +/// one place that decides and a driver can never re-derive a subtly different rule from a raw +/// role. The verdict fed here is the data-plane one (an unknown role on a cluster that +/// has a driver peer denies), because two nodes claiming one Sparkplug host id is the harm the +/// gate exists to prevent — not a duplicate row, but a Secondary's Last Will publishing +/// OFFLINE over a live Primary's ONLINE and stopping every edge node in the +/// group. +/// +/// +/// Polled, not evented, and that is deliberate. A process-wide singleton raising an +/// event onto per-instance drivers outlives every driver it hands a reference to — the exact +/// missing--= leak shape the rediscovery signal had to be careful about. Consumers +/// sample this instead, so a driver that is torn down simply stops asking. The cost is up to +/// one poll interval of latency on a failover, which is inside the edge-visible +/// OFFLINE window a failover already implies. +/// +/// +public interface IDriverPrimaryRoleSource +{ + /// + /// Whether this node currently holds the Primary data-plane role — and may therefore claim an + /// exclusive external identity such as a Sparkplug host id. + /// + bool ShouldActAsPrimary { get; } + + /// + /// Records a fresh decision. Called by DriverHostActor on every redundancy snapshot. + /// + /// + /// The verdict PrimaryGatePolicy.ShouldServiceAsPrimary produced. + /// + void PublishPrimaryRole(bool shouldActAsPrimary); +} + +/// +/// The a driver uses when nothing publishes one — a +/// standalone host, a unit test, or any deployment with no redundancy manager wired. +/// +/// +/// +/// It answers , and the alternative is worse. Defaulting closed +/// would be the reflexive "fail-safe" choice, but there is no safety to gain: with nothing +/// publishing a role there is by definition no peer to collide with, and a closed default +/// would make an exclusive-identity claim silently never happen on the single-node deployment +/// that is the common case — an inert feature with no error, which is precisely the failure +/// mode Gitea #511 was filed about. +/// +/// +/// The risk this shifts onto the wiring is real and is guarded there instead: a redundant +/// deployment whose composition root forgets to supply the live source would fall back to this +/// and let both nodes claim. DriverFactoryBootstrapPrimaryRoleSourceTests pins that the +/// Host resolves a real one. +/// +/// +public sealed class UnmanagedDriverPrimaryRoleSource : IDriverPrimaryRoleSource +{ + /// The shared instance — it holds no state. + public static readonly UnmanagedDriverPrimaryRoleSource Instance = new(); + + private UnmanagedDriverPrimaryRoleSource() + { + } + + /// + public bool ShouldActAsPrimary => true; + + /// + /// No-op: there is no redundancy manager to publish anything here. + public void PublishPrimaryRole(bool shouldActAsPrimary) + { + } +} diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttDriverOptions.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttDriverOptions.cs index 8acb9148..c40bae79 100644 --- a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttDriverOptions.cs +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttDriverOptions.cs @@ -190,6 +190,12 @@ public sealed record MqttSparkplugOptions /// When true, this driver instance acts as the Sparkplug Primary Host /// Application. At most one primary host may exist per host-id per broker. /// + /// + /// Implemented by SparkplugPrimaryHost (Gitea #511) on a dedicated broker connection + /// whose lifetime is the claim, and gated on the redundancy Primary role so the two nodes + /// of a pair never both claim. Requires ; set without one, the driver warns + /// and declines rather than publishing to a malformed topic. + /// public bool ActAsPrimaryHost { get; init; } = false; /// diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttLastWill.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttLastWill.cs new file mode 100644 index 00000000..a65a905d --- /dev/null +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/MqttLastWill.cs @@ -0,0 +1,37 @@ +namespace ZB.MOM.WW.OtOpcUa.Driver.Mqtt; + +/// +/// An MQTT Last Will and Testament, as the client options factory wants it (Gitea #511). +/// +/// +/// +/// A Will can only be registered at CONNECT, and that single fact drives the whole design +/// of the Sparkplug primary-host claim. It rides in the CONNECT packet, so it cannot be +/// added, changed or withdrawn on a live session. A node that gains the Primary role after +/// connecting therefore cannot simply start publishing ONLINE — it would have no Will, +/// and a crash would leave a retained ONLINE asserting forever that a dead host is +/// alive. Equally, a node that registers a Will and later loses the role cannot withdraw it, +/// so its eventual disconnect would publish OFFLINE over the new Primary's live claim +/// and stop every edge node in the group. +/// +/// +/// The consequence is that the claim must be bound to the lifetime of a connection: +/// SparkplugPrimaryHost opens a dedicated connection when the node gains Primary and +/// closes it when the node loses Primary, rather than trying to mutate the ingest session it +/// shares with the rest of the driver. +/// +/// +/// Clean session matters too. A broker that resumes an existing session for the same +/// client id may discard the Will registered by the new CONNECT. The primary-host connection +/// forces clean-session on for that reason, regardless of the driver's configured value. +/// +/// +/// The topic the broker publishes the Will to. +/// The Will body. +/// Requested QoS, 0–2. +/// +/// Whether the broker retains the Will. For a Sparkplug host death certificate this is +/// : an edge node that connects after the host died must still learn +/// the host is offline, and only a retained message reaches it. +/// +public sealed record MqttLastWill(string Topic, byte[] Payload, int Qos, bool Retain); diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/Sparkplug/SparkplugStatePayload.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/Sparkplug/SparkplugStatePayload.cs new file mode 100644 index 00000000..1065f109 --- /dev/null +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Contracts/Sparkplug/SparkplugStatePayload.cs @@ -0,0 +1,141 @@ +using System.Text; +using System.Text.Json; + +namespace ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Sparkplug; + +/// +/// Builds the Sparkplug v3.0 primary-host STATE bodies — the retained ONLINE birth +/// and the matching OFFLINE death that is registered as the MQTT Last Will (Gitea #511). +/// +/// +/// +/// Encode only. The receive side lives in SparkplugIngestor.TryReadStateOnline, +/// which additionally tolerates the pre-3.0 bare ONLINE/OFFLINE text form. This +/// type only ever produces the v3.0 JSON shape, matching +/// 's refusal to produce the legacy topic. +/// +/// +/// The two bodies share one timestamp, and that is a spec requirement rather than a +/// convenience. Sparkplug 3.0 pairs a host's birth and death certificates by their +/// timestamp field: an edge node that receives an OFFLINE whose timestamp is +/// older than the ONLINE it already holds is entitled to ignore it as a stale death +/// from a previous session. That rule is what makes the mechanism safe across a reconnect — +/// and it means the death body has to be built before CONNECT (a Will is registered in +/// the CONNECT packet) while the birth is published after CONNACK. Deriving each from +/// its own UtcNow would give them different timestamps and quietly break the pairing, +/// so mints both at once and there is no single-body overload to +/// reach for by accident. +/// +/// +public static class SparkplugStatePayload +{ + /// + /// QoS for both STATE bodies. Sparkplug 3.0 requires QoS 1 for the host birth and death — + /// unlike the QoS 0 that carries NBIRTH/DBIRTH/DATA. A host claim delivered at most once is a + /// claim that may simply never arrive. + /// + public const int StateQos = 1; + + /// + /// Mints the matched ONLINE/OFFLINE pair for one host session, both carrying + /// . + /// + /// The Sparkplug host id; used to build the topic. + /// + /// Sparkplug epoch milliseconds for this session. Supplied by the caller rather than read from + /// the clock here so the value is visible at the call site and testable. + /// + /// The topic plus both bodies. + /// is blank. + public static SparkplugStateSession ForSession(string hostId, long timestampMs) + { + ArgumentException.ThrowIfNullOrWhiteSpace(hostId); + + return new SparkplugStateSession( + Topic: SparkplugTopic.FormatState(hostId), + TimestampMs: timestampMs, + OnlineBody: Encode(online: true, timestampMs), + OfflineBody: Encode(online: false, timestampMs)); + } + + /// Encodes one STATE body: {"online":<bool>,"timestamp":<ms>}. + /// The online flag. + /// Sparkplug epoch milliseconds. + /// The UTF-8 body bytes. + /// + /// Hand-written rather than serialized from a DTO. The body is two fields, and the wire form + /// is fixed by the spec — a serializer would put naming policy, casing options and a shared + /// JsonSerializerOptions between this repo and a wire contract it does not control. + /// timestamp is emitted as a bare JSON number, never a string: a quoted timestamp + /// parses as a valid JSON object and is silently wrong to every conformant host. + /// + public static byte[] Encode(bool online, long timestampMs) => + Encoding.UTF8.GetBytes( + $"{{\"online\":{(online ? "true" : "false")},\"timestamp\":{timestampMs.ToString(System.Globalization.CultureInfo.InvariantCulture)}}}"); + + /// Reads the online flag back out of a v3.0 STATE body, for tests and diagnostics. + /// The STATE body bytes. + /// The decoded flag on success. + /// The decoded timestamp on success. + /// when the body is a well-formed v3.0 STATE object. + public static bool TryDecode(ReadOnlySpan body, out bool online, out long timestampMs) + { + online = false; + timestampMs = 0; + + if (body.IsEmpty) + { + return false; + } + + try + { + var reader = new Utf8JsonReader(body); + if (!JsonDocument.TryParseValue(ref reader, out var doc)) + { + return false; + } + + using (doc) + { + if (doc.RootElement.ValueKind != JsonValueKind.Object + || !doc.RootElement.TryGetProperty("online", out var flag) + || flag.ValueKind is not (JsonValueKind.True or JsonValueKind.False)) + { + return false; + } + + online = flag.GetBoolean(); + timestampMs = doc.RootElement.TryGetProperty("timestamp", out var ts) + && ts.ValueKind == JsonValueKind.Number + && ts.TryGetInt64(out var parsed) + ? parsed + : 0; + return true; + } + } + catch (JsonException) + { + return false; + } + } +} + +/// +/// The STATE topic plus the matched pair of bodies for one primary-host session (Gitea #511). +/// +/// The v3.0 STATE topic, spBv1.0/STATE/{hostId}. +/// The session timestamp carried by BOTH bodies. +/// +/// The birth certificate — published retained, at QoS 1, immediately after CONNACK. +/// +/// +/// The death certificate — registered as the MQTT Last Will in the CONNECT packet, and also +/// published explicitly on a clean stand-down so the broker holds it without waiting for a +/// keep-alive timeout. +/// +public sealed record SparkplugStateSession( + string Topic, + long TimestampMs, + byte[] OnlineBody, + byte[] OfflineBody); diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Transport/MqttClientOptionsFactory.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Transport/MqttClientOptionsFactory.cs index 4e4e9278..8b0dcd69 100644 --- a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Transport/MqttClientOptionsFactory.cs +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Transport/MqttClientOptionsFactory.cs @@ -41,20 +41,51 @@ public static class MqttClientOptionsFactory /// empty MQTTnet generates a random client id. /// /// Optional logger for the deferred CA-pin load; never receives credentials. + /// + /// Optional MQTT Last Will registered in the CONNECT packet (Gitea #511 — the Sparkplug + /// primary-host death certificate). See for why this can only be + /// supplied here. + /// + /// + /// Forces clean-session on or off, ignoring . Used + /// by the primary-host connection, which must connect clean so the broker cannot resume a + /// previous session and discard the Will — see . + /// public static MqttClientOptions BuildClientOptions( MqttDriverOptions options, string? clientIdSuffix, - ILogger? logger = null) + ILogger? logger = null, + MqttLastWill? lastWill = null, + bool? cleanSessionOverride = null) { ArgumentNullException.ThrowIfNull(options); var builder = new MqttClientOptionsBuilder() .WithTcpServer(options.Host, options.Port) .WithProtocolVersion(MapProtocolVersion(options.ProtocolVersion)) - .WithCleanSession(options.CleanSession) + .WithCleanSession(cleanSessionOverride ?? options.CleanSession) .WithKeepAlivePeriod(TimeSpan.FromSeconds(options.KeepAliveSeconds)) .WithTimeout(TimeSpan.FromSeconds(options.ConnectTimeoutSeconds)); + if (lastWill is { } will) + { + builder = builder + .WithWillTopic(will.Topic) + .WithWillPayload(will.Payload) + .WithWillQualityOfServiceLevel((MQTTnet.Protocol.MqttQualityOfServiceLevel)will.Qos) + .WithWillRetain(will.Retain); + + // MQTT 5.0 only. Left at its default the broker MAY hold the Will back for up to the + // session-expiry interval after an ungraceful disconnect, which for a host death + // certificate is precisely the wrong behaviour: the whole point is that edge nodes learn + // promptly. Zero means "publish it the moment the network connection is lost". + // The setter is harmless on 3.1.1 — the property simply has no wire representation there. + if (options.ProtocolVersion == MqttProtocolVersion.V500) + { + builder = builder.WithWillDelayInterval(0); + } + } + var clientId = string.Concat(options.ClientId ?? string.Empty, clientIdSuffix ?? string.Empty); if (!string.IsNullOrWhiteSpace(clientId)) { diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttConnection.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttConnection.cs index 6582de2e..57219b83 100644 --- a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttConnection.cs +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttConnection.cs @@ -286,11 +286,40 @@ public sealed class MqttConnection : IAsyncDisposable, IMqttSubscribeTransport, private Task? _reconnectWorker; private int _state = (int)MqttConnectionState.Disconnected; + /// Client-id suffix distinguishing this connection from the driver's other one; see the ctor. + private readonly string? _clientIdSuffix; + + /// The Will to register on every CONNECT, or null. See . + private readonly MqttLastWill? _lastWill; + + /// Clean-session override, or null to use the configured value. + private readonly bool? _cleanSessionOverride; + /// Stores configuration only — no network, no client instantiation, no supervisor. /// Broker connection settings. /// Driver instance id, used only for log/diagnostic correlation. /// Optional logger; never receives credentials. - public MqttConnection(MqttDriverOptions options, string driverId, ILogger? logger = null) + /// + /// Appended to the configured client id so a second connection from the same driver — the + /// Sparkplug primary-host claim (Gitea #511) — does not collide with the ingest session. Two + /// MQTT clients presenting one client id is not an error the broker reports: it silently + /// disconnects the older one, so the two would take turns evicting each other forever. + /// + /// + /// Optional Last Will registered in the CONNECT packet, and therefore rebuilt on every + /// reconnect attempt along with the rest of the options. See . + /// + /// + /// Forces clean-session on or off regardless of . + /// Null keeps the configured value. + /// + public MqttConnection( + MqttDriverOptions options, + string driverId, + ILogger? logger = null, + string? clientIdSuffix = null, + MqttLastWill? lastWill = null, + bool? cleanSessionOverride = null) { ArgumentNullException.ThrowIfNull(options); ArgumentException.ThrowIfNullOrWhiteSpace(driverId); @@ -298,6 +327,9 @@ public sealed class MqttConnection : IAsyncDisposable, IMqttSubscribeTransport, _options = options; _driverId = driverId; _logger = logger; + _clientIdSuffix = clientIdSuffix; + _lastWill = lastWill; + _cleanSessionOverride = cleanSessionOverride; } /// @@ -370,6 +402,47 @@ public sealed class MqttConnection : IAsyncDisposable, IMqttSubscribeTransport, /// internal Func? AfterConnectHookForTests { get; set; } + /// + /// Test seam: drops the session the way a crashed process does — no MQTT DISCONNECT, so + /// the broker treats the closed socket as an abnormal termination and publishes the Last Will. + /// + /// A task completing once the client is gone and the supervisor has stopped. + /// + /// + /// Exists because the Sparkplug primary-host contract's most important leg is the one a + /// normal teardown cannot reach (Gitea #511): DisposeAsync sends a clean + /// DISCONNECT, which by MQTT rule means the broker discards the Will. So an + /// in-suite test driven through the ordinary lifecycle can only ever observe the explicit + /// stand-down OFFLINE, and would pass identically against an implementation whose + /// Will was never armed at all. + /// + /// + /// Not a full substitute for the kill -9 the live gate runs by hand — that also + /// proves the process dies without any of this code running — but it is the closest an + /// in-process test can get, and it is what makes the Will's content observable. + /// + /// + internal async Task AbandonForTests() + { + // Mark disposed first, so the supervisor cannot reconnect into the gap and publish a fresh + // birth on top of the Will the broker is about to deliver. + Interlocked.Exchange(ref _disposed, 1); + SetState(MqttConnectionState.Disposed); + + try + { + await _lifetimeCts.CancelAsync().ConfigureAwait(false); + } + catch (ObjectDisposedException) + { + // Nothing to cancel. + } + + // Dispose WITHOUT DisconnectAsync: MQTTnet closes the channel, the broker sees a dead socket + // rather than a graceful goodbye, and the Will fires. This is the whole point of the seam. + Interlocked.Exchange(ref _client, null)?.Dispose(); + } + private bool Disposed => Volatile.Read(ref _disposed) != 0; /// @@ -568,7 +641,8 @@ public sealed class MqttConnection : IAsyncDisposable, IMqttSubscribeTransport, MqttClientOptions clientOptions; try { - clientOptions = MqttClientOptionsFactory.BuildClientOptions(_options, clientIdSuffix: null, _logger); + clientOptions = MqttClientOptionsFactory.BuildClientOptions( + _options, _clientIdSuffix, _logger, _lastWill, _cleanSessionOverride); } catch (Exception ex) { diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriver.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriver.cs index 4f1e4d54..e8826724 100644 --- a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriver.cs +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriver.cs @@ -185,6 +185,16 @@ public sealed class MqttDriver private MqttConnection? _connection; private CancellationTokenSource? _hostProbeCts; + /// The Primary data-plane verdict the Sparkplug host claim is gated on (Gitea #511). + private readonly IDriverPrimaryRoleSource _primaryRoleSource; + + /// + /// The Sparkplug primary-host claim, or when this configuration does not + /// ask for one. Owns its own broker connection — see for why + /// it cannot share the ingest session. + /// + private SparkplugPrimaryHost? _primaryHost; + private DriverHealth _health = new(DriverState.Unknown, null, null); private HostState _hostState = HostState.Unknown; private DateTime _hostStateChangedUtc = DateTime.UtcNow; @@ -198,7 +208,18 @@ public sealed class MqttDriver /// /// Stable logical id of this driver instance. /// Optional logger; never receives credentials or payload bodies. - public MqttDriver(MqttDriverOptions options, string driverInstanceId, ILogger? logger = null) + /// + /// Gitea #511: the Primary data-plane verdict the Sparkplug primary-host claim is gated on. + /// falls back to — which + /// always claims — for standalone hosts and tests. On a redundant pair that fallback is the + /// dual-claim this gate exists to prevent, so the Host resolves a real one and + /// DriverFactoryBootstrap does so with GetRequiredService. + /// + public MqttDriver( + MqttDriverOptions options, + string driverInstanceId, + ILogger? logger = null, + IDriverPrimaryRoleSource? primaryRoleSource = null) { ArgumentNullException.ThrowIfNull(options); ArgumentException.ThrowIfNullOrWhiteSpace(driverInstanceId); @@ -206,6 +227,7 @@ public sealed class MqttDriver _options = options; _driverInstanceId = driverInstanceId; _logger = logger; + _primaryRoleSource = primaryRoleSource ?? UnmanagedDriverPrimaryRoleSource.Instance; _subscriptions = CreateSubscriptionManager(options); _sparkplug = CreateSparkplugIngestor(options); RegisterAuthoredTags(options); @@ -1001,6 +1023,7 @@ public sealed class MqttDriver WriteHealth(new DriverHealth(DriverState.Healthy, connection.LastMessageUtc, null)); TransitionHost(HostState.Running); StartHostProbe(); + await StartPrimaryHostAsync(cancellationToken).ConfigureAwait(false); } catch (Exception ex) { @@ -1094,21 +1117,15 @@ public sealed class MqttDriver return null; } - if (options.Sparkplug is { ActAsPrimaryHost: true }) + // The flag no longer reads as if it does something it does not (Gitea #511) — but a request it + // CANNOT honour still warns loudly rather than being dropped, because the operator's plant is + // waiting on a STATE message that will never arrive. + if (SparkplugPrimaryHost.DescribeUnusable(options) is { } unusable) { - // Loud, because the flag reads as if it does something. Being a Sparkplug Primary Host is a - // three-part contract — a retained ONLINE after CONNECT, a matching retained OFFLINE - // registered as the MQTT Last Will AT CONNECT TIME, and an explicit OFFLINE on clean - // shutdown — and edge nodes stop publishing while their host is offline. Shipping the - // ONLINE half without the Will is strictly worse than shipping neither: a crashed node - // would leave a retained ONLINE asserting forever that a dead host is alive, which is the - // exact state the mechanism exists to prevent. The Will belongs in - // MqttClientOptionsFactory.BuildClientOptions; until it is there this flag stays inert and said so. _logger?.LogWarning( - "MQTT driver '{DriverId}': Sparkplug actAsPrimaryHost is set but primary-host STATE " - + "publishing is not implemented — this driver observes STATE and never publishes one. " - + "Edge nodes gated on this host id will not see it come online.", - _driverInstanceId); + "MQTT driver '{DriverId}': {Reason} Edge nodes gated on this host id will not see it come online.", + _driverInstanceId, + unusable); } var ingestor = new SparkplugIngestor( @@ -1263,9 +1280,55 @@ public sealed class MqttDriver o.Sparkplug, }; + /// + /// Opens the Sparkplug primary-host claim when this configuration asks for one (Gitea #511). + /// + /// + /// + /// Runs last, and can never fail the initialize. The claim is an advisory assertion + /// to other applications on the broker; the ingest path is this driver's data plane. A + /// broker that accepts the ingest session but rejects a publish on the STATE topic — an ACL + /// that does not grant spBv1.0/STATE/# is the ordinary way this happens — must cost + /// the operator a warning and a plant-visible missing host, not every tag's value. + /// already swallows and retries; the catch + /// here covers the rest so no future edit can turn this into a fault path by accident. + /// + /// + private async Task StartPrimaryHostAsync(CancellationToken cancellationToken) + { + if (!SparkplugPrimaryHost.CanClaim(_options)) + { + return; + } + + try + { + var host = new SparkplugPrimaryHost(_options, _driverInstanceId, _primaryRoleSource, _logger); + _primaryHost = host; + await host.StartAsync(cancellationToken).ConfigureAwait(false); + } + catch (Exception ex) + { + _logger?.LogWarning( + ex, + "MQTT driver '{DriverId}': the Sparkplug primary-host claim could not be started; ingest is unaffected.", + _driverInstanceId); + } + } + /// Shared teardown for , and the session rebuild. private async Task TeardownAsync() { + // Stand the host claim down FIRST, while the broker is still reachable and before the ingest + // session goes. Its explicit retained OFFLINE is what makes the transition immediate for edge + // nodes; leaving it to the Will costs them up to 1.5 keep-alive periods of believing a host + // that has already stopped is still online. + var primaryHost = Interlocked.Exchange(ref _primaryHost, null); + if (primaryHost is not null) + { + await primaryHost.DisposeAsync().ConfigureAwait(false); + } + var probe = Interlocked.Exchange(ref _hostProbeCts, null); if (probe is not null) { diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriverFactoryExtensions.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriverFactoryExtensions.cs index dc6d9bea..cf6dc094 100644 --- a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriverFactoryExtensions.cs +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/MqttDriverFactoryExtensions.cs @@ -49,16 +49,30 @@ public static class MqttDriverFactoryExtensions /// /// The driver factory registry to register with. /// Optional logger factory used to create per-instance loggers. - public static void Register(DriverFactoryRegistry registry, ILoggerFactory? loggerFactory = null) + /// + /// Gitea #511: the Primary data-plane verdict the Sparkplug primary-host claim is gated on, + /// captured at registration time like . Null falls back to + /// (always claims) — correct for a standalone + /// host or a test, and the reason DriverFactoryBootstrap resolves it with + /// GetRequiredService rather than letting a redundant deployment reach that fallback. + /// + public static void Register( + DriverFactoryRegistry registry, + ILoggerFactory? loggerFactory = null, + IDriverPrimaryRoleSource? primaryRoleSource = null) { ArgumentNullException.ThrowIfNull(registry); - registry.Register(DriverTypeName, (id, json) => CreateInstance(id, json, loggerFactory)); + registry.Register(DriverTypeName, (id, json) => CreateInstance(id, json, loggerFactory, primaryRoleSource)); } /// Public for the Server-side bootstrapper + test consumers. /// Stable logical id of the driver instance. /// The DriverConfig JSON blob for the instance. /// Optional logger factory for the per-instance logger. + /// + /// Gitea #511: the Primary data-plane verdict gating the Sparkplug primary-host claim; null + /// falls back to . + /// /// A configured, not-yet-connected . /// /// or is blank. @@ -68,7 +82,8 @@ public static class MqttDriverFactoryExtensions public static MqttDriver CreateInstance( string driverInstanceId, string driverConfigJson, - ILoggerFactory? loggerFactory = null) + ILoggerFactory? loggerFactory = null, + IDriverPrimaryRoleSource? primaryRoleSource = null) { ArgumentException.ThrowIfNullOrWhiteSpace(driverInstanceId); ArgumentException.ThrowIfNullOrWhiteSpace(driverConfigJson); @@ -79,6 +94,7 @@ public static class MqttDriverFactoryExtensions ?? throw new InvalidOperationException( $"MQTT driver config for '{driverInstanceId}' deserialised to null"); - return new MqttDriver(options, driverInstanceId, loggerFactory?.CreateLogger()); + return new MqttDriver( + options, driverInstanceId, loggerFactory?.CreateLogger(), primaryRoleSource); } } diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugIngestor.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugIngestor.cs index a5c294ef..91b0836d 100644 --- a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugIngestor.cs +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugIngestor.cs @@ -73,9 +73,11 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Sparkplug; /// subscriber is contained, and the rebirth publish is dispatched off-thread. /// /// -/// Primary-host STATE publishing is deliberately NOT implemented — see -/// and the remarks on -/// . This type observes STATE; it never publishes one. +/// This type only ever observes STATE. Primary-host STATE publishing ships +/// (Gitea #511) but deliberately does not live here: the claim is bound to the lifetime of its +/// own dedicated connection, because an MQTT Will can only be registered at CONNECT. See +/// , and the remarks on for what +/// this side does with an observed one. /// /// public sealed class SparkplugIngestor @@ -1029,18 +1031,17 @@ public sealed class SparkplugIngestor /// /// /// - /// Receive only. This driver never publishes STATE, and - /// is therefore inert — deliberately, and - /// loudly. Being a Sparkplug Primary Host is not "publish an ONLINE message": it is a - /// three-part contract — a retained ONLINE STATE published after CONNECT, a matching - /// retained OFFLINE registered as the client's MQTT Last Will at CONNECT time, - /// and an explicit OFFLINE on clean shutdown. Edge nodes subscribe to it and stop publishing - /// while their host is offline. Shipping the ONLINE half without the Will is strictly worse - /// than shipping neither: an OtOpcUa node that crashes would leave a retained ONLINE asserting - /// forever that a dead host is alive, which is precisely the state the mechanism exists to - /// prevent. The Will has to be set inside MqttClientOptionsFactory.BuildClientOptions — a - /// different file, a different task — so this task implements the observation half and - /// warns when the flag is set. See the design doc §7/§8. + /// Receive only, on this connection. The publish half ships as + /// (Gitea #511), on a connection of its own — an MQTT Will + /// can only be registered in the CONNECT packet, so a claim that is acquired and released at + /// runtime cannot ride the long-lived ingest session this type is attached to. + /// + /// + /// A host claimed by THIS node is observed here too, and that is correct rather than an + /// oversight. The ingestor subscribes the configured host id whether or not this node + /// publishes it, so a node acting as primary host sees its own retained ONLINE come + /// back. Nothing here gates on it — is informational — so the + /// echo costs one log line at the transition and cannot feed back into the claim. /// /// /// Both payload forms are accepted on receive: the v3.0 JSON {"online":bool,...} and diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugPrimaryHost.cs b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugPrimaryHost.cs new file mode 100644 index 00000000..7911c872 --- /dev/null +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/Sparkplug/SparkplugPrimaryHost.cs @@ -0,0 +1,470 @@ +using Microsoft.Extensions.Logging; +using ZB.MOM.WW.OtOpcUa.Core.Abstractions; + +namespace ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Sparkplug; + +/// +/// Claims the Sparkplug Primary Host Application identity for this node — the three-part contract +/// promises and, until Gitea #511, did not +/// deliver: a retained ONLINE while the claim is held, a matching retained OFFLINE +/// registered as the MQTT Last Will, and an explicit OFFLINE on a clean stand-down. +/// +/// +/// +/// The claim is a whole dedicated connection, not a message. A Will can only be +/// registered in the CONNECT packet (see ), so a claim that must be +/// acquired and released at runtime cannot live on the driver's shared ingest session — that +/// session connects once and stays up, and its Will could be neither added on gaining the role +/// nor withdrawn on losing it. This type therefore opens its own connection when the +/// node gains Primary and closes it when the node loses Primary. The connection's lifetime +/// is the claim, which is what makes every leg of the contract fall out for free: +/// +/// the Will is registered because the connection was opened to hold the claim; +/// a kill -9 drops the connection, so the broker publishes the Will; +/// a clean stand-down publishes OFFLINE and then disconnects, so the retained +/// message is correct before the Will could ever fire. +/// +/// +/// +/// Why not rebuild the ingest connection instead. That was the shape first sketched on +/// the issue, and it works, but it drops every subscription and the whole birth cache on each +/// role change — producing a data gap on the Secondary→Primary transition, which is precisely +/// the moment a plant most needs values flowing. A second connection costs one extra client id +/// and leaves ingest untouched. +/// +/// +/// Primary-gated, by owner decision (2026-07-31). Both nodes of a redundant pair +/// subscribe independently — MQTT fan-out is per-connection and the Primary gate applies +/// downstream of ingest — so without gating, both would claim the same host id. The sharp +/// failure is not the two fighting over the retained STATE: it is that the +/// Secondary's death would publish OFFLINE, edge nodes would stop publishing, +/// and the surviving Primary would be perfectly healthy throughout. Redundancy would cause the +/// outage the mechanism exists to prevent. The gate is +/// , sampled on a timer. +/// +/// +/// Accepted trade: a brief edge-visible OFFLINE window during failover, while the +/// old Primary stands down and the new one connects and republishes. That is a genuine state +/// transition — for a window there really is no host — not a glitch to paper over. +/// +/// +/// Reconnect re-asserts the claim. The dedicated connection carries the same supervisor +/// as the ingest one, and Reconnected republishes the birth. Without that, a broker +/// restart would leave the host connected but its retained ONLINE gone — a live host +/// invisible to every edge node, with nothing in any log to say so. +/// +/// +public sealed class SparkplugPrimaryHost : IAsyncDisposable +{ + /// + /// Appended to the driver's configured client id for the STATE connection. Two MQTT clients + /// presenting one client id is not reported as an error — the broker silently evicts the older + /// one — so ingest and the host claim would take turns killing each other forever. + /// + internal const string ClientIdSuffix = "-spbhost"; + + /// How often the role gate is sampled. Bounds the failover republish latency. + private static readonly TimeSpan RoleSampleInterval = TimeSpan.FromSeconds(1); + + private readonly MqttDriverOptions _options; + private readonly string _hostId; + private readonly string _driverId; + private readonly IDriverPrimaryRoleSource _roleSource; + private readonly ILogger? _logger; + private readonly TimeProvider _timeProvider; + + /// Serializes claim/release against each other and against . + private readonly SemaphoreSlim _gate = new(1, 1); + + private CancellationTokenSource? _loopCts; + + /// The live claim, or null when this node is not currently the primary host. + private MqttConnection? _connection; + + /// The session bodies backing ; non-null exactly when it is. + private SparkplugStateSession? _session; + + private int _disposed; + + /// Creates a primary-host claim. Opens nothing — does that. + /// Broker connection settings; the host id comes from its Sparkplug section. + /// Driver instance id, for log correlation. + /// The Primary data-plane verdict this claim is gated on. + /// Optional logger. + /// Clock seam; defaults to . + /// + /// The options carry no Sparkplug host id — exists so a caller never has + /// to hit this. + /// + public SparkplugPrimaryHost( + MqttDriverOptions options, + string driverId, + IDriverPrimaryRoleSource roleSource, + ILogger? logger = null, + TimeProvider? timeProvider = null) + { + ArgumentNullException.ThrowIfNull(options); + ArgumentException.ThrowIfNullOrWhiteSpace(driverId); + ArgumentNullException.ThrowIfNull(roleSource); + + var hostId = options.Sparkplug?.HostId; + if (string.IsNullOrWhiteSpace(hostId)) + { + throw new ArgumentException( + "A Sparkplug primary-host claim needs a hostId; check CanClaim first.", nameof(options)); + } + + _options = options; + _hostId = hostId.Trim(); + _driverId = driverId; + _roleSource = roleSource; + _logger = logger; + _timeProvider = timeProvider ?? TimeProvider.System; + } + + /// + /// Whether asks for — and can support — a primary-host claim: + /// Sparkplug mode, actAsPrimaryHost set, and a non-blank hostId. + /// + /// The driver options to test. + /// when a claim should be made. + /// + /// The blank-host-id case is a configuration error the AdminUI form already refuses, but the + /// driver must not fault on it: the config could have been authored before that validation + /// existed. It is reported by and the flag is treated as off. + /// + public static bool CanClaim(MqttDriverOptions options) => + options is { Mode: MqttMode.SparkplugB, Sparkplug: { ActAsPrimaryHost: true } spb } + && !string.IsNullOrWhiteSpace(spb.HostId); + + /// + /// Describes why an actAsPrimaryHost request cannot be honoured, or null when it can be + /// (or was never made). + /// + /// The driver options to test. + /// An operator-facing reason, or . + public static string? DescribeUnusable(MqttDriverOptions options) + { + if (options?.Sparkplug is not { ActAsPrimaryHost: true } spb) + { + return null; + } + + if (options.Mode != MqttMode.SparkplugB) + { + return "actAsPrimaryHost is set but the driver is not in SparkplugB mode; there is no host state to publish."; + } + + return string.IsNullOrWhiteSpace(spb.HostId) + ? "actAsPrimaryHost is set but hostId is blank; a host claim has no topic to publish on." + : null; + } + + /// The STATE topic this claim publishes on. + public string StateTopic => SparkplugTopic.FormatState(_hostId); + + /// + /// Whether the claim is currently held — i.e. a retained ONLINE has been published and a + /// Will is armed behind it. + /// + public bool IsClaimed => Volatile.Read(ref _connection) is not null; + + /// + /// Test seam: how many times a claim connect has been attempted, successful or not. + /// Always ignored in production. + /// + /// + /// Without this, "a Secondary does not claim" is a vacuous assertion. The obvious test — + /// start a Secondary and assert is false — passes identically whether + /// the gate works or whether the gate is deleted and the connect simply fails against a broker + /// the test cannot reach. Counting attempts separates "did not try" from "tried and failed", + /// which is the whole distinction the gate is. + /// + internal int ClaimAttemptsForTests => Volatile.Read(ref _claimAttempts); + + private int _claimAttempts; + + /// + /// Test seam: kills the claim connection the way a crashed process does — no clean + /// DISCONNECT and no explicit stand-down publish — so the broker delivers the Last Will. + /// See for why this cannot be reached through the + /// ordinary lifecycle. + /// + /// A task completing once the connection is gone. + internal async Task AbandonClaimForTests() + { + // Stop the reconcile loop first, or the next tick sees no connection, decides the claim is + // lost, and re-claims — republishing ONLINE over the Will this is meant to observe. + var loop = Interlocked.Exchange(ref _loopCts, null); + if (loop is not null) + { + await loop.CancelAsync().ConfigureAwait(false); + loop.Dispose(); + } + + var connection = Interlocked.Exchange(ref _connection, null); + _session = null; + if (connection is not null) + { + await connection.AbandonForTests().ConfigureAwait(false); + } + } + + /// + /// Starts the role-reconcile loop. Returns once the first reconcile has run, so a caller that + /// starts as Primary has published its ONLINE before this completes. + /// + /// Cancels the initial reconcile. + /// A task completing after the first reconcile. + public async Task StartAsync(CancellationToken cancellationToken) + { + ObjectDisposedException.ThrowIf(Volatile.Read(ref _disposed) != 0, this); + + var cts = new CancellationTokenSource(); + var previous = Interlocked.Exchange(ref _loopCts, cts); + if (previous is not null) + { + await previous.CancelAsync().ConfigureAwait(false); + previous.Dispose(); + } + + // Reconcile once inline. A failure here is logged and swallowed, never rethrown: the driver's + // ingest path is the data plane, and refusing to start it because a broker would not accept a + // host claim would trade every tag's value for an advisory message. The loop retries. + await ReconcileAsync(cancellationToken).ConfigureAwait(false); + + _ = Task.Run(() => ReconcileLoopAsync(cts.Token), CancellationToken.None); + } + + /// + /// Stands the claim down cleanly: publishes an explicit retained OFFLINE, then + /// disconnects. Idempotent, and safe to call when no claim is held. + /// + /// Bounds the stand-down publish. + /// A task completing when the claim is released. + public async Task StopAsync(CancellationToken cancellationToken) + { + var loop = Interlocked.Exchange(ref _loopCts, null); + if (loop is not null) + { + await loop.CancelAsync().ConfigureAwait(false); + loop.Dispose(); + } + + await ReleaseAsync("shutdown", cancellationToken).ConfigureAwait(false); + } + + /// + public async ValueTask DisposeAsync() + { + if (Interlocked.Exchange(ref _disposed, 1) != 0) + { + return; + } + + // Bounded: dispose must not hang on an unreachable broker. A stand-down we cannot publish is + // covered by the Will the moment the socket closes, which is the whole point of having one. + using var deadline = new CancellationTokenSource(TimeSpan.FromSeconds(_options.ConnectTimeoutSeconds)); + try + { + await StopAsync(deadline.Token).ConfigureAwait(false); + } + catch (Exception ex) + { + _logger?.LogDebug( + ex, "MQTT driver '{DriverId}': Sparkplug primary-host stand-down failed during dispose.", _driverId); + } + + _gate.Dispose(); + } + + private async Task ReconcileLoopAsync(CancellationToken ct) + { + try + { + while (!ct.IsCancellationRequested) + { + await Task.Delay(RoleSampleInterval, _timeProvider, ct).ConfigureAwait(false); + await ReconcileAsync(ct).ConfigureAwait(false); + } + } + catch (OperationCanceledException) + { + // Shutdown. + } + catch (Exception ex) + { + // The loop must not die silently — a dead loop means the claim freezes in whatever state + // it was last in, including "claimed by a node that is no longer Primary". + _logger?.LogError( + ex, "MQTT driver '{DriverId}': Sparkplug primary-host reconcile loop stopped.", _driverId); + } + } + + /// + /// Brings the held claim into line with the current role verdict. Never throws — a transient + /// broker failure leaves the claim as it was and the next tick tries again. + /// + private async Task ReconcileAsync(CancellationToken cancellationToken) + { + try + { + if (_roleSource.ShouldActAsPrimary) + { + await ClaimAsync(cancellationToken).ConfigureAwait(false); + } + else + { + await ReleaseAsync("this node is not the redundancy Primary", cancellationToken).ConfigureAwait(false); + } + } + catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested) + { + throw; + } + catch (Exception ex) + { + _logger?.LogWarning( + ex, + "MQTT driver '{DriverId}': could not reconcile the Sparkplug primary-host claim for '{HostId}'; will retry.", + _driverId, + _hostId); + } + } + + private async Task ClaimAsync(CancellationToken cancellationToken) + { + if (Volatile.Read(ref _connection) is not null) + { + return; // Already held; the connection's own supervisor keeps it that way. + } + + await _gate.WaitAsync(cancellationToken).ConfigureAwait(false); + try + { + if (_connection is not null || Volatile.Read(ref _disposed) != 0) + { + return; + } + + Interlocked.Increment(ref _claimAttempts); + + // ONE timestamp for both bodies — the Will is built here, before CONNECT, and the birth + // published after CONNACK. See SparkplugStatePayload's remarks on why they must match. + var session = SparkplugStatePayload.ForSession( + _hostId, _timeProvider.GetUtcNow().ToUnixTimeMilliseconds()); + + var connection = new MqttConnection( + _options, + _driverId, + _logger, + clientIdSuffix: ClientIdSuffix, + lastWill: new MqttLastWill( + session.Topic, session.OfflineBody, SparkplugStatePayload.StateQos, Retain: true), + // Forced clean, ignoring the driver's configured value: a broker that resumes a prior + // session for this client id may keep the OLD session's Will and discard the one this + // CONNECT carries — leaving a claim with no death certificate behind it, which is the + // single state this whole mechanism exists to make impossible. + cleanSessionOverride: true); + + // Re-assert on every reconnect. A broker restart drops retained messages; without this the + // host would be connected and believed offline by every edge node, silently. + connection.Reconnected += async ct => + { + await connection.PublishAsync( + session.Topic, session.OnlineBody, SparkplugStatePayload.StateQos, retain: true, ct) + .ConfigureAwait(false); + + _logger?.LogInformation( + "MQTT driver '{DriverId}': re-published Sparkplug primary-host ONLINE for '{HostId}' after reconnect.", + _driverId, + _hostId); + }; + + await connection.ConnectAsync(cancellationToken).ConfigureAwait(false); + + try + { + await connection.PublishAsync( + session.Topic, session.OnlineBody, SparkplugStatePayload.StateQos, retain: true, cancellationToken) + .ConfigureAwait(false); + } + catch + { + // A connection whose birth never landed is worse than no connection: it holds a Will + // that will publish OFFLINE for a claim that was never asserted, and it looks claimed + // to IsClaimed. Tear it down and let the next tick retry from scratch. + await connection.DisposeAsync().ConfigureAwait(false); + throw; + } + + _session = session; + Volatile.Write(ref _connection, connection); + + _logger?.LogInformation( + "MQTT driver '{DriverId}': claimed Sparkplug primary host '{HostId}' — retained ONLINE published on '{Topic}', " + + "OFFLINE armed as the Last Will.", + _driverId, + _hostId, + session.Topic); + } + finally + { + _gate.Release(); + } + } + + private async Task ReleaseAsync(string reason, CancellationToken cancellationToken) + { + if (Volatile.Read(ref _connection) is null) + { + return; + } + + await _gate.WaitAsync(CancellationToken.None).ConfigureAwait(false); + try + { + var connection = Interlocked.Exchange(ref _connection, null); + var session = _session; + _session = null; + if (connection is null || session is null) + { + return; + } + + try + { + // Explicit OFFLINE before disconnecting. The Will would eventually say the same thing, + // but only after the broker's keep-alive timeout notices the socket is gone — up to + // 1.5 keep-alive periods of edge nodes believing a host that has already stood down is + // still online. Publishing it makes the transition immediate. + await connection.PublishAsync( + session.Topic, session.OfflineBody, SparkplugStatePayload.StateQos, retain: true, cancellationToken) + .ConfigureAwait(false); + + _logger?.LogInformation( + "MQTT driver '{DriverId}': released Sparkplug primary host '{HostId}' ({Reason}) — retained OFFLINE published.", + _driverId, + _hostId, + reason); + } + catch (Exception ex) + { + // Not fatal, and not silent. The Will still covers this: dropping the connection below + // makes the broker publish the identical OFFLINE body. The only thing lost is promptness. + _logger?.LogWarning( + ex, + "MQTT driver '{DriverId}': could not publish the Sparkplug primary-host OFFLINE for '{HostId}'; " + + "the Last Will will deliver it when the session drops.", + _driverId, + _hostId); + } + + await connection.DisposeAsync().ConfigureAwait(false); + } + finally + { + _gate.Release(); + } + } +} diff --git a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.csproj b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.csproj index 79edc634..2a88db4e 100644 --- a/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.csproj +++ b/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.csproj @@ -25,6 +25,10 @@ + + diff --git a/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverForm.razor b/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverForm.razor index cb18f6bc..bef3d0d3 100644 --- a/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverForm.razor +++ b/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverForm.razor @@ -225,7 +225,7 @@
-
Sparkplug Host Application identity. Receive-only in this version.
+
Sparkplug Host Application identity — the spBv1.0/STATE/{hostId} topic. Required to act as Primary Host.
@@ -237,25 +237,42 @@
@if (_form.SparkplugActAsPrimaryHost) { - @* Shown rather than the flag being hidden: an operator who needs a primary host must - learn it is absent HERE, not from a plant that never sees a STATE message. The - driver logs the same warning at startup so the two cannot drift. *@ -
- + } + else + { +
+ +
+ } }
@@ -263,7 +280,6 @@ Sparkplug tags bind by the group / edge node / device / metric tuple, not by topic — author them with Browse device… on a device under this driver, which builds its tree from observed birth certificates. - MQTT tags are read-only (write-through is not implemented).
} diff --git a/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverFormModel.cs b/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverFormModel.cs index a003bc63..ebc3c40f 100644 --- a/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverFormModel.cs +++ b/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/MqttDriverFormModel.cs @@ -142,17 +142,23 @@ public sealed class MqttDriverFormModel public string SparkplugGroupId { get; set; } = ""; /// - /// Sparkplug mode: the Host Application identity. Optional, and receive-only in this - /// version — see . + /// Sparkplug mode: the Host Application identity — the spBv1.0/STATE/{hostId} topic the + /// driver observes, and publishes on when is set. + /// Optional for observation; required to claim. /// public string SparkplugHostId { get; set; } = ""; /// - /// Sparkplug mode: claim the Primary Host Application role. Not implemented — STATE - /// publishing is out of scope, and the driver logs a warning rather than being silently inert - /// when this is set. Surfaced (rather than hidden) so an operator who needs it learns that from - /// the form instead of from a quiet plant. + /// Sparkplug mode: claim the Primary Host Application role (Gitea #511) — a retained + /// ONLINE, a matching OFFLINE armed as the MQTT Last Will, and an explicit + /// OFFLINE on clean shutdown. /// + /// + /// Primary-gated: only the node holding the redundancy Primary role claims it, so the two + /// nodes of a pair cannot fight over one host id. At most one primary host may exist per host id + /// per broker, which the form states — it is not enforceable from here, since a second + /// deployment pointing at the same broker is invisible to this one. + /// public bool SparkplugActAsPrimaryHost { get; set; } /// Sparkplug mode: answer a detected sequence-number gap with a rebirth request (NCMD). diff --git a/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/SparkplugPrimaryHostAdvice.cs b/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/SparkplugPrimaryHostAdvice.cs new file mode 100644 index 00000000..1601d9aa --- /dev/null +++ b/src/Server/ZB.MOM.WW.OtOpcUa.AdminUI/Components/Shared/Drivers/Forms/SparkplugPrimaryHostAdvice.cs @@ -0,0 +1,35 @@ +namespace ZB.MOM.WW.OtOpcUa.AdminUI.Components.Shared.Drivers.Forms; + +/// +/// The rule deciding which primary-host advisory MqttDriverForm shows when +/// Act as Primary Host is on (Gitea #511). +/// +/// +/// +/// A plain static rather than markup logic, because this repo has no bUnit. A condition +/// written inline in a .razor file is unreachable from any test, and the failure mode +/// here is specific: an operator who ticks the box with a blank host id must see a +/// refusal, not the ordinary "here is what will happen" note. Getting that backwards +/// tells them a claim is being made when the driver is in fact declining to make one. +/// +/// +/// Deliberately mirrors SparkplugPrimaryHost.DescribeUnusable's blank-host-id arm. The +/// mode arm is not duplicated: this panel only renders inside the SparkplugB branch of the +/// form, so mode cannot be wrong here. +/// +/// +public static class SparkplugPrimaryHostAdvice +{ + /// + /// Describes why a primary-host claim cannot be made for , or + /// when it can. + /// + /// The Sparkplug host id as typed into the form. + /// An operator-facing reason, or . + public static string? DescribeBlockingProblem(string? hostId) => + string.IsNullOrWhiteSpace(hostId) + ? "A Sparkplug host claim is published on spBv1.0/STATE/{hostId}, so it needs a Host ID. " + + "Set one above, or turn this off — the driver will otherwise log a warning at startup " + + "and publish nothing." + : null; +} diff --git a/src/Server/ZB.MOM.WW.OtOpcUa.Host/Drivers/DriverFactoryBootstrap.cs b/src/Server/ZB.MOM.WW.OtOpcUa.Host/Drivers/DriverFactoryBootstrap.cs index 3b743031..29037bfe 100644 --- a/src/Server/ZB.MOM.WW.OtOpcUa.Host/Drivers/DriverFactoryBootstrap.cs +++ b/src/Server/ZB.MOM.WW.OtOpcUa.Host/Drivers/DriverFactoryBootstrap.cs @@ -55,7 +55,16 @@ public static class DriverFactoryBootstrap // The Galaxy driver resolves its Gateway.ApiKeySecretRef secret: arm through the // shared ISecretResolver (registered unconditionally by AddZbSecrets on every node). var secretResolver = sp.GetRequiredService(); - Register(registry, loggerFactory, secretResolver, scriptRoot); + // Gitea #511: the MQTT driver's Sparkplug primary-host claim is Primary-gated, and unlike + // every other gated operation it is a STANDING assertion on the driver's own connection — + // there is no inbound message for DriverHostActor to intercept — so the verdict has to + // reach the driver itself. Registered unconditionally on driver-role nodes by + // AddOtOpcUaRuntime. GetRequiredService, not GetService: a null here silently falls the + // driver back to "claim unconditionally", which on a redundant pair is the dual-claim this + // whole mechanism exists to prevent, and it would fail as a plant outage rather than as a + // startup error. + var primaryRoleSource = sp.GetRequiredService(); + Register(registry, loggerFactory, secretResolver, primaryRoleSource, scriptRoot); return registry; }); services.AddSingleton(sp => @@ -142,6 +151,7 @@ public static class DriverFactoryBootstrap DriverFactoryRegistry registry, ILoggerFactory? loggerFactory, ISecretResolver secretResolver, + IDriverPrimaryRoleSource primaryRoleSource, ZB.MOM.WW.OtOpcUa.Core.Scripting.ScriptRootLogger? scriptRoot = null) { Driver.AbCip.AbCipDriverFactoryExtensions.Register(registry); @@ -150,7 +160,7 @@ public static class DriverFactoryBootstrap Driver.FOCAS.FocasDriverFactoryExtensions.Register(registry); Driver.Galaxy.GalaxyDriverFactoryExtensions.Register(registry, secretResolver, loggerFactory); Driver.Modbus.ModbusDriverFactoryExtensions.Register(registry, loggerFactory); - Driver.Mqtt.MqttDriverFactoryExtensions.Register(registry, loggerFactory); + Driver.Mqtt.MqttDriverFactoryExtensions.Register(registry, loggerFactory, primaryRoleSource); // Tier A (the Register default): fully managed — HttpClient + System.Xml.Linq, no native SDK, // no COM. Tier C is the only tier that arms process-level recycle (MemoryRecycle hard-breach / // ScheduledRecycleScheduler), which would be wrong here: the driver is in-process and killing diff --git a/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Drivers/DriverHostActor.cs b/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Drivers/DriverHostActor.cs index 5359cfa5..6d257dbd 100644 --- a/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Drivers/DriverHostActor.cs +++ b/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Drivers/DriverHostActor.cs @@ -273,6 +273,19 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers /// today, the alarm store-and-forward drain. Null on nodes that do not wire one. private readonly IRedundancyRoleView? _redundancyRoleView; + /// + /// Where the Primary data-plane verdict is published for drivers that must know it + /// directly (Gitea #511). Null on nodes that wire no redundancy manager. + /// + /// + /// Note the different verdict from : that one carries + /// , which OPENS on an unknown role. A + /// Sparkplug host-id claim is an exclusive assertion on a shared broker, so it takes the + /// data-plane verdict, which closes. Publishing the drain verdict here would let both nodes of + /// a pair claim the host id during every boot window. + /// + private readonly IDriverPrimaryRoleSource? _primaryRoleSource; + /// /// Host of this node's LocalDb replication partner — the only node that holds a copy of this /// node's alarm queue, and therefore the only node it may ever stand down in favour of. @@ -408,7 +421,8 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers bool fetchAndCacheMode = false, IDeploymentArtifactFetcher? artifactFetcher = null, IAlarmStateStore? alarmStateStore = null, - ITelemetryLocalHub? telemetryHub = null) => + ITelemetryLocalHub? telemetryHub = null, + IDriverPrimaryRoleSource? primaryRoleSource = null) => // WARNING: this forwarding list is POSITIONAL, and Props.Create compiles it into an // expression tree. Six IActorRef? parameters and several interface-typed ones mean a // mis-ordered argument is usually type-compatible and therefore compiles clean, then binds @@ -419,7 +433,7 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers healthPublisher, virtualTagEvaluator, historyWriter, virtualTagHostOverride, loggerFactory, scriptRootLogger, scriptedAlarmHostOverride, invokerFactory, driverMemberCountProvider, deploymentArtifactCache, redundancyRoleView, replicationPeerHost, fetchAndCacheMode, artifactFetcher, - alarmStateStore, telemetryHub)); + alarmStateStore, telemetryHub, primaryRoleSource)); /// Initializes a new DriverHostActor with the specified dependencies. /// Database context factory for configuration database access. @@ -460,6 +474,12 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers /// Per-cluster mesh Phase 5: optional node-local live-telemetry hub each /// Primary-gated native-alarm transition is also emitted into, and which is threaded into the spawned /// VirtualTag + ScriptedAlarm hosts. Null (admin-only nodes / tests) skips the emit and passes null down. + /// Gitea #511: where the Primary data-plane verdict is published + /// for drivers that assert a standing exclusive identity on a shared external system — today the MQTT + /// driver's Sparkplug primary-host STATE claim. Deliberately a separate parameter from + /// even though the production object implements both: a test that + /// supplies only a role-view double must not silently also satisfy this, or its primary-role assertions + /// pass without the publish ever happening. Null on nodes that wire no redundancy manager. public DriverHostActor( IDbContextFactory? dbFactory, CommonsNodeId localNode, @@ -483,11 +503,13 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers bool fetchAndCacheMode = false, IDeploymentArtifactFetcher? artifactFetcher = null, IAlarmStateStore? alarmStateStore = null, - ITelemetryLocalHub? telemetryHub = null) + ITelemetryLocalHub? telemetryHub = null, + IDriverPrimaryRoleSource? primaryRoleSource = null) { _telemetryHub = telemetryHub; _deploymentArtifactCache = deploymentArtifactCache; _redundancyRoleView = redundancyRoleView; + _primaryRoleSource = primaryRoleSource; _replicationPeerHost = replicationPeerHost; _fetchAndCacheMode = fetchAndCacheMode; _artifactFetcher = artifactFetcher; @@ -1331,6 +1353,12 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers _redundancyRoleView?.Publish( PrimaryGatePolicy.ShouldDrainAlarmHistory(_localRole, queueSharingPeerIsPrimary: peerIsPrimary)); + + // The DATA-PLANE verdict, deliberately — the same one HandleRouteNodeWrite gates on, not the + // drain verdict published immediately above. A driver reading this claims an exclusive identity + // on a shared external system (Gitea #511: the Sparkplug host id), where two claimants is the + // harm, so an unknown role with a driver peer present must deny. + _primaryRoleSource?.PublishPrimaryRole(ShouldServiceAsPrimary()); } private void Stale() diff --git a/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Redundancy/IRedundancyRoleView.cs b/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Redundancy/IRedundancyRoleView.cs index a9c41dff..b450e9e2 100644 --- a/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Redundancy/IRedundancyRoleView.cs +++ b/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/Redundancy/IRedundancyRoleView.cs @@ -1,3 +1,4 @@ +using ZB.MOM.WW.OtOpcUa.Core.Abstractions; using ZB.MOM.WW.OtOpcUa.Runtime.Drivers; namespace ZB.MOM.WW.OtOpcUa.Runtime.Redundancy; @@ -39,8 +40,22 @@ public interface IRedundancyRoleView void Publish(bool shouldDrainAlarmHistory); } -/// Thread-safe backed by a volatile field. -public sealed class RedundancyRoleView : IRedundancyRoleView +/// +/// Thread-safe + , each +/// backed by its own volatile field. +/// +/// +/// +/// Two verdicts, one object, on purpose. Both are published from the same +/// DriverHostActor snapshot handler and both are read off-actor, so a second class +/// would duplicate the publish plumbing to hold a second bool. They are kept as distinct +/// properties rather than collapsed into one because they are genuinely different +/// decisions from different policies — see 's remarks on why +/// the drain gate must open on an unknown role where the data-plane gate closes. Collapsing +/// them is the bug that live gate already found once. +/// +/// +public sealed class RedundancyRoleView : IRedundancyRoleView, IDriverPrimaryRoleSource { // Seeded with the decision for "role unknown" rather than a bare false. An unpublished view and a // node whose role nothing ever reports are genuinely the same situation, and they must behave the @@ -49,9 +64,22 @@ public sealed class RedundancyRoleView : IRedundancyRoleView private volatile bool _shouldDrainAlarmHistory = PrimaryGatePolicy.ShouldDrainAlarmHistory(localRole: null, queueSharingPeerIsPrimary: false); + // Seeded from the same policy that will later publish here, for the unknown-role/no-peer case: + // a node nothing has reported a role for, on a cluster with no driver peer, is a single-node + // deployment and may claim. The moment a snapshot arrives this is replaced by the real verdict, + // and a multi-driver cluster's unknown role denies. + private volatile bool _shouldActAsPrimary = + PrimaryGatePolicy.ShouldServiceAsPrimary(localRole: null, driverMemberCount: 1); + /// public bool ShouldDrainAlarmHistory => _shouldDrainAlarmHistory; + /// + public bool ShouldActAsPrimary => _shouldActAsPrimary; + /// public void Publish(bool shouldDrainAlarmHistory) => _shouldDrainAlarmHistory = shouldDrainAlarmHistory; + + /// + public void PublishPrimaryRole(bool shouldActAsPrimary) => _shouldActAsPrimary = shouldActAsPrimary; } diff --git a/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/ServiceCollectionExtensions.cs b/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/ServiceCollectionExtensions.cs index 12648380..793088f0 100644 --- a/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/ServiceCollectionExtensions.cs +++ b/src/Server/ZB.MOM.WW.OtOpcUa.Runtime/ServiceCollectionExtensions.cs @@ -75,6 +75,22 @@ public static class ServiceCollectionExtensions // telemetry (never DPS) to the Phase-5 gRPC streaming service central dials in on. AddOtOpcUaRuntime // runs only inside Program.cs's hasDriver block, so this lands on driver-role nodes only. services.TryAddSingleton(); + + // Gitea #511: the Primary data-plane verdict, published for drivers that assert a standing + // exclusive identity on a shared external system (today the MQTT driver's Sparkplug host id). + // + // Registered HERE, unconditionally on every driver-role node, and NOT alongside the alarm + // drain's IRedundancyRoleView — which AddAlarmHistorian registers only when that section is + // enabled. Piggybacking on it would leave a redundant pair with no alarm historian configured + // with no primary-role source at all, and the driver's documented no-source fallback is + // "claim" — so both nodes of that pair would claim the same host id and their Wills would + // fight over the retained STATE. Exactly the failure #511 exists to prevent, reached by a + // registration accident in an unrelated section. + // + // Both interfaces are forwarded to ONE RedundancyRoleView instance, so a node that has both + // publishes two verdicts into the same object rather than into two that disagree. + services.TryAddSingleton(); + services.TryAddSingleton(sp => sp.GetRequiredService()); return services; } @@ -117,8 +133,10 @@ public static class ServiceCollectionExtensions // The view is a plain singleton so it exists even on nodes whose DriverHostActor never // publishes to it — an unpublished view reads as "no peer, drain", which is the correct - // posture for a deployment that runs no redundancy at all. - services.TryAddSingleton(); + // posture for a deployment that runs no redundancy at all. Forwarded to the same instance + // AddOtOpcUaRuntime registered for IDriverPrimaryRoleSource: one object, two verdicts. + services.TryAddSingleton(); + services.TryAddSingleton(sp => sp.GetRequiredService()); // THE GATE ONLY APPLIES TO A REPLICATED QUEUE. Standing down is only ever safe because some // other node holds the same rows and will send them instead — and the only node that does is @@ -499,7 +517,11 @@ public static class ServiceCollectionExtensions // Phase 5: the node-local live-telemetry hub (registered in AddOtOpcUaRuntime). The host // emits its Primary-gated native-alarm transitions into it and threads it into the // VirtualTag + ScriptedAlarm hosts it spawns. - telemetryHub: resolver.GetService()), + telemetryHub: resolver.GetService(), + // Gitea #511: where this actor publishes its Primary DATA-PLANE verdict for drivers + // that claim an exclusive external identity. Registered unconditionally by + // AddOtOpcUaRuntime, unlike redundancyRoleView above — see the comment there. + primaryRoleSource: resolver.GetService()), DriverHostActorName); registry.Register(driverHost); diff --git a/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.IntegrationTests/MqttPrimaryHostLiveTests.cs b/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.IntegrationTests/MqttPrimaryHostLiveTests.cs new file mode 100644 index 00000000..fc9f6825 --- /dev/null +++ b/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.IntegrationTests/MqttPrimaryHostLiveTests.cs @@ -0,0 +1,379 @@ +using System.Buffers; +using System.Collections.Concurrent; +using MQTTnet; +using Shouldly; +using Xunit; +using ZB.MOM.WW.OtOpcUa.Core.Abstractions; +using ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Sparkplug; + +namespace ZB.MOM.WW.OtOpcUa.Driver.Mqtt.IntegrationTests; + +/// +/// Live gate for the Sparkplug primary-host claim (Gitea #511), against the Mosquitto fixture. +/// +/// +/// +/// The issue's acceptance criteria, leg by leg: the broker holds a retained ONLINE while +/// the claim runs; an abrupt death leaves OFFLINE (the Will fires); a clean shutdown +/// leaves OFFLINE; and the pair-node question is answered rather than left to chance — +/// a node that is not Primary claims nothing, and a role change moves the claim. +/// +/// +/// Each test uses its own host id. A Sparkplug host id is a broker-wide singleton by +/// definition, and the retained STATE outlives the test that wrote it — two tests sharing an id +/// would see each other's leftovers, and would do so intermittently depending on ordering. +/// +/// +/// Retained messages are cleaned up. A retained ONLINE for a host that no longer +/// exists is exactly the lie this feature prevents, so leaving one on a shared fixture would be +/// poor manners at best and a confusing false positive for the next run at worst. +/// +/// +[Trait("Category", "Integration")] +[Collection("MqttFixture")] +public sealed class MqttPrimaryHostLiveTests(MqttFixture fixture) +{ + private static readonly TimeSpan Timeout = TimeSpan.FromSeconds(15); + + private void SkipIfUnconfigured() => Assert.SkipWhen(fixture.SkipReason is not null, fixture.SkipReason ?? ""); + + [Fact] + public async Task A_primary_publishes_a_retained_ONLINE_that_a_late_subscriber_still_sees() + { + // Retention is the point, not an optimisation: an edge node that connects AFTER the host came + // up must still learn the host is alive. A non-retained ONLINE reaches only whoever happened to + // be subscribed at that instant, and every later joiner sees an absent host forever. + SkipIfUnconfigured(); + + var hostId = NewHostId(); + var ct = TestContext.Current.CancellationToken; + await using var host = NewHost(hostId, isPrimary: true); + + await host.StartAsync(ct); + host.IsClaimed.ShouldBeTrue("the fixture broker accepted the claim connection"); + + // Subscribe only NOW — after the birth was published — so only a retained message can satisfy it. + await using var watcher = await StateWatcher.StartAsync(fixture, hostId, ct); + var body = await watcher.WaitForOneAsync(Timeout, ct); + + SparkplugStatePayload.TryDecode(body, out var online, out var timestamp).ShouldBeTrue(); + online.ShouldBeTrue(); + timestamp.ShouldBeGreaterThan(0); + + await host.StopAsync(ct); + await ClearRetainedAsync(hostId, ct); + } + + [Fact] + public async Task An_abrupt_death_leaves_a_retained_OFFLINE_because_the_will_fires() + { + // THE leg the whole design exists for, and the one no unit test can reach: proof that the + // broker is holding our death certificate and delivers it when the socket dies without a + // goodbye. Without it a crashed node would leave a retained ONLINE asserting forever that a + // dead host is alive — strictly worse than never publishing at all. + SkipIfUnconfigured(); + + var hostId = NewHostId(); + var ct = TestContext.Current.CancellationToken; + var host = NewHost(hostId, isPrimary: true); + + await host.StartAsync(ct); + host.IsClaimed.ShouldBeTrue(); + + await using var watcher = await StateWatcher.StartAsync(fixture, hostId, ct); + var birth = await watcher.WaitForOneAsync(Timeout, ct); + SparkplugStatePayload.TryDecode(birth, out var wasOnline, out var birthTimestamp).ShouldBeTrue(); + wasOnline.ShouldBeTrue(); + + // Kill the socket with no DISCONNECT. A clean teardown would make the broker DISCARD the Will + // by protocol rule, so this test would then be observing the explicit stand-down publish and + // would pass against an implementation that never armed a Will. + await host.AbandonClaimForTests(); + + var death = await watcher.WaitForMatchAsync( + p => SparkplugStatePayload.TryDecode(p, out var o, out _) && !o, Timeout, ct); + + SparkplugStatePayload.TryDecode(death, out _, out var deathTimestamp).ShouldBeTrue(); + + // Sparkplug 3.0 pairs a host's birth and death by timestamp — an edge node may ignore an + // OFFLINE older than the ONLINE it holds. Mismatched timestamps produce two well-formed + // messages and a death certificate conformant hosts are entitled to throw away. + deathTimestamp.ShouldBe(birthTimestamp); + + await host.DisposeAsync(); + await ClearRetainedAsync(hostId, ct); + } + + [Fact] + public async Task A_clean_shutdown_leaves_a_retained_OFFLINE_without_waiting_for_the_will() + { + SkipIfUnconfigured(); + + var hostId = NewHostId(); + var ct = TestContext.Current.CancellationToken; + var host = NewHost(hostId, isPrimary: true); + + await host.StartAsync(ct); + await using var watcher = await StateWatcher.StartAsync(fixture, hostId, ct); + await watcher.WaitForMatchAsync( + p => SparkplugStatePayload.TryDecode(p, out var o, out _) && o, Timeout, ct); + + await host.StopAsync(ct); + + // Promptly — the assertion is that this arrives well inside the keep-alive window it would take + // the broker to notice a dead socket, which is why the explicit publish exists at all. + await watcher.WaitForMatchAsync( + p => SparkplugStatePayload.TryDecode(p, out var o, out _) && !o, Timeout, ct); + + await host.DisposeAsync(); + await ClearRetainedAsync(hostId, ct); + } + + [Fact] + public async Task A_node_that_is_not_primary_publishes_nothing_at_all() + { + // The pair-node answer. Not merely "does not win the race" — a Secondary must never open a + // claim connection, because the Will it would register is the hazard: its own death would then + // publish OFFLINE over a perfectly healthy Primary's ONLINE and stop the whole group. + SkipIfUnconfigured(); + + var hostId = NewHostId(); + var ct = TestContext.Current.CancellationToken; + await using var watcher = await StateWatcher.StartAsync(fixture, hostId, ct); + await using var host = NewHost(hostId, isPrimary: false); + + await host.StartAsync(ct); + host.ClaimAttemptsForTests.ShouldBe(0); + + // Give the reconcile loop several ticks to misbehave in. + await Task.Delay(TimeSpan.FromSeconds(3), ct); + + host.IsClaimed.ShouldBeFalse(); + host.ClaimAttemptsForTests.ShouldBe(0); + watcher.Count.ShouldBe(0, "a Secondary must not touch the STATE topic"); + } + + [Fact] + public async Task A_failover_moves_the_claim_offline_then_online_again() + { + // Both halves of the accepted trade, observed: losing Primary publishes OFFLINE (a genuine + // state transition — for a window there really is no host), and regaining it republishes + // ONLINE. The republish is the half that would be easy to omit; without it a node that failed + // back would run as Primary while every edge node believed it was gone. + SkipIfUnconfigured(); + + var hostId = NewHostId(); + var ct = TestContext.Current.CancellationToken; + var role = new MutableRole(isPrimary: true); + await using var host = new SparkplugPrimaryHost(Options(hostId), "live-failover", role); + + await using var watcher = await StateWatcher.StartAsync(fixture, hostId, ct); + + await host.StartAsync(ct); + await watcher.WaitForMatchAsync( + p => SparkplugStatePayload.TryDecode(p, out var o, out _) && o, Timeout, ct); + + role.IsPrimary = false; + await watcher.WaitForMatchAsync( + p => SparkplugStatePayload.TryDecode(p, out var o, out _) && !o, Timeout, ct); + await WaitUntilAsync(() => !host.IsClaimed, ct); + + var offlineSeen = watcher.CountMatching( + p => SparkplugStatePayload.TryDecode(p, out var o, out _) && !o); + + role.IsPrimary = true; + await WaitUntilAsync(() => host.IsClaimed, ct); + + // A SECOND online, after the offline — not merely "an online exists", which the birth already + // satisfied before the failover even started. + await WaitUntilAsync( + () => watcher.CountMatching(p => SparkplugStatePayload.TryDecode(p, out var o, out _) && o) >= 2, + ct); + + offlineSeen.ShouldBeGreaterThanOrEqualTo(1); + + await host.StopAsync(ct); + await ClearRetainedAsync(hostId, ct); + } + + // ---- helpers ----------------------------------------------------------------------------------- + + /// A per-test host id: the retained STATE outlives the test that wrote it. + private static string NewHostId() => $"otopcua-live-{Guid.NewGuid():N}"[..28]; + + private MqttDriverOptions Options(string hostId) => new() + { + Host = fixture.PlainHost, + Port = fixture.PlainPort, + Username = fixture.Username, + Password = fixture.Password, + UseTls = false, + ClientId = $"otopcua-live-{Guid.NewGuid():N}"[..20], + ConnectTimeoutSeconds = 10, + Mode = MqttMode.SparkplugB, + Sparkplug = new MqttSparkplugOptions + { + GroupId = "OtOpcUaSim", + HostId = hostId, + ActAsPrimaryHost = true, + }, + }; + + private SparkplugPrimaryHost NewHost(string hostId, bool isPrimary) => + new(Options(hostId), $"live-{hostId}", new MutableRole(isPrimary)); + + /// + /// Clears the retained STATE this test left behind — a zero-length retained publish is MQTT's + /// "forget this". Leaving a retained ONLINE for a host that no longer exists is precisely the + /// lie the feature prevents. + /// + private async Task ClearRetainedAsync(string hostId, CancellationToken ct) + { + var client = new MqttClientFactory().CreateMqttClient(); + try + { + await client.ConnectAsync( + new MqttClientOptionsBuilder() + .WithTcpServer(fixture.PlainHost, fixture.PlainPort) + .WithCredentials(fixture.Username, fixture.Password) + .WithClientId($"otopcua-live-clean-{Guid.NewGuid():N}"[..23]) + .WithTimeout(TimeSpan.FromSeconds(10)) + .Build(), + ct); + + await client.PublishAsync( + new MqttApplicationMessageBuilder() + .WithTopic(SparkplugTopic.FormatState(hostId)) + .WithPayload(Array.Empty()) + .WithRetainFlag(true) + .Build(), + ct); + + await client.DisconnectAsync(cancellationToken: ct); + } + finally + { + client.Dispose(); + } + } + + private static async Task WaitUntilAsync(Func condition, CancellationToken ct) + { + var deadline = DateTime.UtcNow + Timeout; + while (!condition()) + { + if (DateTime.UtcNow >= deadline) + { + throw new TimeoutException($"Condition was not satisfied within {Timeout}."); + } + + await Task.Delay(100, ct); + } + } + + /// A role source a test can flip, standing in for a redundancy failover. + private sealed class MutableRole(bool isPrimary) : IDriverPrimaryRoleSource + { + private volatile bool _isPrimary = isPrimary; + + public bool IsPrimary + { + get => _isPrimary; + set => _isPrimary = value; + } + + public bool ShouldActAsPrimary => _isPrimary; + + public void PublishPrimaryRole(bool shouldActAsPrimary) => _isPrimary = shouldActAsPrimary; + } + + /// Subscribes one host's STATE topic and records every body seen, in order. + private sealed class StateWatcher : IAsyncDisposable + { + private readonly IMqttClient _client; + private readonly ConcurrentQueue _bodies = new(); + + private StateWatcher(IMqttClient client) => _client = client; + + public int Count => _bodies.Count; + + public static async Task StartAsync(MqttFixture fixture, string hostId, CancellationToken ct) + { + var client = new MqttClientFactory().CreateMqttClient(); + var watcher = new StateWatcher(client); + + client.ApplicationMessageReceivedAsync += args => + { + watcher._bodies.Enqueue(args.ApplicationMessage.Payload.ToArray()); + return Task.CompletedTask; + }; + + await client.ConnectAsync( + new MqttClientOptionsBuilder() + .WithTcpServer(fixture.PlainHost, fixture.PlainPort) + .WithCredentials(fixture.Username, fixture.Password) + .WithClientId($"otopcua-live-state-{Guid.NewGuid():N}"[..23]) + .WithTimeout(TimeSpan.FromSeconds(10)) + .Build(), + ct); + + await client.SubscribeAsync( + new MqttClientSubscribeOptionsBuilder() + .WithTopicFilter(f => f.WithTopic(SparkplugTopic.FormatState(hostId))) + .Build(), + ct); + + return watcher; + } + + public int CountMatching(Func predicate) => _bodies.Count(b => Safe(predicate, b)); + + public async Task WaitForOneAsync(TimeSpan timeout, CancellationToken ct) + => await WaitForMatchAsync(_ => true, timeout, ct); + + public async Task WaitForMatchAsync(Func predicate, TimeSpan timeout, CancellationToken ct) + { + var deadline = DateTime.UtcNow + timeout; + while (true) + { + if (_bodies.FirstOrDefault(b => Safe(predicate, b)) is { } match) + { + return match; + } + + if (DateTime.UtcNow >= deadline) + { + throw new TimeoutException( + $"No matching STATE message within {timeout} ({_bodies.Count} seen, none matching)."); + } + + await Task.Delay(100, ct); + } + } + + private static bool Safe(Func predicate, byte[] body) + { + try { return predicate(body); } + catch { return false; } + } + + public async ValueTask DisposeAsync() + { + try + { + if (_client.IsConnected) + { + await _client.DisconnectAsync(); + } + } + catch + { + // Teardown only. + } + finally + { + _client.Dispose(); + } + } + } +} diff --git a/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Tests/SparkplugPrimaryHostTests.cs b/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Tests/SparkplugPrimaryHostTests.cs new file mode 100644 index 00000000..451a060c --- /dev/null +++ b/tests/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Tests/SparkplugPrimaryHostTests.cs @@ -0,0 +1,263 @@ +using System.Text; +using MQTTnet; +using Shouldly; +using Xunit; +using ZB.MOM.WW.OtOpcUa.Core.Abstractions; +using ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Sparkplug; + +namespace ZB.MOM.WW.OtOpcUa.Driver.Mqtt.Tests; + +/// +/// Unit tests for the Sparkplug primary-host claim (Gitea #511) — the parts that are decidable +/// without a broker: the STATE bodies, the Will registration, and the gate that decides whether a +/// claim is attempted at all. +/// +/// +/// The claim/release state machine itself needs a broker and is covered by +/// MqttPrimaryHostLiveTests in the integration suite. What is pinned here is everything a +/// live test could not tell apart from a working implementation by accident — above all that the +/// birth and the Will carry the SAME timestamp, which a live test would see as two well-formed +/// messages. +/// +[Trait("Category", "Unit")] +public sealed class SparkplugPrimaryHostTests +{ + private static MqttDriverOptions Options( + bool actAsPrimaryHost = true, + string hostId = "otopcua-primary", + MqttMode mode = MqttMode.SparkplugB) + => new() + { + Host = "broker.example", + Port = 1883, + ClientId = "otopcua", + Mode = mode, + Sparkplug = new MqttSparkplugOptions + { + GroupId = "OtOpcUaSim", + HostId = hostId, + ActAsPrimaryHost = actAsPrimaryHost, + }, + }; + + // ---- The matched-timestamp invariant -------------------------------------------------------- + + [Fact] + public void The_birth_and_the_will_carry_the_same_timestamp() + { + // Sparkplug 3.0 pairs a host's birth and death certificates by their timestamp, so an edge node + // may ignore an OFFLINE older than the ONLINE it holds. The two bodies are necessarily built at + // different moments — the Will goes in the CONNECT packet, the birth is published after CONNACK + // — so reading the clock twice is the natural mistake, and it produces two individually + // well-formed messages that no live test would flag. + var session = SparkplugStatePayload.ForSession("otopcua-primary", 1_770_000_000_123); + + SparkplugStatePayload.TryDecode(session.OnlineBody, out var online, out var birthTs).ShouldBeTrue(); + SparkplugStatePayload.TryDecode(session.OfflineBody, out var offline, out var deathTs).ShouldBeTrue(); + + online.ShouldBeTrue(); + offline.ShouldBeFalse(); + birthTs.ShouldBe(1_770_000_000_123); + deathTs.ShouldBe(birthTs); + } + + [Fact] + public void The_state_topic_is_the_v3_form() + => SparkplugStatePayload.ForSession("scada-primary", 1).Topic.ShouldBe("spBv1.0/STATE/scada-primary"); + + [Fact] + public void The_timestamp_is_a_bare_json_number() + { + // A quoted timestamp still parses as a valid JSON object, so a serializer choosing string + // formatting for a long would be silently wrong to every conformant host. + var body = Encoding.UTF8.GetString(SparkplugStatePayload.Encode(online: true, 1_770_000_000_123)); + + body.ShouldBe("{\"online\":true,\"timestamp\":1770000000123}"); + } + + [Fact] + public void The_body_survives_a_non_invariant_culture() + { + var previous = Thread.CurrentThread.CurrentCulture; + Thread.CurrentThread.CurrentCulture = new System.Globalization.CultureInfo("de-DE"); + try + { + Encoding.UTF8.GetString(SparkplugStatePayload.Encode(online: false, 1_770_000_000_123)) + .ShouldBe("{\"online\":false,\"timestamp\":1770000000123}"); + } + finally + { + Thread.CurrentThread.CurrentCulture = previous; + } + } + + // ---- The Will actually reaches the CONNECT packet -------------------------------------------- + + [Fact] + public void The_will_is_registered_on_the_client_options_retained_at_qos1() + { + // The single most important assertion in this file. A retained ONLINE with no Will behind it is + // strictly worse than publishing nothing: a crashed node then asserts forever that a dead host + // is alive. This is the check that the death certificate is armed at CONNECT rather than merely + // constructed. + var session = SparkplugStatePayload.ForSession("otopcua-primary", 42); + var will = new MqttLastWill(session.Topic, session.OfflineBody, SparkplugStatePayload.StateQos, Retain: true); + + var built = MqttClientOptionsFactory.BuildClientOptions( + Options(), SparkplugPrimaryHost.ClientIdSuffix, logger: null, lastWill: will, cleanSessionOverride: true); + + built.WillTopic.ShouldBe("spBv1.0/STATE/otopcua-primary"); + built.WillRetain.ShouldBeTrue(); + built.WillQualityOfServiceLevel.ShouldBe(MQTTnet.Protocol.MqttQualityOfServiceLevel.AtLeastOnce); + SparkplugStatePayload.TryDecode(built.WillPayload, out var online, out _).ShouldBeTrue(); + online.ShouldBeFalse(); + } + + [Fact] + public void No_will_is_registered_when_none_is_supplied() + // Every other connection this repo opens — ingest, browse, probe — must stay Will-free. A Will + // leaking onto the ingest session would publish a host death when ingest merely reconnects. + => MqttClientOptionsFactory.BuildClientOptions(Options(), clientIdSuffix: null).WillTopic.ShouldBeNull(); + + [Fact] + public void The_claim_connection_forces_clean_session_over_the_configured_value() + { + // A broker resuming a previous session for this client id may keep the OLD session's Will and + // discard the one this CONNECT carries — a claim with no death certificate behind it. + var persistent = Options() with { CleanSession = false }; + + MqttClientOptionsFactory.BuildClientOptions(persistent, "-spbhost", cleanSessionOverride: true) + .CleanSession.ShouldBeTrue(); + + // ...and the override is genuinely an override, not a constant. + MqttClientOptionsFactory.BuildClientOptions(persistent, clientIdSuffix: null) + .CleanSession.ShouldBeFalse(); + } + + [Fact] + public void The_claim_connection_uses_a_distinct_client_id() + { + // Two MQTT clients presenting one client id is not an error the broker reports: it evicts the + // older one. Ingest and the claim would take turns killing each other, forever, looking like a + // flapping broker. + var ingest = MqttClientOptionsFactory.BuildClientOptions(Options(), clientIdSuffix: null).ClientId; + var claim = MqttClientOptionsFactory + .BuildClientOptions(Options(), SparkplugPrimaryHost.ClientIdSuffix).ClientId; + + claim.ShouldNotBe(ingest); + claim.ShouldBe("otopcua-spbhost"); + } + + // ---- Whether a claim is attempted at all ----------------------------------------------------- + + [Fact] + public void A_configured_claim_is_claimable() + => SparkplugPrimaryHost.CanClaim(Options()).ShouldBeTrue(); + + [Theory] + [InlineData("")] + [InlineData(" ")] + public void A_blank_host_id_is_refused_rather_than_publishing_to_a_malformed_topic(string hostId) + { + // "spBv1.0/STATE/" is a legal MQTT topic, so a publish would succeed and reach nobody. + SparkplugPrimaryHost.CanClaim(Options(hostId: hostId)).ShouldBeFalse(); + SparkplugPrimaryHost.DescribeUnusable(Options(hostId: hostId)).ShouldNotBeNullOrWhiteSpace(); + } + + [Fact] + public void The_flag_is_ignored_outside_sparkplug_mode_and_says_so() + { + var plain = Options(mode: MqttMode.Plain); + + SparkplugPrimaryHost.CanClaim(plain).ShouldBeFalse(); + SparkplugPrimaryHost.DescribeUnusable(plain).ShouldNotBeNullOrWhiteSpace(); + } + + [Fact] + public void An_unset_flag_produces_no_complaint() + { + // DescribeUnusable must stay silent about a configuration that never asked for anything, or the + // driver warns on every ordinary Sparkplug deployment. + SparkplugPrimaryHost.CanClaim(Options(actAsPrimaryHost: false)).ShouldBeFalse(); + SparkplugPrimaryHost.DescribeUnusable(Options(actAsPrimaryHost: false)).ShouldBeNull(); + SparkplugPrimaryHost.DescribeUnusable(Options(actAsPrimaryHost: false, hostId: "")).ShouldBeNull(); + } + + [Fact] + public void Constructing_a_claim_without_a_host_id_throws_rather_than_half_working() + => Should.Throw(() => + new SparkplugPrimaryHost(Options(hostId: " "), "drv-1", UnmanagedDriverPrimaryRoleSource.Instance)); + + // ---- The gate --------------------------------------------------------------------------------- + + [Fact] + public void A_driver_with_no_role_source_claims() + { + // The documented fallback for a standalone host or a test: with nothing publishing a role there + // is no peer to collide with, and defaulting closed would make the feature silently inert on the + // single-node deployment that is its commonest use. + UnmanagedDriverPrimaryRoleSource.Instance.ShouldActAsPrimary.ShouldBeTrue(); + + // Publishing into it is a no-op rather than a throw, so a caller need not special-case it. + UnmanagedDriverPrimaryRoleSource.Instance.PublishPrimaryRole(false); + UnmanagedDriverPrimaryRoleSource.Instance.ShouldActAsPrimary.ShouldBeTrue(); + } + + [Fact] + public async Task A_secondary_never_even_attempts_a_claim_connection() + { + // The whole point of gating. Asserted on ATTEMPTS, not on IsClaimed: both nodes point at the + // same unreachable broker here, so IsClaimed is false either way and an IsClaimed-only + // assertion would pass just as happily with the gate deleted. See ClaimAttemptsForTests. + var host = new SparkplugPrimaryHost( + Unreachable(), "drv-1", new FixedRole(shouldActAsPrimary: false)); + + await host.StartAsync(TestContext.Current.CancellationToken); + + host.ClaimAttemptsForTests.ShouldBe(0); + host.IsClaimed.ShouldBeFalse(); + await host.DisposeAsync(); + } + + [Fact] + public async Task A_primary_attempts_the_claim_and_survives_a_broker_it_cannot_reach() + { + // The falsifying control for the test above — same options, same broker, opposite verdict — so + // "0 attempts" there is a fact about the gate rather than about the fixture. + // + // It also pins the swallow: the claim is advisory and ingest is the data plane, so a broker that + // refuses it must cost a warning, not the driver. And IsClaimed must stay honest — a connection + // whose ONLINE never landed is not a claim. + var host = new SparkplugPrimaryHost(Unreachable(), "drv-1", new FixedRole(shouldActAsPrimary: true)); + + await Should.NotThrowAsync(() => host.StartAsync(TestContext.Current.CancellationToken)); + + host.ClaimAttemptsForTests.ShouldBe(1); + host.IsClaimed.ShouldBeFalse(); + await host.DisposeAsync(); + } + + /// A broker that refuses instantly, so a connect attempt is observable but not slow. + private static MqttDriverOptions Unreachable() => + Options() with { Host = "127.0.0.1", Port = 1, ConnectTimeoutSeconds = 1 }; + + [Fact] + public async Task Stopping_an_unclaimed_host_is_a_no_op() + { + var host = new SparkplugPrimaryHost(Options(), "drv-1", new FixedRole(shouldActAsPrimary: false)); + + await Should.NotThrowAsync(() => host.StopAsync(TestContext.Current.CancellationToken)); + + // Twice: teardown runs from both ShutdownAsync and DisposeAsync, so a second release that threw + // — or that published a second OFFLINE — would surface on every ordinary driver shutdown. + await Should.NotThrowAsync(async () => await host.DisposeAsync()); + await Should.NotThrowAsync(async () => await host.DisposeAsync()); + } + + private sealed class FixedRole(bool shouldActAsPrimary) : IDriverPrimaryRoleSource + { + public bool ShouldActAsPrimary { get; private set; } = shouldActAsPrimary; + + public void PublishPrimaryRole(bool value) => ShouldActAsPrimary = value; + } +}