Files
lmxopcua/src/ZB.MOM.WW.OtOpcUa.Server/Redundancy/RedundancyTopology.cs
Joseph Doherty 84fe88fadb Phase 6.3 Stream A — RedundancyTopology + ClusterTopologyLoader + RedundancyCoordinator
Lands the data path that feeds the Phase 6.3 ServiceLevelCalculator shipped in
PR #89. OPC UA node wiring (ServiceLevel variable + ServerUriArray +
RedundancySupport) still deferred to task #147; peer-probe loops (Stream B.1/B.2
runtime layer beyond the calculator logic) deferred.

Server.Redundancy additions:
- RedundancyTopology record — immutable snapshot (ClusterId, SelfNodeId,
  SelfRole, Mode, Peers[], SelfApplicationUri). ServerUriArray() emits the
  OPC UA Part 4 §6.6.2.2 shape (self first, peers lexicographically by
  NodeId). RedundancyPeer record with per-peer Host/OpcUaPort/DashboardPort/
  ApplicationUri so the follow-up peer-probe loops know where to probe.
- ClusterTopologyLoader — pure fn from ServerCluster + ClusterNode[] to
  RedundancyTopology. Enforces Phase 6.3 Stream A.1 invariants:
    * At least one node per cluster.
    * At most 2 nodes (decision #83, v2.0 cap).
    * Every node belongs to the target cluster.
    * Unique ApplicationUri across the cluster (OPC UA Part 4 trust pin,
      decision #86).
    * At most 1 Primary per cluster in Warm/Hot modes (decision #84).
    * Self NodeId must be a member of the cluster.
  Violations throw InvalidTopologyException with a decision-ID-tagged message
  so operators know which invariant + what to fix.
- RedundancyCoordinator singleton — holds the current topology + IsTopologyValid
  flag. InitializeAsync throws on invariant violation (startup fails fast).
  RefreshAsync logs + flips IsTopologyValid=false (runtime won't tear down a
  running server; ServiceLevelCalculator falls to InvalidTopology band = 2
  which surfaces the problem to clients without crashing). CAS-style swap
  via Volatile.Write so readers always see a coherent snapshot.

Tests (10 new ClusterTopologyLoaderTests):
- Single-node standalone loads + empty peer list.
- Two-node cluster loads self + peer.
- ServerUriArray puts self first + peers sort lexicographically.
- Empty-nodes throws.
- Self-not-in-cluster throws.
- Three-node cluster rejected with decision #83 message.
- Duplicate ApplicationUri rejected with decision #86 shape reference.
- Two Primaries in Warm mode rejected (decision #84 + runtime-band reference).
- Cross-cluster node rejected.
- None-mode allows any role mix (standalone clusters don't enforce Primary count).

Full solution dotnet test: 1178 passing (was 1168, +10). Pre-existing
Client.CLI Subscribe flake unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 11:24:14 -04:00

56 lines
2.6 KiB
C#

using ZB.MOM.WW.OtOpcUa.Configuration.Enums;
namespace ZB.MOM.WW.OtOpcUa.Server.Redundancy;
/// <summary>
/// Snapshot of the cluster topology the <see cref="RedundancyCoordinator"/> holds. Read
/// once at startup + refreshed on publish-generation notification. Immutable — every
/// refresh produces a new instance so observers can compare identity-equality to detect
/// topology change.
/// </summary>
/// <remarks>
/// Per Phase 6.3 Stream A.1. Invariants enforced by the loader (see
/// <see cref="ClusterTopologyLoader"/>): at most one Primary per cluster for
/// WarmActive/Hot redundancy modes; every node has a unique ApplicationUri (OPC UA
/// Part 4 requirement — clients pin trust here); at most 2 nodes total per cluster
/// (decision #83).
/// </remarks>
public sealed record RedundancyTopology(
string ClusterId,
string SelfNodeId,
RedundancyRole SelfRole,
RedundancyMode Mode,
IReadOnlyList<RedundancyPeer> Peers,
string SelfApplicationUri)
{
/// <summary>Peer count — 0 for a standalone (single-node) cluster, 1 for v2 two-node clusters.</summary>
public int PeerCount => Peers.Count;
/// <summary>
/// ServerUriArray shape per OPC UA Part 4 §6.6.2.2 — self first, peers in stable
/// deterministic order (lexicographic by NodeId), self's ApplicationUri always at index 0.
/// </summary>
public IReadOnlyList<string> ServerUriArray() =>
new[] { SelfApplicationUri }
.Concat(Peers.OrderBy(p => p.NodeId, StringComparer.OrdinalIgnoreCase).Select(p => p.ApplicationUri))
.ToList();
}
/// <summary>One peer in the cluster (every node other than self).</summary>
/// <param name="NodeId">Peer's stable logical NodeId (e.g. <c>"LINE3-OPCUA-B"</c>).</param>
/// <param name="Role">Peer's declared redundancy role from the shared config DB.</param>
/// <param name="Host">Peer's hostname / IP — drives the health-probe target.</param>
/// <param name="OpcUaPort">Peer's OPC UA endpoint port.</param>
/// <param name="DashboardPort">Peer's dashboard / health-endpoint port.</param>
/// <param name="ApplicationUri">Peer's declared ApplicationUri (carried in <see cref="RedundancyTopology.ServerUriArray"/>).</param>
public sealed record RedundancyPeer(
string NodeId,
RedundancyRole Role,
string Host,
int OpcUaPort,
int DashboardPort,
string ApplicationUri);
/// <summary>Thrown when the loader detects a topology-invariant violation at startup or refresh.</summary>
public sealed class InvalidTopologyException(string message) : Exception(message);