Files
lmxopcua/src/ZB.MOM.WW.OtOpcUa.Server/Redundancy/ClusterTopologyLoader.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

97 lines
4.6 KiB
C#

using ZB.MOM.WW.OtOpcUa.Configuration.Entities;
using ZB.MOM.WW.OtOpcUa.Configuration.Enums;
namespace ZB.MOM.WW.OtOpcUa.Server.Redundancy;
/// <summary>
/// Pure-function mapper from the shared config DB's <see cref="ServerCluster"/> +
/// <see cref="ClusterNode"/> rows to an immutable <see cref="RedundancyTopology"/>.
/// Validates Phase 6.3 Stream A.1 invariants and throws
/// <see cref="InvalidTopologyException"/> on violation so the coordinator can fail startup
/// fast with a clear message rather than boot into an ambiguous state.
/// </summary>
/// <remarks>
/// Stateless — the caller owns the DB round-trip + hands rows in. Keeping it pure makes
/// the invariant matrix testable without EF or SQL Server.
/// </remarks>
public static class ClusterTopologyLoader
{
/// <summary>Build a topology snapshot for the given self node. Throws on invariant violation.</summary>
public static RedundancyTopology Load(string selfNodeId, ServerCluster cluster, IReadOnlyList<ClusterNode> nodes)
{
ArgumentException.ThrowIfNullOrWhiteSpace(selfNodeId);
ArgumentNullException.ThrowIfNull(cluster);
ArgumentNullException.ThrowIfNull(nodes);
ValidateClusterShape(cluster, nodes);
ValidateUniqueApplicationUris(nodes);
ValidatePrimaryCount(cluster, nodes);
var self = nodes.FirstOrDefault(n => string.Equals(n.NodeId, selfNodeId, StringComparison.OrdinalIgnoreCase))
?? throw new InvalidTopologyException(
$"Self node '{selfNodeId}' is not a member of cluster '{cluster.ClusterId}'. " +
$"Members: {string.Join(", ", nodes.Select(n => n.NodeId))}.");
var peers = nodes
.Where(n => !string.Equals(n.NodeId, selfNodeId, StringComparison.OrdinalIgnoreCase))
.Select(n => new RedundancyPeer(
NodeId: n.NodeId,
Role: n.RedundancyRole,
Host: n.Host,
OpcUaPort: n.OpcUaPort,
DashboardPort: n.DashboardPort,
ApplicationUri: n.ApplicationUri))
.ToList();
return new RedundancyTopology(
ClusterId: cluster.ClusterId,
SelfNodeId: self.NodeId,
SelfRole: self.RedundancyRole,
Mode: cluster.RedundancyMode,
Peers: peers,
SelfApplicationUri: self.ApplicationUri);
}
private static void ValidateClusterShape(ServerCluster cluster, IReadOnlyList<ClusterNode> nodes)
{
if (nodes.Count == 0)
throw new InvalidTopologyException($"Cluster '{cluster.ClusterId}' has zero nodes.");
// Decision #83 — v2.0 caps clusters at two nodes.
if (nodes.Count > 2)
throw new InvalidTopologyException(
$"Cluster '{cluster.ClusterId}' has {nodes.Count} nodes. v2.0 supports at most 2 nodes per cluster (decision #83).");
// Every node must belong to the given cluster.
var wrongCluster = nodes.FirstOrDefault(n =>
!string.Equals(n.ClusterId, cluster.ClusterId, StringComparison.OrdinalIgnoreCase));
if (wrongCluster is not null)
throw new InvalidTopologyException(
$"Node '{wrongCluster.NodeId}' belongs to cluster '{wrongCluster.ClusterId}', not '{cluster.ClusterId}'.");
}
private static void ValidateUniqueApplicationUris(IReadOnlyList<ClusterNode> nodes)
{
var dup = nodes
.GroupBy(n => n.ApplicationUri, StringComparer.Ordinal)
.FirstOrDefault(g => g.Count() > 1);
if (dup is not null)
throw new InvalidTopologyException(
$"Nodes {string.Join(", ", dup.Select(n => n.NodeId))} share ApplicationUri '{dup.Key}'. " +
$"OPC UA Part 4 requires unique ApplicationUri per server — clients pin trust here (decision #86).");
}
private static void ValidatePrimaryCount(ServerCluster cluster, IReadOnlyList<ClusterNode> nodes)
{
// Standalone mode: any role is fine. Warm / Hot: at most one Primary per cluster.
if (cluster.RedundancyMode == RedundancyMode.None) return;
var primaries = nodes.Count(n => n.RedundancyRole == RedundancyRole.Primary);
if (primaries > 1)
throw new InvalidTopologyException(
$"Cluster '{cluster.ClusterId}' has {primaries} Primary nodes in redundancy mode {cluster.RedundancyMode}. " +
$"At most one Primary per cluster (decision #84). Runtime detects and demotes both to ServiceLevel 2 " +
$"per the 8-state matrix; startup fails fast to surface the misconfiguration earlier.");
}
}