lmxopcua/src/Server/ZB.MOM.WW.OtOpcUa.Admin/Services/RedundancyMetrics.cs

using System.Diagnostics.Metrics;

namespace ZB.MOM.WW.OtOpcUa.Admin.Services;

/// <summary>
///     OpenTelemetry-compatible instrumentation for the redundancy surface. Uses in-box
///     <see cref="System.Diagnostics.Metrics"/> so no NuGet dependency is required to emit —
///     any MeterListener (dotnet-counters, OpenTelemetry.Extensions.Hosting OTLP exporter,
///     Prometheus exporter, etc.) picks up the instruments by the <see cref="MeterName"/>.
/// </summary>
/// <remarks>
///     Exporter configuration (OTLP, Prometheus, etc.) is intentionally NOT wired here —
///     that's a deployment-ops decision that belongs in <c>Program.cs</c> behind an
///     <c>appsettings</c> toggle. This class owns only the Meter + instruments so the
///     production data stream exists regardless of exporter availability.
///
///     Counter + gauge names follow the otel-semantic-conventions pattern:
///     <c>otopcua.redundancy.*</c> with tags for ClusterId + (for transitions) FromRole/ToRole/NodeId.
/// </remarks>
public sealed class RedundancyMetrics : IDisposable
{
    public const string MeterName = "ZB.MOM.WW.OtOpcUa.Redundancy";

    private readonly Meter _meter;
    private readonly Counter<long> _roleTransitions;
    private readonly object _gaugeLock = new();
    private readonly Dictionary<string, ClusterGaugeState> _gaugeState = new();

    public RedundancyMetrics()
    {
        _meter = new Meter(MeterName, version: "1.0.0");
        _roleTransitions = _meter.CreateCounter<long>(
            "otopcua.redundancy.role_transition",
            unit: "{transition}",
            description: "Observed RedundancyRole changes per node — tagged FromRole, ToRole, NodeId, ClusterId.");

        // Observable gauges — the callback reports whatever the last Observe*Count call stashed.
        _meter.CreateObservableGauge(
            "otopcua.redundancy.primary_count",
            ObservePrimaryCounts,
            unit: "{node}",
            description: "Count of Primary-role nodes per cluster (should be 1 for N+1 redundant clusters, 0 during failover).");
        _meter.CreateObservableGauge(
            "otopcua.redundancy.secondary_count",
            ObserveSecondaryCounts,
            unit: "{node}",
            description: "Count of Secondary-role nodes per cluster.");
        _meter.CreateObservableGauge(
            "otopcua.redundancy.stale_count",
            ObserveStaleCounts,
            unit: "{node}",
            description: "Count of cluster nodes whose LastSeenAt is older than StaleThreshold.");
    }

    /// <summary>
    ///     Update the per-cluster snapshot consumed by the ObservableGauges. Poller calls this
    ///     at the end of every tick so the collectors see fresh numbers on the next observation
    ///     window (by default 1s for dotnet-counters, configurable per exporter).
    /// </summary>
    public void SetClusterCounts(string clusterId, int primary, int secondary, int stale)
    {
        lock (_gaugeLock)
        {
            _gaugeState[clusterId] = new ClusterGaugeState(primary, secondary, stale);
        }
    }

    /// <summary>
    ///     Increment the role_transition counter when a node's RedundancyRole changes. Tags
    ///     allow breakdowns by from/to roles (e.g. Primary → Secondary for planned failover vs
    ///     Primary → Standalone for emergency recovery) + by cluster for multi-site fleets.
    /// </summary>
    public void RecordRoleTransition(string clusterId, string nodeId, string fromRole, string toRole)
    {
        _roleTransitions.Add(1,
            new KeyValuePair<string, object?>("cluster.id", clusterId),
            new KeyValuePair<string, object?>("node.id", nodeId),
            new KeyValuePair<string, object?>("from_role", fromRole),
            new KeyValuePair<string, object?>("to_role", toRole));
    }

    public void Dispose() => _meter.Dispose();

    private IEnumerable<Measurement<long>> ObservePrimaryCounts() => SnapshotGauge(s => s.Primary);
    private IEnumerable<Measurement<long>> ObserveSecondaryCounts() => SnapshotGauge(s => s.Secondary);
    private IEnumerable<Measurement<long>> ObserveStaleCounts() => SnapshotGauge(s => s.Stale);

    private IEnumerable<Measurement<long>> SnapshotGauge(Func<ClusterGaugeState, int> selector)
    {
        List<Measurement<long>> results;
        lock (_gaugeLock)
        {
            results = new List<Measurement<long>>(_gaugeState.Count);
            foreach (var (cluster, state) in _gaugeState)
                results.Add(new Measurement<long>(selector(state),
                    new KeyValuePair<string, object?>("cluster.id", cluster)));
        }
        return results;
    }

    private readonly record struct ClusterGaugeState(int Primary, int Secondary, int Stale);
}