lmxopcua/src/Core/ZB.MOM.WW.OtOpcUa.Cluster/Resources/akka.conf

# Base Akka.NET cluster configuration for OtOpcUa fused-host nodes.
#
# Roles, seed nodes, public hostname/port, and the actor system name are overlaid
# at runtime by ServiceCollectionExtensions.WithOtOpcUaClusterBootstrap (via Akka.Hosting).
# Everything else here is the cluster-wide tuning that should match across nodes.
#
# Any divergence from these defaults must be deliberate and recorded in docs/v2/Architecture.md.

akka {
    # Akka logger wiring (route ILoggingAdapter → Serilog) is configured via Akka.Hosting's
    # ConfigureLoggers in ServiceCollectionExtensions.WithOtOpcUaClusterBootstrap — HOCON
    # `akka.loggers` alone is not honored by Akka.Hosting. logger-startup-timeout is kept here
    # since the Serilog logger can be slow to initialize at startup.
    logger-startup-timeout = 30s

    extensions = [
        "Akka.Cluster.Tools.PublishSubscribe.DistributedPubSubExtensionProvider, Akka.Cluster.Tools"
    ]

    actor {
        provider = cluster
    }

    remote {
        dot-netty.tcp {
            hostname = "0.0.0.0"
            port = 4053
        }
        transport-failure-detector {
            heartbeat-interval = 2s
            acceptable-heartbeat-pause = 10s
        }
    }

    cluster {
        seed-nodes = []
        roles = []
        min-nr-of-members = 1

        # DOWNING. The provider is NOT selected here — this file is added with HoconAddMode.Append,
        # which loses to what Akka.Hosting's WithClustering emits, so a downing-provider-class set
        # here would be silently overridden. Selection lives in
        # ServiceCollectionExtensions.BuildDowningHocon (Prepended, which outranks WithClustering),
        # driven by Cluster:SplitBrainResolverStrategy.
        #
        # The DEFAULT strategy is "auto-down", under which this whole block is inert: Akka's
        # AutoDowning provider is installed with auto-down-unreachable-after = 15s, and the leader
        # among the reachable members downs the unreachable peer — so a hard crash of EITHER node,
        # oldest included, fails over. The trade is dual-active during a real network partition.
        #
        # The block below applies only when an operator selects "keep-oldest". Note that keep-oldest
        # is NOT safe for a two-node pair: Akka.NET's KeepOldest.OldestDecision only lets
        # down-if-alone rescue a side holding >= 2 members, so a 1-vs-1 survivor downs ITSELF and
        # (with run-coordinated-shutdown-when-down) exits — a crash of the oldest node becomes a
        # total outage. See docs/Redundancy.md.
        #
        # stable-after must stay >= failure-detector.acceptable-heartbeat-pause (10s) + margin, and
        # must equal ServiceCollectionExtensions.DowningStableAfter so both strategies fail over at
        # the same latency. Both constraints are pinned by SplitBrainResolverActivationTests.
        split-brain-resolver {
            active-strategy = "keep-oldest"
            stable-after = 15s
            keep-oldest {
                down-if-alone = on
            }
        }

        failure-detector {
            heartbeat-interval = 2s
            threshold = 10.0
            acceptable-heartbeat-pause = 10s
        }

        down-removal-margin = 15s
        run-coordinated-shutdown-when-down = on

        singleton {
            singleton-name = "singleton"
        }
        singleton-proxy {
            singleton-identification-interval = 1s
        }
    }

    coordinated-shutdown {
        run-by-clr-shutdown-hook = on
        default-phase-timeout = 30s
    }
}

# Pinned dispatcher used by OpcUaPublishActor (Task 44) so the OPC UA SDK sees
# only one thread per actor instance — its session/subscription locks expect
# strict single-threaded access.
opcua-synchronized-dispatcher {
    type = "PinnedDispatcher"
    executor = "thread-pool-executor"
    throughput = 1
}