30d0697c28
`IHostConnectivityProbe` was a dead surface: eleven drivers implement it, `GetHostStatuses()` had ZERO production call sites, and `OnHostStatusChanged` had no subscriber outside the Galaxy driver's own aggregator. Per-host connectivity was computed by every driver and read by nobody. The issue offered "build the publisher or delete it". The publisher as its entity doc described it — driver nodes upserting `DriverHostStatus` rows — is not buildable: per-cluster mesh Phase 4 gates `AddOtOpcUaConfigDb` on the `admin` role, so a driver-only node has no ConfigDb connection to write rows with. So the capability is kept and the transport changed. `DriverHealthChanged.HostStatuses` now carries the probe result to `/hosts` as a Hosts column. That channel already reached the page, already survives the mesh split via the Phase 5 gRPC telemetry stream, and already replays a last-value snapshot on re-subscribe — so per-host state re-primes after a reconnect without a durable store. Both halves of the interface finally do what they are for: the event triggers a prompt publish, the pull is the source of truth. The point of the column is the case the driver-level state chip structurally cannot express: a multi-device driver stays aggregate-Healthy while ONE of its devices is unreachable. Two traps, both pinned by tests that were falsified against the prod code: - The host digest MUST be in the publish fingerprint. On a single-host-down transition every other fingerprint component is unchanged, so the dedup would swallow exactly the publish carrying the news — the trap that already bit the rediscovery signal. Removing it turns the guard test red, verified. - null (no probe) must stay distinct from empty (probe with no hosts). proto3 cannot tell an absent repeated field from an empty one, hence the explicit `has_host_statuses` flag; collapsing them would render every probe-less driver as one whose devices are all fine. Dropped: the DriverHostStatus entity, enum, DbSet, model config and table (migration DropDriverHostStatusTable — empty on every deployment, so the scaffolder's data-loss warning is moot, and Down() recreates it exactly). Found en route, NOT fixed here: `DriverInstanceResilienceStatus` is the identical defect — no writer, no reader, only a DbSet declaration, while the live data rides the `driver-resilience-status` telemetry channel. Its doc-comment now states that rather than describing the sampler and AdminUI join that were never built. Filed as #524 rather than widening this schema change beyond what was asked. Claude-Session: https://claude.ai/code/session_015p7wGqy3YpZNCpDzTpGMKo
217 lines
7.8 KiB
C#
217 lines
7.8 KiB
C#
using Shouldly;
|
|
using Xunit;
|
|
using ZB.MOM.WW.OtOpcUa.AdminUI.Hosts;
|
|
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Drivers;
|
|
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.AdminUI.Tests.Hosts;
|
|
|
|
/// <summary>
|
|
/// Covers <see cref="HostsDriverView.Build"/>: the pure, DB-agnostic view-model builder that
|
|
/// groups driver-health snapshots by cluster, attaches each cluster's nodes, and enriches each
|
|
/// driver row with the configured name + type. The builder is null-safe and stable-ordered so
|
|
/// the (later) <c>/hosts</c> Razor section renders deterministically.
|
|
/// </summary>
|
|
public sealed class HostsDriverViewTests
|
|
{
|
|
private static readonly DateTime When = new(2026, 6, 18, 0, 0, 0, DateTimeKind.Utc);
|
|
|
|
private static DriverHealthChanged Snap(string cluster, string instance, string state = "Healthy") =>
|
|
new(cluster, instance, state, null, null, 0, When);
|
|
|
|
private static HostsNodeInfo Node(string cluster, string node, string host = "h", int port = 4840) =>
|
|
new(cluster, node, host, port);
|
|
|
|
private static HostsDriverInstanceInfo Instance(string instance, string cluster, string name, string type) =>
|
|
new(instance, cluster, name, type);
|
|
|
|
[Fact]
|
|
public void Build_groups_two_clusters_with_their_nodes_and_snapshots()
|
|
{
|
|
var snaps = new[]
|
|
{
|
|
Snap("MAIN", "drv-a"),
|
|
Snap("EDGE", "drv-b"),
|
|
};
|
|
var nodes = new[]
|
|
{
|
|
Node("MAIN", "MAIN-1"),
|
|
Node("EDGE", "EDGE-1"),
|
|
};
|
|
|
|
var groups = HostsDriverView.Build(snaps, nodes, instances: null);
|
|
|
|
groups.Count.ShouldBe(2);
|
|
var main = groups.Single(g => g.ClusterId == "MAIN");
|
|
var edge = groups.Single(g => g.ClusterId == "EDGE");
|
|
|
|
main.Nodes.Select(n => n.NodeId).ShouldBe(new[] { "MAIN-1" });
|
|
main.Drivers.Select(d => d.DriverInstanceId).ShouldBe(new[] { "drv-a" });
|
|
edge.Nodes.Select(n => n.NodeId).ShouldBe(new[] { "EDGE-1" });
|
|
edge.Drivers.Select(d => d.DriverInstanceId).ShouldBe(new[] { "drv-b" });
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_enriches_driver_row_from_matching_instance()
|
|
{
|
|
var groups = HostsDriverView.Build(
|
|
new[] { Snap("MAIN", "drv-a", "Faulted") },
|
|
nodes: null,
|
|
new[] { Instance("drv-a", "MAIN", "Pump House Modbus", "Modbus") });
|
|
|
|
var row = groups.Single().Drivers.Single();
|
|
row.DriverInstanceId.ShouldBe("drv-a");
|
|
row.Name.ShouldBe("Pump House Modbus");
|
|
row.DriverType.ShouldBe("Modbus");
|
|
row.State.ShouldBe("Faulted");
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_leaves_name_and_type_null_for_unknown_driver()
|
|
{
|
|
var groups = HostsDriverView.Build(
|
|
new[] { Snap("MAIN", "orphan") },
|
|
nodes: null,
|
|
new[] { Instance("drv-a", "MAIN", "Known", "Modbus") });
|
|
|
|
var row = groups.Single().Drivers.Single(d => d.DriverInstanceId == "orphan");
|
|
row.Name.ShouldBeNull();
|
|
row.DriverType.ShouldBeNull();
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_includes_cluster_with_nodes_but_no_snapshots()
|
|
{
|
|
var groups = HostsDriverView.Build(
|
|
snapshots: null,
|
|
new[] { Node("MAIN", "MAIN-1") },
|
|
instances: null);
|
|
|
|
var group = groups.Single();
|
|
group.ClusterId.ShouldBe("MAIN");
|
|
group.Nodes.Count.ShouldBe(1);
|
|
group.Drivers.ShouldBeEmpty();
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_with_empty_inputs_returns_empty_list()
|
|
{
|
|
HostsDriverView.Build(
|
|
Array.Empty<DriverHealthChanged>(),
|
|
Array.Empty<HostsNodeInfo>(),
|
|
Array.Empty<HostsDriverInstanceInfo>()).ShouldBeEmpty();
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_with_all_null_inputs_returns_empty_list_without_throwing()
|
|
{
|
|
HostsDriverView.Build(snapshots: null, nodes: null, instances: null).ShouldBeEmpty();
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_orders_drivers_by_name_then_instance_id()
|
|
{
|
|
var snaps = new[]
|
|
{
|
|
Snap("MAIN", "drv-z"), // no instance -> null name -> sorts by id "drv-z"
|
|
Snap("MAIN", "drv-a"), // no instance -> null name -> sorts by id "drv-a"
|
|
Snap("MAIN", "drv-m"), // named "Alpha"
|
|
};
|
|
var instances = new[]
|
|
{
|
|
Instance("drv-m", "MAIN", "Alpha", "Modbus"),
|
|
};
|
|
|
|
var drivers = HostsDriverView.Build(snaps, nodes: null, instances).Single().Drivers;
|
|
|
|
// Sort key is (Name ?? DriverInstanceId): "Alpha"(drv-m), "drv-a", "drv-z".
|
|
drivers.Select(d => d.DriverInstanceId).ShouldBe(new[] { "drv-m", "drv-a", "drv-z" });
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_takes_first_when_instance_id_appears_twice()
|
|
{
|
|
var groups = HostsDriverView.Build(
|
|
new[] { Snap("MAIN", "drv-a") },
|
|
nodes: null,
|
|
new[]
|
|
{
|
|
Instance("drv-a", "MAIN", "First", "Modbus"),
|
|
Instance("drv-a", "MAIN", "Second", "S7"),
|
|
});
|
|
|
|
var row = groups.Single().Drivers.Single();
|
|
row.Name.ShouldBe("First");
|
|
row.DriverType.ShouldBe("Modbus");
|
|
}
|
|
|
|
[Fact]
|
|
public void Build_orders_clusters_case_insensitively()
|
|
{
|
|
var groups = HostsDriverView.Build(
|
|
new[] { Snap("zeta", "d1"), Snap("Alpha", "d2") },
|
|
new[] { Node("Beta", "b1") },
|
|
instances: null);
|
|
|
|
groups.Select(g => g.ClusterId).ShouldBe(new[] { "Alpha", "Beta", "zeta" });
|
|
}
|
|
|
|
/// <summary>
|
|
/// Per-host connectivity flows through to the row (Gitea #521), and <c>DegradedHosts</c> picks out
|
|
/// exactly the hosts an operator needs to look at. This is the case the driver-level Status chip
|
|
/// cannot express: the driver is Healthy and one of its devices is not.
|
|
/// </summary>
|
|
[Fact]
|
|
public void Build_carries_host_statuses_and_flags_only_the_degraded_ones()
|
|
{
|
|
var snapshot = Snap("MAIN", "drv-a") with
|
|
{
|
|
HostStatuses =
|
|
[
|
|
new HostConnectivityStatus("plc-a", HostState.Running, When),
|
|
new HostConnectivityStatus("plc-b", HostState.Stopped, When),
|
|
new HostConnectivityStatus("plc-c", HostState.Faulted, When),
|
|
],
|
|
};
|
|
|
|
var row = HostsDriverView.Build([snapshot], nodes: null, instances: null).Single().Drivers.Single();
|
|
|
|
row.State.ShouldBe("Healthy");
|
|
row.HostStatuses!.Count.ShouldBe(3);
|
|
row.DegradedHosts.Select(h => h.HostName).ShouldBe(["plc-b", "plc-c"]);
|
|
}
|
|
|
|
/// <summary>
|
|
/// <see cref="HostState.Unknown"/> counts as degraded. A probe that has not completed its first tick
|
|
/// — or one a driver failed to start at all, which AbCip logs explicitly — reports Unknown, and
|
|
/// rendering that as healthy is how an unstarted probe stays invisible.
|
|
/// </summary>
|
|
[Fact]
|
|
public void Unknown_host_state_counts_as_degraded()
|
|
{
|
|
var snapshot = Snap("MAIN", "drv-a") with
|
|
{
|
|
HostStatuses = [new HostConnectivityStatus("plc-a", HostState.Unknown, When)],
|
|
};
|
|
|
|
var row = HostsDriverView.Build([snapshot], nodes: null, instances: null).Single().Drivers.Single();
|
|
|
|
row.DegradedHosts.ShouldHaveSingleItem().HostName.ShouldBe("plc-a");
|
|
}
|
|
|
|
/// <summary>
|
|
/// A driver with no probe keeps a null host list — distinct from a probe reporting zero hosts. The
|
|
/// /hosts column renders "—" for the former and "0 hosts" for the latter, and collapsing them would
|
|
/// claim every probe-less driver's devices are fine.
|
|
/// </summary>
|
|
[Fact]
|
|
public void A_driver_without_host_statuses_keeps_null_and_reports_no_degraded_hosts()
|
|
{
|
|
var row = HostsDriverView.Build([Snap("MAIN", "drv-a")], nodes: null, instances: null)
|
|
.Single().Drivers.Single();
|
|
|
|
row.HostStatuses.ShouldBeNull();
|
|
row.DegradedHosts.ShouldBeEmpty();
|
|
}
|
|
}
|