Joseph Doherty
859d63178a
Integration-sweep follow-up #6 (SQL leg). The sweep flagged 7 heavy 2-node deploy/failover/reconnect E2E tests as 'time out under amd64-emulated SQL' and suggested raising deadlines. That diagnosis was WRONG: run against real (native-amd64) SQL on the Docker host, they still hang — even at 4x deadline. Root cause is that these tests had never actually run against real SQL, only the EF in-memory provider, which does NOT enforce foreign keys. Two distinct defects, both hidden by in-memory: 1. Missing FK-parent seed (5 tests). The deploy records a NodeDeploymentState row per node, FK'd to ClusterNode (FK_NodeDeploymentState_ClusterNode_NodeId). The tests never seeded ServerCluster + ClusterNode, so on SQL each node-state INSERT throws and the deploy never seals (waits the full deadline regardless of size). Added TwoNodeClusterHarness.SeedDefaultClusterAsync (seeds a ServerCluster + a ClusterNode per node; Warm/NodeCount=2 to satisfy the SQL CHECK constraint CK_ServerCluster_RedundancyMode_NodeCount AND the ClusterEnabledNodeCountMismatch validator). Called it in DeployHappyPath x2 / Failover / FleetDiagnostics / EquipmentNamespace; fixed DriverReconnect to seed node B + NodeCount=2. 2. Stale EquipmentId (EquipmentNamespace test; pre-existing on BOTH providers). Seeded EquipmentId='eq-1', but the later-added EquipmentIdNotDerived validator requires EquipmentId == DeriveEquipmentId(EquipmentUuid) ('EQ-'+first 12 hex). Fixed the seed to a canonical id + matching UUID. Only surfaced once the FK fix let the deploy reach equipment validation. Also added OTOPCUA_HARNESS_SQL_HOST / OTOPCUA_HARNESS_LDAP_HOST overrides so the harness fixtures can run on the native-amd64 Docker host (avoids arm64 mssql emulation entirely). Verified: the 5 SQL-backed classes go 11/11 green vs native SQL; in-memory default unregressed (12/12). RoslynVirtualTagEvaluatorTests racing test is a pre-existing flaky race (not SQL-backed; passes in isolation) — left as-is.
85 lines
3.6 KiB
C#
85 lines
3.6 KiB
C#
using Microsoft.Extensions.DependencyInjection;
|
|
using Shouldly;
|
|
using Xunit;
|
|
using ZB.MOM.WW.OtOpcUa.Commons.Interfaces;
|
|
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Admin;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.Host.IntegrationTests;
|
|
|
|
/// <summary>
|
|
/// End-to-end <see cref="IFleetDiagnosticsClient"/> round-trip via the cluster:
|
|
/// admin node asks node-B's <c>DriverHostActor</c> for a snapshot via <c>ActorSelection</c>.
|
|
/// Verifies the cross-node Ask/Reply works and the snapshot reflects the target node's
|
|
/// view (NodeId + CurrentRevision after a deploy).
|
|
/// </summary>
|
|
public sealed class FleetDiagnosticsRoundTripTests
|
|
{
|
|
private static CancellationToken Ct => TestContext.Current.CancellationToken;
|
|
|
|
/// <summary>Verifies that get diagnostics returns a snapshot with the target node ID.</summary>
|
|
[Fact]
|
|
public async Task GetDiagnostics_returns_snapshot_with_target_NodeId()
|
|
{
|
|
await using var harness = await TwoNodeClusterHarness.StartAsync();
|
|
|
|
// Resolve target NodeId from the cluster — second member ordered by address.
|
|
var members = Akka.Cluster.Cluster.Get(harness.NodeASystem).State.Members
|
|
.OrderBy(m => m.Address.ToString())
|
|
.ToArray();
|
|
members.Length.ShouldBe(2);
|
|
var targetAddress = members[1].Address;
|
|
var targetNodeId = Commons.Types.NodeId.Parse($"{targetAddress.Host}:{targetAddress.Port}");
|
|
|
|
await using var scope = harness.NodeA.Services.CreateAsyncScope();
|
|
var client = scope.ServiceProvider.GetRequiredService<IFleetDiagnosticsClient>();
|
|
|
|
var snapshot = await client.GetDiagnosticsAsync(targetNodeId, Ct);
|
|
|
|
snapshot.NodeId.ShouldBe(targetNodeId);
|
|
snapshot.Drivers.ShouldBeEmpty(); // No driver children yet (F7).
|
|
snapshot.AsOfUtc.ShouldBeGreaterThan(DateTime.UtcNow.AddSeconds(-30));
|
|
}
|
|
|
|
/// <summary>Verifies that get diagnostics after deploy reports the current revision.</summary>
|
|
[Fact]
|
|
public async Task GetDiagnostics_after_deploy_reports_current_revision()
|
|
{
|
|
await using var harness = await TwoNodeClusterHarness.StartAsync();
|
|
await harness.SeedDefaultClusterAsync();
|
|
|
|
await using var scope = harness.NodeA.Services.CreateAsyncScope();
|
|
var adminOps = scope.ServiceProvider.GetRequiredService<IAdminOperationsClient>();
|
|
var diagnostics = scope.ServiceProvider.GetRequiredService<IFleetDiagnosticsClient>();
|
|
|
|
var deploy = await adminOps.StartDeploymentAsync(createdBy: "alice@test", Ct);
|
|
deploy.Outcome.ShouldBe(StartDeploymentOutcome.Accepted);
|
|
var expectedRev = deploy.RevisionHash!.Value;
|
|
|
|
// Wait until both DriverHostActors have caught up to the deployed revision.
|
|
var members = Akka.Cluster.Cluster.Get(harness.NodeASystem).State.Members
|
|
.OrderBy(m => m.Address.ToString())
|
|
.Select(m => Commons.Types.NodeId.Parse($"{m.Address.Host}:{m.Address.Port}"))
|
|
.ToArray();
|
|
|
|
foreach (var nodeId in members)
|
|
{
|
|
await WaitForAsync(async () =>
|
|
{
|
|
var snap = await diagnostics.GetDiagnosticsAsync(nodeId, Ct);
|
|
return snap.CurrentRevision == expectedRev;
|
|
}, TimeSpan.FromSeconds(15));
|
|
}
|
|
}
|
|
|
|
private static async Task WaitForAsync(Func<Task<bool>> condition, TimeSpan timeout)
|
|
{
|
|
var deadline = DateTime.UtcNow + timeout;
|
|
while (DateTime.UtcNow < deadline)
|
|
{
|
|
if (await condition()) return;
|
|
await Task.Delay(200);
|
|
}
|
|
throw new TimeoutException($"Condition not met within {timeout}");
|
|
}
|
|
}
|