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.
106 lines
4.4 KiB
C#
106 lines
4.4 KiB
C#
using Akka.Cluster;
|
|
using Microsoft.EntityFrameworkCore;
|
|
using Microsoft.Extensions.DependencyInjection;
|
|
using Shouldly;
|
|
using Xunit;
|
|
using ZB.MOM.WW.OtOpcUa.Commons.Interfaces;
|
|
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Admin;
|
|
using ZB.MOM.WW.OtOpcUa.Configuration;
|
|
using ZB.MOM.WW.OtOpcUa.Configuration.Enums;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.Host.IntegrationTests;
|
|
|
|
/// <summary>
|
|
/// Failover scenarios layered on <see cref="TwoNodeClusterHarness"/> Stop/Restart primitives.
|
|
/// Covers graceful node loss, rejoin on the same Akka port, and deployment under reduced membership.
|
|
/// </summary>
|
|
public sealed class FailoverDuringDeployTests
|
|
{
|
|
private static CancellationToken Ct => TestContext.Current.CancellationToken;
|
|
|
|
/// <summary>Verifies that stopping node B shrinks the cluster to one up member.</summary>
|
|
[Fact]
|
|
public async Task Stopping_node_b_shrinks_cluster_to_one_up_member()
|
|
{
|
|
await using var harness = await TwoNodeClusterHarness.StartAsync();
|
|
Akka.Cluster.Cluster.Get(harness.NodeASystem).State.Members
|
|
.Count(m => m.Status == MemberStatus.Up).ShouldBe(2);
|
|
|
|
await harness.StopNodeBAsync();
|
|
await harness.WaitForClusterSizeAsync(1, TimeSpan.FromSeconds(20));
|
|
|
|
Akka.Cluster.Cluster.Get(harness.NodeASystem).State.Members
|
|
.Count(m => m.Status == MemberStatus.Up).ShouldBe(1);
|
|
}
|
|
|
|
/// <summary>Verifies that a restarted node B rejoins the cluster on the same port.</summary>
|
|
[Fact]
|
|
public async Task Restarted_node_b_rejoins_cluster_on_same_port()
|
|
{
|
|
await using var harness = await TwoNodeClusterHarness.StartAsync();
|
|
|
|
await harness.StopNodeBAsync();
|
|
await harness.WaitForClusterSizeAsync(1, TimeSpan.FromSeconds(20));
|
|
|
|
await harness.RestartNodeBAsync();
|
|
|
|
Akka.Cluster.Cluster.Get(harness.NodeASystem).State.Members
|
|
.Count(m => m.Status == MemberStatus.Up).ShouldBe(2);
|
|
Akka.Cluster.Cluster.Get(harness.NodeBSystem).State.Members
|
|
.Count(m => m.Status == MemberStatus.Up).ShouldBe(2);
|
|
}
|
|
|
|
/// <summary>Verifies that a deployment started with node B down seals with one-node state.</summary>
|
|
[Fact]
|
|
public async Task Deployment_started_with_node_b_down_seals_with_one_node_state()
|
|
{
|
|
// Establishes that ConfigPublishCoordinator.DiscoverDriverNodes snapshots membership at
|
|
// dispatch time — when only node A is Up, only one ApplyAck is expected and the
|
|
// deployment seals without B ever participating.
|
|
await using var harness = await TwoNodeClusterHarness.StartAsync();
|
|
await harness.SeedDefaultClusterAsync();
|
|
|
|
await harness.StopNodeBAsync();
|
|
await harness.WaitForClusterSizeAsync(1, TimeSpan.FromSeconds(20));
|
|
|
|
await using var scope = harness.NodeA.Services.CreateAsyncScope();
|
|
var client = scope.ServiceProvider.GetRequiredService<IAdminOperationsClient>();
|
|
|
|
var result = await client.StartDeploymentAsync(createdBy: "alice@test", Ct);
|
|
result.Outcome.ShouldBe(StartDeploymentOutcome.Accepted);
|
|
var deploymentId = result.DeploymentId!.Value.Value;
|
|
|
|
await WaitForAsync(async () =>
|
|
{
|
|
await using var db = await CreateDbAsync(harness);
|
|
var d = await db.Deployments.AsNoTracking()
|
|
.FirstOrDefaultAsync(d => d.DeploymentId == deploymentId, Ct);
|
|
return d?.Status == DeploymentStatus.Sealed;
|
|
}, TimeSpan.FromSeconds(15));
|
|
|
|
await using var db = await CreateDbAsync(harness);
|
|
var nodeStates = await db.NodeDeploymentStates.AsNoTracking()
|
|
.Where(s => s.DeploymentId == deploymentId)
|
|
.ToListAsync(Ct);
|
|
nodeStates.Count.ShouldBe(1);
|
|
nodeStates[0].Status.ShouldBe(NodeDeploymentStatus.Applied);
|
|
}
|
|
|
|
private static async Task<OtOpcUaConfigDbContext> CreateDbAsync(TwoNodeClusterHarness harness)
|
|
{
|
|
var factory = harness.NodeA.Services.GetRequiredService<IDbContextFactory<OtOpcUaConfigDbContext>>();
|
|
return await factory.CreateDbContextAsync();
|
|
}
|
|
|
|
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}");
|
|
}
|
|
}
|