fix(harness): make deploy E2E tests pass against real SQL (seed cluster FKs)
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.
This commit is contained in:
Joseph Doherty
@@ -14,6 +14,8 @@ using ZB.MOM.WW.OtOpcUa.AdminUI.Clients;
|
||||
using ZB.MOM.WW.OtOpcUa.AdminUI.Hubs;
|
||||
using ZB.MOM.WW.OtOpcUa.Cluster;
|
||||
using ZB.MOM.WW.OtOpcUa.Configuration;
|
||||
using ZB.MOM.WW.OtOpcUa.Configuration.Entities;
|
||||
using ZB.MOM.WW.OtOpcUa.Configuration.Enums;
|
||||
using ZB.MOM.WW.OtOpcUa.ControlPlane;
|
||||
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
|
||||
using ZB.MOM.WW.OtOpcUa.Host.Health;
|
||||
@@ -36,7 +38,9 @@ namespace ZB.MOM.WW.OtOpcUa.Host.IntegrationTests;
|
||||
/// <item><c>OTOPCUA_HARNESS_USE_SQL=1</c> → swap the in-memory DB for SQL Server on
|
||||
/// <c>localhost:14331</c> (see <c>docker-compose.yml</c>). Each harness gets a unique
|
||||
/// database name (<c>OtOpcUa_Harness_{guid}</c>) created via <c>EnsureCreated</c>
|
||||
/// and dropped via <c>EnsureDeleted</c> on dispose.</item>
|
||||
/// and dropped via <c>EnsureDeleted</c> on dispose. Override the SQL / LDAP host with
|
||||
/// <c>OTOPCUA_HARNESS_SQL_HOST</c> / <c>OTOPCUA_HARNESS_LDAP_HOST</c> to point at native
|
||||
/// fixtures on the shared Docker host (avoids the arm64-Mac emulated-mssql slowdown).</item>
|
||||
/// <item><c>OTOPCUA_HARNESS_USE_LDAP=1</c> → drop the stub and point <c>LdapAuthService</c>
|
||||
/// at the GLAuth container on <c>localhost:3894</c> (see Docker/glauth/config.toml).</item>
|
||||
/// </list>
|
||||
@@ -114,6 +118,53 @@ public sealed class TwoNodeClusterHarness : IAsyncDisposable
|
||||
public Task<OtOpcUaConfigDbContext> CreateConfigDbContextAsync()
|
||||
=> NodeA.Services.GetRequiredService<IDbContextFactory<OtOpcUaConfigDbContext>>().CreateDbContextAsync();
|
||||
|
||||
/// <summary>
|
||||
/// Seeds a default <see cref="ServerCluster"/> plus a <see cref="ClusterNode"/> row for BOTH
|
||||
/// harness nodes (<see cref="NodeANodeId"/> / <see cref="NodeBNodeId"/>) so the real-SQL FK
|
||||
/// constraint <c>FK_NodeDeploymentState_ClusterNode_NodeId</c> is satisfied when a deployment
|
||||
/// records per-node state. The EF in-memory provider ignores FK constraints, so deploy E2E
|
||||
/// tests pass without this; against SQL Server each node's <c>NodeDeploymentState</c> INSERT
|
||||
/// fails without its parent <see cref="ClusterNode"/> row and the deployment never seals.
|
||||
/// No-op unless <c>OTOPCUA_HARNESS_USE_SQL=1</c> (in-memory needs no seeding). Call once, before
|
||||
/// <c>StartDeploymentAsync</c>, in tests that don't already seed their own cluster + both nodes.
|
||||
/// </summary>
|
||||
/// <param name="clusterId">Cluster id for the seeded rows. Defaults to <c>MAIN</c>.</param>
|
||||
public async Task SeedDefaultClusterAsync(string clusterId = "MAIN")
|
||||
{
|
||||
if (!Mode.UseSqlServer) return;
|
||||
await using var db = await CreateConfigDbContextAsync();
|
||||
db.ServerClusters.Add(new ServerCluster
|
||||
{
|
||||
ClusterId = clusterId,
|
||||
Name = "Harness Default Cluster",
|
||||
Enterprise = "zb",
|
||||
Site = "central",
|
||||
// 2-node cluster → Warm/Hot per CK_ServerCluster_RedundancyMode_NodeCount
|
||||
// (NodeCount=1↔None, NodeCount=2↔Warm|Hot). The harness runs two nodes.
|
||||
NodeCount = 2,
|
||||
RedundancyMode = RedundancyMode.Warm,
|
||||
CreatedBy = "harness",
|
||||
});
|
||||
db.ClusterNodes.AddRange(
|
||||
new ClusterNode
|
||||
{
|
||||
NodeId = NodeANodeId,
|
||||
ClusterId = clusterId,
|
||||
Host = LoopbackHost,
|
||||
ApplicationUri = "urn:zb:harness:node-a",
|
||||
CreatedBy = "harness",
|
||||
},
|
||||
new ClusterNode
|
||||
{
|
||||
NodeId = NodeBNodeId,
|
||||
ClusterId = clusterId,
|
||||
Host = LoopbackHost,
|
||||
ApplicationUri = "urn:zb:harness:node-b",
|
||||
CreatedBy = "harness",
|
||||
});
|
||||
await db.SaveChangesAsync();
|
||||
}
|
||||
|
||||
/// <summary>Boots both nodes and waits up to <paramref name="formationTimeout"/> for cluster convergence.</summary>
|
||||
/// <param name="formationTimeout">Maximum time to wait for cluster formation; defaults to 20 seconds if not provided.</param>
|
||||
/// <param name="driverFactory">Optional opt-in <see cref="IDriverFactory"/> both nodes register so deployed
|
||||
@@ -131,7 +182,12 @@ public sealed class TwoNodeClusterHarness : IAsyncDisposable
|
||||
if (harness.Mode.UseSqlServer)
|
||||
{
|
||||
harness._sqlDbName = $"OtOpcUa_Harness_{Guid.NewGuid():N}";
|
||||
harness._sqlConnString = $"Server=localhost,14331;Database={harness._sqlDbName};User Id=sa;Password=OtOpcUa!Harness123;TrustServerCertificate=True;";
|
||||
// SQL host is overridable so the heavy 2-node E2E tests can target NATIVE-amd64 SQL on the
|
||||
// shared Docker host instead of the arm64 Mac's emulated mssql:2022 (no arm64 image → ~5-10×
|
||||
// slower → the deploy/failover E2E tests time out). Set OTOPCUA_HARNESS_SQL_HOST=10.100.0.35,14331
|
||||
// with the harness sql container brought up there. Defaults to localhost,14331.
|
||||
var sqlHost = Environment.GetEnvironmentVariable("OTOPCUA_HARNESS_SQL_HOST") ?? "localhost,14331";
|
||||
harness._sqlConnString = $"Server={sqlHost};Database={harness._sqlDbName};User Id=sa;Password=OtOpcUa!Harness123;TrustServerCertificate=True;";
|
||||
await EnsureSqlSchemaCreatedAsync(harness._sqlConnString);
|
||||
}
|
||||
|
||||
@@ -295,7 +351,8 @@ public sealed class TwoNodeClusterHarness : IAsyncDisposable
|
||||
// Bound section is Security:Ldap (see LdapOptions.SectionName); Transport replaces the
|
||||
// old UseTls bool and AllowInsecure replaces AllowInsecureLdap (Task 1.4).
|
||||
configOverrides["Security:Ldap:Enabled"] = "true";
|
||||
configOverrides["Security:Ldap:Server"] = "localhost";
|
||||
// Overridable alongside the SQL host so the GLAuth container can live on the Docker host too.
|
||||
configOverrides["Security:Ldap:Server"] = Environment.GetEnvironmentVariable("OTOPCUA_HARNESS_LDAP_HOST") ?? "localhost";
|
||||
configOverrides["Security:Ldap:Port"] = "3894";
|
||||
configOverrides["Security:Ldap:Transport"] = "None";
|
||||
configOverrides["Security:Ldap:AllowInsecure"] = "true";
|
||||
|
||||
Reference in New Issue
Block a user