a61e041e58
Promotes the two apps' private replacements for ActiveNodeHealthCheck into one shared primitive, and retires the leader/RoleLeader selection they were written to avoid. Both Akka consumers had already hand-rolled a replacement rather than use this package (ScadaBridge OldestNodeActiveHealthCheck, OtOpcUa ClusterPrimaryHealthCheck), so the entire active-node surface here — ActiveNodeHealthCheck, AkkaActiveNodeGate — had ZERO consumers. It was not merely unused: it was avoided, twice, for the same reason. Leadership is address-ordered (host, then port) and has no relationship to time; singleton placement is age-ordered. The two agree on a freshly-formed cluster, which is why single-node and happy-path tests never caught it. They diverge permanently after any restart: the restarted node rejoins as the youngest but keeps its address, so if it holds the lower address it becomes leader while the singletons — and all the work they own — stay on the other node. New ClusterActiveNode is the single implementation: oldest Up member, optional role scope, plus role-preference resolution for a fused node that must answer for the role its singletons are pinned to. ActiveNodeHealthCheck and AkkaActiveNodeGate both delegate to it, so an endpoint gate and the /health/active probe an orchestrator routes by cannot disagree. BREAKING (behaviour, not signature): - Selection is by age, not leadership. - The role-filtered mode no longer reports Healthy for a node LACKING the role. That "not applicable => Healthy" made the tier answer 200 on every node and silently broke leader-pinning (lmxopcua#494); it is now Unhealthy by default, overridable via NoActiveRoleStatus. This case is reachable, not defensive — OtOpcUa's RoleParser admits dev-only and cluster-role-only nodes. - Identity compares UniqueAddress, so a node restarted on the same host:port is correctly a different member during the overlap. Results now carry activeRole/selfAddress/activeNode in the 0.2.0 per-entry data object, so a standby reports WHO is active and a dashboard can render a pair from either node's payload alone. Tests: 45 Akka (was 39), 76 total. The age-vs-address divergence is pinned against a real two-node cluster built so the oldest member is not the lowest-addressed one, with a fixture sanity check so it cannot pass for the wrong reason.
238 lines
9.9 KiB
C#
238 lines
9.9 KiB
C#
using Akka.Actor;
|
|
using Akka.Cluster;
|
|
using Akka.Configuration;
|
|
using Microsoft.Extensions.DependencyInjection;
|
|
using Microsoft.Extensions.Diagnostics.HealthChecks;
|
|
using ZB.MOM.WW.Health.Akka;
|
|
|
|
namespace ZB.MOM.WW.Health.Akka.Tests;
|
|
|
|
/// <summary>
|
|
/// Pins <b>which</b> node the active tier names, against a real two-node cluster deliberately built
|
|
/// so the oldest member is <i>not</i> the lowest-addressed one.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// <para>
|
|
/// The divergence is the whole point. Akka offers two different "first" members:
|
|
/// <c>ClusterState.Leader</c> / <c>RoleLeader</c> is the <b>lowest-addressed</b> Up member
|
|
/// (host, then port — nothing to do with time), while <b>oldest</b> is the member with the
|
|
/// lowest up-number, which is what <c>ClusterSingletonManager</c> uses to place singletons.
|
|
/// </para>
|
|
/// <para>
|
|
/// They coincide on a freshly-formed cluster, which is why every single-node and happy-path
|
|
/// test missed it and why the leader-based check survived to 0.2.1. They diverge the moment a
|
|
/// node restarts: the restarted node rejoins as the youngest while keeping its address, so if
|
|
/// it holds the lower address it becomes leader while the singletons — and every piece of work
|
|
/// they own — stay on the other node. This fixture reproduces that state directly instead of
|
|
/// waiting for a restart.
|
|
/// </para>
|
|
/// </remarks>
|
|
public sealed class ClusterActiveNodeTests : IAsyncLifetime
|
|
{
|
|
// Fixed, unusual ports: the test needs a deterministic address ordering, which port 0 cannot give.
|
|
// Distinct from OtOpcUa's equivalent fixture (19_530/19_531) so the two suites can run at once.
|
|
private const int OldestPort = 19_541; // joins FIRST -> oldest, but the HIGHER address
|
|
private const int YoungestPort = 19_540; // joins SECOND -> cluster leader, the LOWER address
|
|
|
|
private const string SystemName = "health-active-node";
|
|
|
|
private ActorSystem? _oldest;
|
|
private ActorSystem? _youngest;
|
|
|
|
private static Config NodeConfig(int port, string roles) => ConfigurationFactory.ParseString($$"""
|
|
akka {
|
|
loglevel = "WARNING"
|
|
actor.provider = "Akka.Cluster.ClusterActorRefProvider, Akka.Cluster"
|
|
remote.dot-netty.tcp {
|
|
hostname = "127.0.0.1"
|
|
port = {{port}}
|
|
}
|
|
cluster {
|
|
seed-nodes = ["akka.tcp://{{SystemName}}@127.0.0.1:{{OldestPort}}"]
|
|
roles = [{{roles}}]
|
|
min-nr-of-members = 1
|
|
run-coordinated-shutdown-when-down = off
|
|
downing-provider-class = ""
|
|
}
|
|
}
|
|
""");
|
|
|
|
public async Task InitializeAsync()
|
|
{
|
|
// Order matters: the seed forms the cluster and is therefore the oldest member. The oldest
|
|
// node is fused (admin + driver); the younger one is driver-only, so the role-scoped
|
|
// assertions below can distinguish "oldest of this role" from "oldest overall".
|
|
_oldest = ActorSystem.Create(SystemName, NodeConfig(OldestPort, "\"admin\", \"driver\""));
|
|
await WaitForUpAsync(_oldest, expectedMembers: 1);
|
|
|
|
_youngest = ActorSystem.Create(SystemName, NodeConfig(YoungestPort, "\"driver\""));
|
|
await WaitForUpAsync(_oldest, expectedMembers: 2);
|
|
await WaitForUpAsync(_youngest, expectedMembers: 2);
|
|
}
|
|
|
|
public async Task DisposeAsync()
|
|
{
|
|
if (_youngest is not null) await _youngest.Terminate();
|
|
if (_oldest is not null) await _oldest.Terminate();
|
|
}
|
|
|
|
private static async Task WaitForUpAsync(ActorSystem system, int expectedMembers)
|
|
{
|
|
var cluster = Cluster.Get(system);
|
|
var deadline = DateTime.UtcNow + TimeSpan.FromSeconds(30);
|
|
while (DateTime.UtcNow < deadline)
|
|
{
|
|
if (cluster.State.Members.Count(m => m.Status == MemberStatus.Up) >= expectedMembers) return;
|
|
await Task.Delay(100);
|
|
}
|
|
|
|
throw new TimeoutException(
|
|
$"cluster on port {cluster.SelfAddress.Port} never saw {expectedMembers} Up members "
|
|
+ $"(saw {cluster.State.Members.Count(m => m.Status == MemberStatus.Up)})");
|
|
}
|
|
|
|
/// <summary>
|
|
/// Sanity check on the fixture itself: if the two orderings did not actually diverge, every
|
|
/// assertion below would pass for the wrong reason.
|
|
/// </summary>
|
|
[Fact]
|
|
public void Fixture_actually_produces_divergent_age_and_address_ordering()
|
|
{
|
|
var state = Cluster.Get(_oldest!).State;
|
|
|
|
Assert.Equal(YoungestPort, state.Leader!.Port);
|
|
Assert.Equal(YoungestPort, state.RoleLeader("driver")!.Port);
|
|
}
|
|
|
|
[Fact]
|
|
public void OldestUpMember_IsTheOldest_NotTheLeader()
|
|
{
|
|
var members = Cluster.Get(_oldest!).State.Members;
|
|
|
|
Assert.Equal(OldestPort, ClusterActiveNode.OldestUpMember(members)!.Address.Port);
|
|
Assert.Equal(OldestPort, ClusterActiveNode.OldestUpMember(members, "driver")!.Address.Port);
|
|
}
|
|
|
|
[Fact]
|
|
public void OldestUpMember_IsRoleScoped()
|
|
{
|
|
var members = Cluster.Get(_oldest!).State.Members;
|
|
|
|
// Only the fused node carries admin, so it owns the admin slot even though it is not the
|
|
// lowest-addressed member.
|
|
Assert.Equal(OldestPort, ClusterActiveNode.OldestUpMember(members, "admin")!.Address.Port);
|
|
|
|
// A role nobody carries has no owner.
|
|
Assert.Null(ClusterActiveNode.OldestUpMember(members, "no-such-role"));
|
|
}
|
|
|
|
[Fact]
|
|
public void SelfIsActive_IsTrueOnlyOnTheOldestNode()
|
|
{
|
|
Assert.True(ClusterActiveNode.SelfIsActive(Cluster.Get(_oldest!)));
|
|
Assert.False(ClusterActiveNode.SelfIsActive(Cluster.Get(_youngest!)));
|
|
}
|
|
|
|
[Fact]
|
|
public void SelfIsActive_RoleScoped_YoungestOwnsNoSlot()
|
|
{
|
|
// Driver-scoped: the fused node is still the oldest driver, so the driver-only node is standby.
|
|
Assert.True(ClusterActiveNode.SelfIsActive(Cluster.Get(_oldest!), "driver"));
|
|
Assert.False(ClusterActiveNode.SelfIsActive(Cluster.Get(_youngest!), "driver"));
|
|
|
|
// Admin-scoped: the driver-only node does not carry admin, so it can never be the admin active
|
|
// node — even though it is the cluster leader.
|
|
Assert.False(ClusterActiveNode.SelfIsActive(Cluster.Get(_youngest!), "admin"));
|
|
}
|
|
|
|
[Fact]
|
|
public async Task HealthCheck_IsHealthyOnTheOldestAndUnhealthyOnTheLeader()
|
|
{
|
|
var onOldest = await CheckAsync(_oldest!, new ActiveNodeHealthCheckOptions());
|
|
var onYoungest = await CheckAsync(_youngest!, new ActiveNodeHealthCheckOptions());
|
|
|
|
Assert.Equal(HealthStatus.Healthy, onOldest.Status);
|
|
|
|
// The node the old leader-based check would have called active. Exactly one 200 per cluster is
|
|
// the property an orchestrator's active-tier routing depends on.
|
|
Assert.Equal(HealthStatus.Unhealthy, onYoungest.Status);
|
|
}
|
|
|
|
[Fact]
|
|
public async Task HealthCheck_DataNamesTheActiveNode_EvenFromAStandby()
|
|
{
|
|
// A standby reporting *who* is active is what lets a dashboard render the pair from either
|
|
// node's payload alone (the 0.2.0 per-entry data object).
|
|
var result = await CheckAsync(_youngest!, new ActiveNodeHealthCheckOptions());
|
|
|
|
Assert.Equal($"akka.tcp://{SystemName}@127.0.0.1:{OldestPort}", result.Data["activeNode"]);
|
|
Assert.Equal($"akka.tcp://{SystemName}@127.0.0.1:{YoungestPort}", result.Data["selfAddress"]);
|
|
}
|
|
|
|
[Fact]
|
|
public async Task HealthCheck_RolePreference_FusedNodeAnswersForAdmin()
|
|
{
|
|
var options = new ActiveNodeHealthCheckOptions { RolePreference = ["admin", "driver"] };
|
|
|
|
var onOldest = await CheckAsync(_oldest!, options);
|
|
var onYoungest = await CheckAsync(_youngest!, options);
|
|
|
|
Assert.Equal(HealthStatus.Healthy, onOldest.Status);
|
|
Assert.Equal("admin", onOldest.Data["activeRole"]);
|
|
|
|
// Resolves to driver (it has no admin role) and loses to the older fused node.
|
|
Assert.Equal(HealthStatus.Unhealthy, onYoungest.Status);
|
|
Assert.Equal("driver", onYoungest.Data["activeRole"]);
|
|
}
|
|
|
|
[Fact]
|
|
public async Task HealthCheck_NodeOwningNoneOfThePreferredRoles_IsUnhealthyByDefault()
|
|
{
|
|
var options = new ActiveNodeHealthCheckOptions { RolePreference = ["no-such-role"] };
|
|
|
|
var result = await CheckAsync(_oldest!, options);
|
|
|
|
// Not "not applicable ⇒ Healthy": a node that owns no active work must stay out of the pool.
|
|
Assert.Equal(HealthStatus.Unhealthy, result.Status);
|
|
Assert.Contains("carries none of the active roles", result.Description);
|
|
Assert.DoesNotContain("activeRole", result.Data.Keys);
|
|
}
|
|
|
|
[Fact]
|
|
public async Task HealthCheck_NoActiveRoleStatus_IsOverridable()
|
|
{
|
|
var options = new ActiveNodeHealthCheckOptions
|
|
{
|
|
RolePreference = ["no-such-role"],
|
|
NoActiveRoleStatus = HealthStatus.Healthy,
|
|
};
|
|
|
|
Assert.Equal(HealthStatus.Healthy, (await CheckAsync(_oldest!, options)).Status);
|
|
}
|
|
|
|
[Fact]
|
|
public void Gate_IsActiveOnlyOnTheOldestNode()
|
|
{
|
|
Assert.True(new AkkaActiveNodeGate(ProviderFor(_oldest!)).IsActiveNode);
|
|
Assert.False(new AkkaActiveNodeGate(ProviderFor(_youngest!)).IsActiveNode);
|
|
|
|
// Role-scoped: the driver-only node cannot gate admin work.
|
|
Assert.False(new AkkaActiveNodeGate(ProviderFor(_youngest!), "admin").IsActiveNode);
|
|
}
|
|
|
|
private static IServiceProvider ProviderFor(ActorSystem system) =>
|
|
new ServiceCollection().AddSingleton(system).BuildServiceProvider();
|
|
|
|
private static async Task<HealthCheckResult> CheckAsync(
|
|
ActorSystem system,
|
|
ActiveNodeHealthCheckOptions options)
|
|
{
|
|
var check = new ActiveNodeHealthCheck(ProviderFor(system), options);
|
|
var context = new HealthCheckContext
|
|
{
|
|
Registration = new HealthCheckRegistration("active-node", check, HealthStatus.Unhealthy, tags: null),
|
|
};
|
|
return await check.CheckHealthAsync(context);
|
|
}
|
|
}
|