5fe7135e2c
Tasks 3.4-3.6 of the overview-dashboard plan. Polling (3.4/3.5): - OverviewPollerService: one timer at the fastest configured cadence, each target polled when its own interval is due, fan-out per sweep, no retries (the next tick is the retry, so damping stays the only place that decides whether a failure is worth showing). - OverviewSnapshotStore: atomic swap of a complete immutable graph plus a change event. Pages read it and never probe — the cache-first requirement. - LeaderResolver: per-group leader from akka-cluster data, with the split-brain flag scoped to members that are actually answering, so an ordinary failover is not misread as a disagreement. UI (3.6): ThemeShell + StatusPill/TechCard composition against the mockup; instance cards carry the status stripe (dashed for Unreachable), the check detail list and the raw ready/active signal line. Two defects found by verification rather than by review: - The active tier answers with a status code and an EMPTY body, but the client demanded parseable JSON on every probe — so a healthy pair rendered as "role unknown" instead of Active/Standby. Split into ProbeAsync (ready tier, body is the payload) and ProbeStatusAsync (active tier, code is the answer). Caught by a live smoke run against two fake health endpoints; the poller tests now serve an empty body so they hold the fix. - SweepAsync published even when cancellation was already requested, leaving a half-probed registry as the store's final state on shutdown. It now checks the token itself rather than relying on the transport to throw. Also: app.UseAntiforgery() is required despite the anonymous-by-design pipeline — AddRazorComponents stamps antiforgery metadata unconditionally and the endpoint middleware hard-fails without it (every page was 500). Chosen over DisableAntiforgery() so a future form is protected by default. 147 tests, 0 warnings. Live-verified end to end against fake endpoints: Up/Unreachable/Active/Standby, leader chip, cluster-data line, KPI counts.
431 lines
18 KiB
C#
431 lines
18 KiB
C#
using System.Net;
|
||
using Microsoft.Extensions.Logging.Abstractions;
|
||
using Microsoft.Extensions.Options;
|
||
using ZB.MOM.WW.Overview.Polling;
|
||
using ZB.MOM.WW.Overview.Registry;
|
||
|
||
namespace ZB.MOM.WW.Overview.Tests;
|
||
|
||
/// <summary>
|
||
/// Sweep behaviour, driven directly rather than through the timer: the rules worth pinning are what
|
||
/// a sweep probes, what it does with the answers, and when it declines to probe at all.
|
||
/// </summary>
|
||
public class OverviewPollerServiceTests
|
||
{
|
||
private static readonly DateTimeOffset Start = new(2026, 7, 24, 12, 0, 0, TimeSpan.Zero);
|
||
|
||
private static OverviewOptions Registry(params ApplicationEntry[] applications) =>
|
||
new()
|
||
{
|
||
PollIntervalSeconds = 10,
|
||
TimeoutSeconds = 3,
|
||
StaleAfterSeconds = 45,
|
||
Applications = applications,
|
||
};
|
||
|
||
private static ApplicationEntry App(string name, params InstanceEntry[] instances) =>
|
||
new() { Name = name, ManagementLabel = "AdminUI", Instances = instances };
|
||
|
||
private static InstanceEntry Node(
|
||
string name,
|
||
string baseUrl,
|
||
string? group = null,
|
||
bool hasActiveRole = false,
|
||
int? pollIntervalSeconds = null) =>
|
||
new()
|
||
{
|
||
Name = name,
|
||
BaseUrl = baseUrl,
|
||
Group = group,
|
||
HasActiveRole = hasActiveRole,
|
||
PollIntervalSeconds = pollIntervalSeconds,
|
||
};
|
||
|
||
private static (OverviewPollerService Poller, OverviewSnapshotStore Store) Build(
|
||
OverviewOptions options,
|
||
HttpMessageHandler handler,
|
||
TimeProvider timeProvider)
|
||
{
|
||
var store = new OverviewSnapshotStore();
|
||
var poller = new OverviewPollerService(
|
||
Options.Create(options),
|
||
new StubHttpClientFactory(handler),
|
||
store,
|
||
timeProvider,
|
||
NullLogger<OverviewPollerService>.Instance);
|
||
|
||
return (poller, store);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_ProbesReadyForEveryInstance()
|
||
{
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"))
|
||
.Json("http://b:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var (poller, _) = Build(
|
||
Registry(App("App", Node("a", "http://a:8080"), Node("b", "http://b:8080"))),
|
||
handler,
|
||
new FakeTimeProvider(Start));
|
||
|
||
var snapshot = await poller.SweepAsync();
|
||
|
||
Assert.Equal(2, snapshot.AllInstances.Count());
|
||
Assert.All(snapshot.AllInstances, i => Assert.Equal(InstanceStatus.Up, i.Status));
|
||
Assert.Equal(2, handler.Requests.Count);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_TrailingSlashInBaseUrl_DoesNotDoubleTheSeparator()
|
||
{
|
||
// "//health/ready" would 404 on every instance — a registry typo class that must not matter.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var (poller, _) = Build(Registry(App("App", Node("a", "http://a:8080/"))), handler, new FakeTimeProvider(Start));
|
||
|
||
var snapshot = await poller.SweepAsync();
|
||
|
||
Assert.Equal(InstanceStatus.Up, Assert.Single(snapshot.AllInstances).Status);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_ActiveTierProbedOnlyForInstancesThatHaveTheRole()
|
||
{
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"))
|
||
.Status("http://a:8080/health/active", HttpStatusCode.OK)
|
||
.Json("http://gw:5120/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var (poller, _) = Build(
|
||
Registry(App("App", Node("a", "http://a:8080", "pair", hasActiveRole: true), Node("gw", "http://gw:5120"))),
|
||
handler,
|
||
new FakeTimeProvider(Start));
|
||
|
||
var snapshot = await poller.SweepAsync();
|
||
|
||
Assert.DoesNotContain("http://gw:5120/health/active", handler.Requests, StringComparer.Ordinal);
|
||
var byName = snapshot.AllInstances.ToDictionary(i => i.Instance, StringComparer.Ordinal);
|
||
Assert.Equal(ActiveState.Active, byName["a"].Active);
|
||
Assert.Equal(ActiveState.NotApplicable, byName["gw"].Active);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_StandbyAnswers503OnActive_AndIsStillUp()
|
||
{
|
||
// 503 on the ACTIVE tier is the standby's correct answer and says nothing about health —
|
||
// conflating the two tiers would paint every healthy standby in the fleet as Down.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://b:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"))
|
||
.Status("http://b:8080/health/active", HttpStatusCode.ServiceUnavailable);
|
||
var (poller, _) = Build(
|
||
Registry(App("App", Node("b", "http://b:8080", "pair", hasActiveRole: true))),
|
||
handler,
|
||
new FakeTimeProvider(Start));
|
||
|
||
var instance = Assert.Single((await poller.SweepAsync()).AllInstances);
|
||
|
||
Assert.Equal(InstanceStatus.Up, instance.Status);
|
||
Assert.Equal(ActiveState.Standby, instance.Active);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_UnreachableInstance_SkipsTheActiveProbe()
|
||
{
|
||
// Spending a second full timeout to confirm what the first one established would double
|
||
// the worst-case sweep duration for every dead node in the registry.
|
||
var handler = new RoutingHandler().Fails("http://a:8080/health/ready", "Connection refused");
|
||
var (poller, _) = Build(
|
||
Registry(App("App", Node("a", "http://a:8080", "pair", hasActiveRole: true))),
|
||
handler,
|
||
new FakeTimeProvider(Start));
|
||
|
||
await poller.SweepAsync();
|
||
|
||
Assert.DoesNotContain("http://a:8080/health/active", handler.Requests, StringComparer.Ordinal);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_SickInstanceStillGetsItsActiveProbe()
|
||
{
|
||
// A 503 on ready means the app is talking. Whether the sick node is the ACTIVE half is
|
||
// precisely what decides whether this is an outage or a standby nobody is using.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.ServiceUnavailable, HealthBody.Ready("Unhealthy"))
|
||
.Status("http://a:8080/health/active", HttpStatusCode.OK);
|
||
var (poller, _) = Build(
|
||
Registry(App("App", Node("a", "http://a:8080", "pair", hasActiveRole: true))),
|
||
handler,
|
||
new FakeTimeProvider(Start));
|
||
|
||
var instance = Assert.Single((await poller.SweepAsync()).AllInstances);
|
||
|
||
Assert.Equal(InstanceStatus.Down, instance.Status);
|
||
Assert.Equal(ActiveState.Active, instance.Active);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_FirstFailureAfterAGoodPoll_IsDampedThenAdopted()
|
||
{
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var time = new FakeTimeProvider(Start);
|
||
var (poller, _) = Build(Registry(App("App", Node("a", "http://a:8080"))), handler, time);
|
||
|
||
Assert.Equal(InstanceStatus.Up, Assert.Single((await poller.SweepAsync()).AllInstances).Status);
|
||
|
||
handler.Fails("http://a:8080/health/ready", "Connection refused");
|
||
|
||
time.Advance(TimeSpan.FromSeconds(10));
|
||
var damped = Assert.Single((await poller.SweepAsync()).AllInstances);
|
||
Assert.Equal(InstanceStatus.Up, damped.Status);
|
||
Assert.Equal(1, damped.ConsecutiveFailures);
|
||
|
||
time.Advance(TimeSpan.FromSeconds(10));
|
||
var adopted = Assert.Single((await poller.SweepAsync()).AllInstances);
|
||
Assert.Equal(InstanceStatus.Unreachable, adopted.Status);
|
||
Assert.Equal(2, adopted.ConsecutiveFailures);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_LastReachableSurvivesAFailedPoll()
|
||
{
|
||
// "last seen" must keep pointing at the last real contact, not reset to null the moment
|
||
// the instance goes away — that timestamp is how an operator judges how long it has been out.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var time = new FakeTimeProvider(Start);
|
||
var (poller, _) = Build(Registry(App("App", Node("a", "http://a:8080"))), handler, time);
|
||
|
||
await poller.SweepAsync();
|
||
handler.Fails("http://a:8080/health/ready", "Connection refused");
|
||
time.Advance(TimeSpan.FromSeconds(10));
|
||
|
||
var instance = Assert.Single((await poller.SweepAsync()).AllInstances);
|
||
|
||
Assert.Equal(Start, instance.LastReachableUtc);
|
||
Assert.Equal(Start.AddSeconds(10), instance.LastPolledUtc);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_BeforeAnInstanceIsDue_LeavesItAlone()
|
||
{
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var time = new FakeTimeProvider(Start);
|
||
var (poller, _) = Build(Registry(App("App", Node("a", "http://a:8080"))), handler, time);
|
||
|
||
await poller.SweepAsync();
|
||
time.Advance(TimeSpan.FromSeconds(1));
|
||
await poller.SweepAsync();
|
||
|
||
Assert.Single(handler.Requests);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_PerInstanceInterval_IsHonoured()
|
||
{
|
||
// The override is only real if a slow instance actually skips ticks while a fast one runs.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://fast:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"))
|
||
.Json("http://slow:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var time = new FakeTimeProvider(Start);
|
||
var (poller, _) = Build(
|
||
Registry(App(
|
||
"App",
|
||
Node("fast", "http://fast:8080", pollIntervalSeconds: 5),
|
||
Node("slow", "http://slow:8080", pollIntervalSeconds: 30))),
|
||
handler,
|
||
time);
|
||
|
||
for (var i = 0; i < 4; i++)
|
||
{
|
||
await poller.SweepAsync();
|
||
time.Advance(TimeSpan.FromSeconds(5));
|
||
}
|
||
|
||
Assert.Equal(4, handler.Requests.Count(r => r.Contains("fast", StringComparison.Ordinal)));
|
||
Assert.Equal(1, handler.Requests.Count(r => r.Contains("slow", StringComparison.Ordinal)));
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_DueCheckToleratesAnEarlyTick()
|
||
{
|
||
// A tick arriving a few ms early must not push the instance to half its configured rate.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var time = new FakeTimeProvider(Start);
|
||
var (poller, _) = Build(Registry(App("App", Node("a", "http://a:8080"))), handler, time);
|
||
|
||
await poller.SweepAsync();
|
||
time.Advance(TimeSpan.FromMilliseconds(9_900));
|
||
await poller.SweepAsync();
|
||
|
||
Assert.Equal(2, handler.Requests.Count);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_PublishesToTheStore()
|
||
{
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var (poller, store) = Build(Registry(App("App", Node("a", "http://a:8080"))), handler, new FakeTimeProvider(Start));
|
||
OverviewSnapshot? notified = null;
|
||
store.Changed += s => notified = s;
|
||
|
||
var returned = await poller.SweepAsync();
|
||
|
||
Assert.Same(returned, store.Current);
|
||
Assert.Same(returned, notified);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_CarriesRegistryMetadataOntoEveryCard()
|
||
{
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"))
|
||
.Status("http://a:8080/health/active", HttpStatusCode.OK);
|
||
var application = App("ScadaBridge", Node("central-a", "http://a:8080", "central", hasActiveRole: true));
|
||
application.Instances[0].ManagementUrl = "http://a:9000/";
|
||
var (poller, _) = Build(Registry(application), handler, new FakeTimeProvider(Start));
|
||
|
||
var instance = Assert.Single((await poller.SweepAsync()).AllInstances);
|
||
|
||
Assert.Equal("ScadaBridge", instance.Application);
|
||
Assert.Equal("central", instance.Group);
|
||
Assert.Equal("AdminUI", instance.ManagementLabel);
|
||
Assert.Equal("http://a:9000/", instance.ManagementUrl);
|
||
Assert.Equal(TimeSpan.FromSeconds(45), instance.StaleAfter);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_ResolvesGroupLeadersIntoTheSnapshot()
|
||
{
|
||
const string leader = "akka.tcp://scadabridge@a:8082";
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8084/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy", ("akka-cluster", "Healthy", leader)))
|
||
.Status("http://a:8084/health/active", HttpStatusCode.OK)
|
||
.Json("http://b:8084/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy", ("akka-cluster", "Healthy", leader)))
|
||
.Status("http://b:8084/health/active", HttpStatusCode.ServiceUnavailable);
|
||
var (poller, _) = Build(
|
||
Registry(App(
|
||
"ScadaBridge",
|
||
Node("site-a-a", "http://a:8084", "site-a", hasActiveRole: true),
|
||
Node("site-a-b", "http://b:8084", "site-a", hasActiveRole: true))),
|
||
handler,
|
||
new FakeTimeProvider(Start));
|
||
|
||
var application = Assert.Single((await poller.SweepAsync()).Applications);
|
||
var group = Assert.Single(application.Groups);
|
||
|
||
Assert.Equal("site-a", group.Name);
|
||
Assert.Equal("site-a-a", group.LeaderInstance);
|
||
Assert.False(group.Disagreement);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_WorstStatusRollsUpAcrossTheApplication()
|
||
{
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"))
|
||
.Json("http://b:8080/health/ready", HttpStatusCode.ServiceUnavailable, HealthBody.Ready("Unhealthy"));
|
||
var (poller, _) = Build(
|
||
Registry(App("App", Node("a", "http://a:8080"), Node("b", "http://b:8080"))),
|
||
handler,
|
||
new FakeTimeProvider(Start));
|
||
|
||
var application = Assert.Single((await poller.SweepAsync()).Applications);
|
||
|
||
Assert.Equal(InstanceStatus.Down, application.Worst);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_OneSlowInstanceDoesNotDelayTheOthers()
|
||
{
|
||
// The fan-out must be genuinely parallel: a serial sweep over a fleet with several dead
|
||
// nodes would take timeout × dead-node-count and starve the whole dashboard.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"))
|
||
.Json("http://b:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var options = Registry(App("App", Node("a", "http://a:8080"), Node("b", "http://b:8080")));
|
||
var gate = new SemaphoreSlim(0);
|
||
var (poller, _) = Build(options, new GatedHandler(handler, gate), new FakeTimeProvider(Start));
|
||
|
||
var sweep = poller.SweepAsync();
|
||
Assert.False(sweep.IsCompleted);
|
||
|
||
// Both probes must already be in flight; releasing one at a time proves neither waited.
|
||
gate.Release(2);
|
||
var snapshot = await sweep.WaitAsync(TimeSpan.FromSeconds(10));
|
||
|
||
Assert.All(snapshot.AllInstances, i => Assert.Equal(InstanceStatus.Up, i.Status));
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_UnregisteredInstances_RenderAsPendingNotAsHealthy()
|
||
{
|
||
// Between host start and the first probe the registry is already published so the page has
|
||
// its layout. Those cards must read "pending", never an unmeasured "Up".
|
||
var handler = new RoutingHandler();
|
||
var (poller, store) = Build(Registry(App("App", Node("a", "http://a:8080"))), handler, new FakeTimeProvider(Start));
|
||
|
||
Assert.Empty(store.Current.Applications);
|
||
|
||
handler.Fails("http://a:8080/health/ready", "Connection refused");
|
||
var instance = Assert.Single((await poller.SweepAsync()).AllInstances);
|
||
|
||
Assert.Equal(InstanceStatus.Unreachable, instance.Status);
|
||
}
|
||
|
||
[Fact]
|
||
public void PendingSnapshot_IsNeverStale()
|
||
{
|
||
// Staleness on a card that has never been polled would be meaningless and alarming.
|
||
var pending = Snapshots.Instance("a", status: null);
|
||
|
||
Assert.False(pending.IsStale(Start.AddYears(1)));
|
||
}
|
||
|
||
[Fact]
|
||
public void Snapshot_GoesStaleOnceItsWindowElapses()
|
||
{
|
||
var polled = Snapshots.Instance("a") with { LastPolledUtc = Start, StaleAfter = TimeSpan.FromSeconds(45) };
|
||
|
||
Assert.False(polled.IsStale(Start.AddSeconds(45)));
|
||
Assert.True(polled.IsStale(Start.AddSeconds(46)));
|
||
}
|
||
|
||
[Fact]
|
||
public async Task Sweep_HostShutdown_AbandonsTheSweepInsteadOfRecordingFailures()
|
||
{
|
||
// Writing "Unreachable" across the registry on the way out would leave a lie in the store.
|
||
var handler = new RoutingHandler()
|
||
.Json("http://a:8080/health/ready", HttpStatusCode.OK, HealthBody.Ready("Healthy"));
|
||
var (poller, store) = Build(Registry(App("App", Node("a", "http://a:8080"))), handler, new FakeTimeProvider(Start));
|
||
using var shutdown = new CancellationTokenSource();
|
||
await shutdown.CancelAsync();
|
||
|
||
await Assert.ThrowsAnyAsync<OperationCanceledException>(() => poller.SweepAsync(shutdown.Token));
|
||
|
||
Assert.Empty(store.Current.Applications);
|
||
}
|
||
|
||
[Fact]
|
||
public async Task EmptyRegistry_StartsAndStopsWithoutProbing()
|
||
{
|
||
var (poller, _) = Build(Registry(), new RoutingHandler(), new FakeTimeProvider(Start));
|
||
|
||
await poller.StartAsync(CancellationToken.None);
|
||
await poller.StopAsync(CancellationToken.None);
|
||
}
|
||
|
||
/// <summary>Holds every request until the test releases it, proving the fan-out is concurrent.</summary>
|
||
private sealed class GatedHandler(RoutingHandler inner, SemaphoreSlim gate) : HttpMessageHandler
|
||
{
|
||
protected override async Task<HttpResponseMessage> SendAsync(
|
||
HttpRequestMessage request, CancellationToken cancellationToken)
|
||
{
|
||
await gate.WaitAsync(cancellationToken).ConfigureAwait(false);
|
||
return await inner.HandleAsync(request).ConfigureAwait(false);
|
||
}
|
||
}
|
||
}
|