diff --git a/ZB.MOM.WW.Secrets/CHANGELOG.md b/ZB.MOM.WW.Secrets/CHANGELOG.md index 2544c74..8e86708 100644 --- a/ZB.MOM.WW.Secrets/CHANGELOG.md +++ b/ZB.MOM.WW.Secrets/CHANGELOG.md @@ -5,6 +5,34 @@ follows [Keep a Changelog](https://keepachangelog.com/); versions are shared acr package in the family (see `Directory.Build.props`) even when a given release only touches one of them. +## 0.5.0 — Unreleased + +### Added + +- **`ZB.MOM.WW.Secrets.Replicator.Grpc` — hub endpoint failover for followers** + (scadaproj#4). `SecretsGrpcHubClientOptions` gains `FallbackEndpoints`: additional hub + addresses tried, in order, when a call to the primary `Endpoint` (or an earlier fallback) + fails with a transport-level gRPC error. The answering endpoint is sticky — a sweep that + failed over does not re-pay the dead endpoint's full `CallDeadline` on every subsequent + call — and rotation wraps, so a recovered primary is retried the next time the stuck-to + endpoint fails. Only `RpcException` triggers failover; cancellation and everything else + propagate untouched, and when every endpoint fails the last `RpcException` is rethrown so + the sweep degrades to last-known-good exactly as before. Each failover logs a Warning + naming the failed and next endpoint URIs (never any credential material). + - **Same-store requirement:** list only endpoints that serve the SAME store — for + ScadaBridge, the central pair over one shared SQL Server store. Endpoints backed by + independent stores turn a primary outage into a silent convergence stop (failing over + to an emptier hub "succeeds"), which is the exact defect scadaproj#4 recorded. + - Validation fails startup on a blank/relative fallback or one duplicating the primary + or another fallback (a duplicated endpoint silently halves the configured failover). + +### Unchanged + +- With `FallbackEndpoints` empty (the default), the registration graph is identical to + 0.4.x — one keyed channel, one `GrpcSecretsHubClient`, no failover wrapper — and the wire + behavior of every call is byte-identical. Every other package in the family is + behaviorally unchanged in this release. + ## 0.4.1 — 2026-08-07 ### Fixed diff --git a/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/DependencyInjection/SecretsGrpcHubClientExtensions.cs b/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/DependencyInjection/SecretsGrpcHubClientExtensions.cs index 8ad6847..2b9658a 100644 --- a/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/DependencyInjection/SecretsGrpcHubClientExtensions.cs +++ b/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/DependencyInjection/SecretsGrpcHubClientExtensions.cs @@ -45,6 +45,13 @@ public static class SecretsGrpcHubClientExtensions /// means local writes never leave the node, so there is nothing to publish and the store stays /// exactly as the application configured it. A host that forgets AddZbSecrets fails loudly /// at startup when the sweep cannot resolve the store, rather than silently replicating nothing. + /// + /// When is non-empty, one keyed + /// channel and one client are registered per endpoint and the reader becomes a + /// composed over them, primary first. With the list + /// empty — the default — the registration graph is identical to releases before the list + /// existed: one keyed channel, one , no failover wrapper. + /// /// /// The service collection to add to. /// The application configuration. @@ -82,15 +89,79 @@ public static class SecretsGrpcHubClientExtensions services.TryAddKeyedSingleton(ChannelServiceKey, (sp, _) => GrpcChannel.ForAddress( sp.GetRequiredService>().Value.Endpoint)); - services.TryAddSingleton(sp => new GrpcSecretsHubClient( - new SecretsHub.SecretsHubClient( - sp.GetRequiredKeyedService(ChannelServiceKey)), - sp.GetRequiredService>(), - sp.GetRequiredService>(), - sp.GetService())); + if (eager.FallbackEndpoints.Count == 0) + { + // No fallbacks: the graph is exactly the pre-0.5.0 one — the single keyed channel above + // plus one GrpcSecretsHubClient as the reader. Kept as its own branch rather than a + // one-element failover composition so existing consumers see an identical container + // shape and zero added indirection on every call. + services.TryAddSingleton(sp => new GrpcSecretsHubClient( + new SecretsHub.SecretsHubClient( + sp.GetRequiredKeyedService(ChannelServiceKey)), + sp.GetRequiredService>(), + sp.GetRequiredService>(), + sp.GetService())); + } + else + { + // One keyed channel per fallback, each a container-owned singleton for the same + // disposal reason as the primary. The loop variable is copied because the factory + // closes over it and runs long after the loop has finished. + for (int i = 0; i < eager.FallbackEndpoints.Count; i++) + { + int index = i; + services.TryAddKeyedSingleton( + FallbackChannelServiceKey(index), + (sp, _) => GrpcChannel.ForAddress(sp + .GetRequiredService>() + .Value.FallbackEndpoints[index])); + } + + services.TryAddSingleton(sp => + { + IOptions options = + sp.GetRequiredService>(); + ILogger clientLogger = + sp.GetRequiredService>(); + TimeProvider? timeProvider = sp.GetService(); + + GrpcSecretsHubClient ReaderOver(object channelKey) => new( + new SecretsHub.SecretsHubClient( + sp.GetRequiredKeyedService(channelKey)), + options, + clientLogger, + timeProvider); + + IList fallbacks = options.Value.FallbackEndpoints; + var readers = new List(1 + fallbacks.Count) + { + ReaderOver(ChannelServiceKey), + }; + var labels = new List(1 + fallbacks.Count) { options.Value.Endpoint }; + + for (int index = 0; index < fallbacks.Count; index++) + { + readers.Add(ReaderOver(FallbackChannelServiceKey(index))); + labels.Add(fallbacks[index]); + } + + return new FailoverSecretsHubReader( + readers, labels, sp.GetRequiredService>()); + }); + } services.AddHostedService(); return services; } + + /// + /// Service key for the keyed dialing the fallback endpoint at + /// in . + /// The primary endpoint's channel keeps unchanged. + /// + /// Zero-based index into the fallback list. + /// The service key. + internal static string FallbackChannelServiceKey(int index) => + $"{ChannelServiceKey}:fallback:{index}"; } diff --git a/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/FailoverSecretsHubReader.cs b/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/FailoverSecretsHubReader.cs new file mode 100644 index 0000000..8ad8fe4 --- /dev/null +++ b/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/FailoverSecretsHubReader.cs @@ -0,0 +1,141 @@ +using Grpc.Core; +using Microsoft.Extensions.Logging; +using ZB.MOM.WW.Secrets.Abstractions; + +namespace ZB.MOM.WW.Secrets.Replicator.Grpc; + +/// +/// An over several single-endpoint readers: tries each endpoint in +/// rotation order until one answers, remembering the one that did. +/// +/// +/// +/// Safe only when every endpoint serves the same store. This type exists for ScadaBridge's +/// central pair over one shared SQL Server store, where either central answers with the truth. +/// Composed over endpoints with independent stores it would turn a primary outage into a silent +/// convergence stop — the fallback "succeeds" against an emptier inventory (scadaproj#4). The DI +/// extension's options doc carries the same warning where operators author the list. +/// +/// +/// The answering endpoint is sticky. A sweep is one GetManifest plus N +/// GetSecrets batches; without stickiness every call after a primary outage would re-pay the +/// primary's failure — a full CallDeadline of latency — before reaching the healthy fallback. +/// So each call starts at the last endpoint that answered (initially the primary) and rotates from +/// there, which also means a recovered primary is retried naturally the next time the stuck-to +/// endpoint fails, rather than being probed on a timer. +/// +/// +/// Only triggers failover. It is the one signal that means "this +/// endpoint did not usefully answer". is the host stopping +/// — dialing another endpoint with a cancelled token would only delay shutdown — and anything else +/// is a defect, which retrying elsewhere would mask. Both propagate untouched. When every endpoint +/// fails, the last is rethrown so the sweep's catch-all handles +/// it exactly as it handles a single-endpoint outage today. +/// +/// +internal sealed partial class FailoverSecretsHubReader : ISecretsHubReader +{ + private readonly IReadOnlyList _readers; + private readonly IReadOnlyList _endpointLabels; + private readonly ILogger _logger; + + /// + /// Index of the last endpoint that answered; every call starts its rotation here. Read and + /// written with — a torn or stale value costs at worst one extra failed + /// dial, never a wrong result, so a lock would buy nothing. + /// + private int _stickyIndex; + + /// Creates the failover reader. + /// One reader per endpoint, primary first — rotation order. + /// + /// The endpoint URI each reader dials, index-aligned with . Used only + /// in log messages: a URI is not a secret, and naming both sides of a failover is what makes the + /// warning actionable. + /// + /// Logger for failover warnings. + /// + /// is empty or the two lists differ in length. + /// + public FailoverSecretsHubReader( + IReadOnlyList readers, + IReadOnlyList endpointLabels, + ILogger logger) + { + ArgumentNullException.ThrowIfNull(readers); + ArgumentNullException.ThrowIfNull(endpointLabels); + + if (readers.Count == 0) + { + throw new ArgumentException("At least one hub reader is required.", nameof(readers)); + } + + if (readers.Count != endpointLabels.Count) + { + throw new ArgumentException( + $"Endpoint labels ({endpointLabels.Count}) must align one-to-one with readers " + + $"({readers.Count}).", + nameof(endpointLabels)); + } + + _readers = readers; + _endpointLabels = endpointLabels; + _logger = logger ?? throw new ArgumentNullException(nameof(logger)); + } + + /// + public Task> GetManifestAsync(CancellationToken ct) => + ExecuteWithFailoverAsync(static (reader, token) => reader.GetManifestAsync(token), ct); + + /// + public Task> GetManyAsync( + IReadOnlyList names, CancellationToken ct) => + ExecuteWithFailoverAsync((reader, token) => reader.GetManyAsync(names, token), ct); + + // The one rotation, shared by both RPCs so their failover behaviour cannot drift apart. + private async Task ExecuteWithFailoverAsync( + Func> call, CancellationToken ct) + { + int start = Volatile.Read(ref _stickyIndex); + RpcException? lastFailure = null; + + for (int attempt = 0; attempt < _readers.Count; attempt++) + { + int index = (start + attempt) % _readers.Count; + + try + { + T result = await call(_readers[index], ct).ConfigureAwait(false); + Volatile.Write(ref _stickyIndex, index); + return result; + } + catch (RpcException ex) + { + lastFailure = ex; + + if (attempt < _readers.Count - 1) + { + // The message carries the two endpoint URIs and the status code — nothing from + // the exception detail, which is server-authored text no credential belongs in + // but this node cannot vouch for. + LogEndpointFailedOver( + ex, + _endpointLabels[index], + ex.StatusCode, + _endpointLabels[(start + attempt + 1) % _readers.Count]); + } + } + } + + // Every endpoint failed. Rethrowing the LAST failure hands the sweep's catch-all the + // freshest evidence; it logs and retries next tick exactly as for a single endpoint. + throw lastFailure!; + } + + [LoggerMessage( + EventId = 1, + Level = LogLevel.Warning, + Message = "Secrets hub endpoint {FailedEndpoint} did not answer ({StatusCode}); failing over to {NextEndpoint}.")] + private partial void LogEndpointFailedOver( + Exception exception, string failedEndpoint, StatusCode statusCode, string nextEndpoint); +} diff --git a/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/SecretsGrpcHubClientOptions.cs b/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/SecretsGrpcHubClientOptions.cs index 469ee3f..a832079 100644 --- a/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/SecretsGrpcHubClientOptions.cs +++ b/ZB.MOM.WW.Secrets/src/ZB.MOM.WW.Secrets.Replicator.Grpc/SecretsGrpcHubClientOptions.cs @@ -28,6 +28,21 @@ public sealed class SecretsGrpcHubClientOptions /// public string Endpoint { get; set; } = string.Empty; + /// + /// Additional hub addresses tried, in order, when a call to (or an + /// earlier fallback) fails with a transport-level gRPC error. Optional; empty by default. + /// Meaningful only when every listed endpoint serves the SAME store — for ScadaBridge that + /// is the central pair over one shared SQL Server store. Do NOT list endpoints backed by + /// independent stores: failing over to an emptier hub is a silent convergence stop, which is + /// the exact defect (scadaproj#4) the shared store exists to prevent. + /// + /// + /// Getter-only so the configuration binder adds entries to this instance rather than needing a + /// setter. Each entry carries the same http-cleartext caveat as : a plain + /// http fallback sends in cleartext on every failed-over call. + /// + public IList FallbackEndpoints { get; } = []; + /// /// Shared bearer token presented on every call. Required — an unset token is a hard startup /// failure rather than an anonymous call, because the hub authenticates on this alone. @@ -69,8 +84,9 @@ public sealed class SecretsGrpcHubClientOptions /// operator actually has to edit rather than the default one. /// /// - /// The endpoint is missing or is not an absolute http/https URI, the bearer token is missing, or - /// an interval is not positive. + /// The endpoint is missing or is not an absolute http/https URI, a fallback endpoint is blank, + /// not an absolute http/https URI, or duplicates another endpoint, the bearer token is missing, + /// or an interval is not positive. /// public void Validate(string sectionPath = DefaultSectionPath) { @@ -92,6 +108,35 @@ public sealed class SecretsGrpcHubClientOptions $"({sectionPath}:Endpoint, was '{Endpoint}')."); } + var seenEndpoints = new HashSet(StringComparer.OrdinalIgnoreCase) { Endpoint }; + + foreach (string fallback in FallbackEndpoints) + { + if (string.IsNullOrWhiteSpace(fallback)) + { + throw new InvalidOperationException( + $"gRPC secrets hub client fallback endpoints must not be blank " + + $"({sectionPath}:FallbackEndpoints)."); + } + + if (!Uri.TryCreate(fallback, UriKind.Absolute, out Uri? fallbackUri) || + (fallbackUri.Scheme != Uri.UriSchemeHttp && fallbackUri.Scheme != Uri.UriSchemeHttps)) + { + throw new InvalidOperationException( + $"gRPC secrets hub client fallback endpoints must be absolute http or https " + + $"URIs ({sectionPath}:FallbackEndpoints, entry '{fallback}')."); + } + + if (!seenEndpoints.Add(fallback)) + { + // A duplicated endpoint silently halves the failover the operator thinks they + // configured: the rotation would try the same address twice and call it two tries. + throw new InvalidOperationException( + $"gRPC secrets hub client fallback endpoints must not repeat the Endpoint or " + + $"each other ({sectionPath}:FallbackEndpoints, entry '{fallback}')."); + } + } + if (string.IsNullOrWhiteSpace(BearerToken)) { // Fail closed. An empty token would otherwise be presented as `Bearer `, which the hub diff --git a/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/FailoverSecretsHubReaderTests.cs b/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/FailoverSecretsHubReaderTests.cs new file mode 100644 index 0000000..6c4c1b6 --- /dev/null +++ b/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/FailoverSecretsHubReaderTests.cs @@ -0,0 +1,266 @@ +using Grpc.Core; +using ZB.MOM.WW.Secrets.Abstractions; + +namespace ZB.MOM.WW.Secrets.Replicator.Grpc.Tests; + +/// +/// Rotation, stickiness and containment behaviour of the multi-endpoint hub reader. Exercised +/// against scripted fakes: the per-endpoint wire behaviour (headers, +/// deadlines, parse isolation) belongs to GrpcSecretsHubClient and is tested there — this +/// suite is only about which endpoint gets asked, in what order, and what escapes when they all fail. +/// +public sealed class FailoverSecretsHubReaderTests +{ + private const string PrimaryEndpoint = "https://central-a:5001"; + private const string FallbackEndpoint = "https://central-b:5001"; + + private readonly ScriptedHubReader _primary = new(); + private readonly ScriptedHubReader _fallback = new(); + private readonly RecordingLogger _logger = new(); + + private FailoverSecretsHubReader CreateReader() => new( + [_primary, _fallback], + [PrimaryEndpoint, FallbackEndpoint], + _logger); + + private static RpcException Unavailable() => new(new Status( + StatusCode.Unavailable, "connection refused")); + + [Fact] + public async Task A_healthy_primary_is_the_only_endpoint_asked() + { + FailoverSecretsHubReader reader = CreateReader(); + + await reader.GetManifestAsync(CancellationToken.None); + await reader.GetManyAsync([new SecretName("db/password")], CancellationToken.None); + + Assert.Equal(1, _primary.ManifestCalls); + Assert.Equal(1, _primary.ManyCalls); + Assert.Equal(0, _fallback.ManifestCalls); + Assert.Equal(0, _fallback.ManyCalls); + Assert.Equal(0, _logger.WarningCount); + } + + [Fact] + public async Task A_transport_fault_on_the_primary_fails_over_to_the_fallback() + { + _primary.FaultWith = Unavailable; + _fallback.Manifest = [Entry("db/password")]; + + IReadOnlyList manifest = + await CreateReader().GetManifestAsync(CancellationToken.None); + + Assert.Single(manifest); + Assert.Equal(1, _primary.ManifestCalls); + Assert.Equal(1, _fallback.ManifestCalls); + } + + [Fact] + public async Task The_failover_warning_names_both_endpoints() + { + _primary.FaultWith = Unavailable; + + await CreateReader().GetManifestAsync(CancellationToken.None); + + string warning = Assert.Single(_logger.Warnings); + Assert.Contains(PrimaryEndpoint, warning, StringComparison.Ordinal); + Assert.Contains(FallbackEndpoint, warning, StringComparison.Ordinal); + } + + [Fact] + public async Task GetMany_fails_over_too() + { + _primary.FaultWith = Unavailable; + _fallback.Rows = [Row("db/password")]; + + IReadOnlyList rows = await CreateReader() + .GetManyAsync([new SecretName("db/password")], CancellationToken.None); + + Assert.Single(rows); + Assert.Equal(1, _primary.ManyCalls); + Assert.Equal(1, _fallback.ManyCalls); + } + + [Fact] + public async Task The_endpoint_that_answered_is_sticky_for_the_next_call() + { + // A sweep is one GetManifest plus N GetSecrets batches. Without stickiness, every call + // after a primary outage would re-pay the primary's full CallDeadline of latency before + // reaching the fallback that is actually answering. + _primary.FaultWith = Unavailable; + FailoverSecretsHubReader reader = CreateReader(); + + await reader.GetManifestAsync(CancellationToken.None); + await reader.GetManyAsync([new SecretName("db/password")], CancellationToken.None); + + Assert.Equal(1, _primary.ManifestCalls); + Assert.Equal(0, _primary.ManyCalls); + Assert.Equal(1, _fallback.ManyCalls); + } + + [Fact] + public async Task Rotation_wraps_back_to_a_recovered_primary_when_the_fallback_fails_in_turn() + { + _primary.FaultWith = Unavailable; + FailoverSecretsHubReader reader = CreateReader(); + + // Sticks to the fallback… + await reader.GetManifestAsync(CancellationToken.None); + + // …then the fallback dies and the primary has recovered. + _primary.FaultWith = null; + _fallback.FaultWith = Unavailable; + + await reader.GetManifestAsync(CancellationToken.None); + + Assert.Equal(2, _primary.ManifestCalls); + Assert.Equal(2, _fallback.ManifestCalls); + } + + [Fact] + public async Task When_every_endpoint_fails_the_last_exception_is_rethrown() + { + var primaryFault = new RpcException(new Status(StatusCode.Unavailable, "primary down")); + var fallbackFault = new RpcException(new Status(StatusCode.DeadlineExceeded, "fallback down")); + _primary.FaultWith = () => primaryFault; + _fallback.FaultWith = () => fallbackFault; + + RpcException thrown = await Assert.ThrowsAsync( + () => CreateReader().GetManifestAsync(CancellationToken.None)); + + // The LAST endpoint tried, so the sweep's catch-all logs the freshest failure rather than + // one from an endpoint a later attempt already moved past. + Assert.Same(fallbackFault, thrown); + } + + [Fact] + public async Task Cancellation_propagates_immediately_without_failing_over() + { + // Cancellation is the host stopping, not an endpoint fault — dialing the fallback with an + // already-cancelled token would only delay shutdown by another deadline. + _primary.FaultWith = () => new OperationCanceledException(); + + await Assert.ThrowsAsync( + () => CreateReader().GetManifestAsync(CancellationToken.None)); + + Assert.Equal(0, _fallback.ManifestCalls); + Assert.Equal(0, _logger.WarningCount); + } + + [Fact] + public async Task A_non_transport_exception_propagates_immediately_without_failing_over() + { + _primary.FaultWith = () => new InvalidOperationException("a defect, not an outage"); + + await Assert.ThrowsAsync( + () => CreateReader().GetManifestAsync(CancellationToken.None)); + + Assert.Equal(0, _fallback.ManifestCalls); + } + + [Fact] + public async Task No_failover_log_message_carries_token_material() + { + // The warning's whole content is the two endpoint URIs (not secrets) and the gRPC status + // code. Even a status detail that happens to quote a credential must not reach the message. + const string leak = "s3cr3t-bearer-token"; + _primary.FaultWith = () => new RpcException(new Status( + StatusCode.Unauthenticated, $"Bearer {leak} rejected")); + + await CreateReader().GetManifestAsync(CancellationToken.None); + + foreach (string warning in _logger.Warnings) + { + Assert.DoesNotContain(leak, warning, StringComparison.OrdinalIgnoreCase); + } + + Assert.Equal(1, _logger.WarningCount); + } + + [Fact] + public async Task Concurrent_calls_share_the_sticky_index_without_tearing() + { + // The sticky index is plain shared state written from every call path; this pins that + // parallel sweeps (manifest + batches overlapping) never corrupt it or deadlock. + _primary.FaultWith = Unavailable; + FailoverSecretsHubReader reader = CreateReader(); + + await Task.WhenAll(Enumerable.Range(0, 32).Select(async _ => + { + IReadOnlyList manifest = + await reader.GetManifestAsync(CancellationToken.None); + Assert.NotNull(manifest); + })); + + // Every one of the 32 calls ended on the answering fallback. + Assert.Equal(32, _fallback.ManifestCalls); + // And the index is now stuck there: one more call never touches the primary. + int primaryCallsBefore = _primary.ManifestCalls; + await reader.GetManifestAsync(CancellationToken.None); + Assert.Equal(primaryCallsBefore, _primary.ManifestCalls); + } + + private static SecretManifestEntry Entry(string name) => new() + { + Name = new SecretName(name), + Revision = 0, + UpdatedUtc = TestWire.FixedInstant, + }; + + private static StoredSecret Row(string name) => new() + { + Name = new SecretName(name), + ContentType = SecretContentType.Text, + Ciphertext = [0xAA], + Nonce = [1], + Tag = [2], + WrappedDek = [3], + WrapNonce = [4], + WrapTag = [5], + KekId = "sha256:test", + Revision = 0, + CreatedUtc = TestWire.FixedInstant, + UpdatedUtc = TestWire.FixedInstant, + }; + + /// + /// An standing in for one endpoint's client: counts calls, + /// answers from canned data, or faults with whatever a test scripts. + /// + private sealed class ScriptedHubReader : ISecretsHubReader + { + /// Number of GetManifest calls received. + public int ManifestCalls; + + /// Number of GetMany calls received. + public int ManyCalls; + + /// When set, every call throws this instead of answering. + public Func? FaultWith { get; set; } + + /// Canned manifest returned when not faulted. + public IReadOnlyList Manifest { get; set; } = []; + + /// Canned rows returned when not faulted. + public IReadOnlyList Rows { get; set; } = []; + + /// + public Task> GetManifestAsync(CancellationToken ct) + { + Interlocked.Increment(ref ManifestCalls); + return FaultWith is { } fault + ? Task.FromException>(fault()) + : Task.FromResult(Manifest); + } + + /// + public Task> GetManyAsync( + IReadOnlyList names, CancellationToken ct) + { + Interlocked.Increment(ref ManyCalls); + return FaultWith is { } fault + ? Task.FromException>(fault()) + : Task.FromResult(Rows); + } + } +} diff --git a/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/GrpcSecretSyncServiceTests.cs b/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/GrpcSecretSyncServiceTests.cs index c4d396b..f410ec4 100644 --- a/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/GrpcSecretSyncServiceTests.cs +++ b/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/GrpcSecretSyncServiceTests.cs @@ -452,6 +452,82 @@ public sealed class GrpcSecretSyncServiceTests : IDisposable SecretsGrpcHubClientExtensions.ChannelServiceKey)); } + [Fact] + public void Registration_with_no_fallbacks_resolves_the_plain_single_endpoint_client() + { + // The zero-fallback registration graph is the pre-0.5.0 one, unchanged: one keyed channel, + // one GrpcSecretsHubClient as the reader. Consumers wired before FallbackEndpoints existed + // must see an identical container shape. + ServiceCollection services = new(); + services.AddLogging(); + services.AddZbSecretsGrpcHubClient(HubConfig()); + + using ServiceProvider provider = services.BuildServiceProvider(); + + Assert.IsType(provider.GetRequiredService()); + Assert.NotNull(provider.GetRequiredKeyedService( + SecretsGrpcHubClientExtensions.ChannelServiceKey)); + Assert.Null(provider.GetKeyedService( + $"{SecretsGrpcHubClientExtensions.ChannelServiceKey}:fallback:0")); + } + + [Fact] + public void Registration_with_fallbacks_resolves_the_failover_reader_over_one_channel_per_endpoint() + { + ServiceCollection services = new(); + services.AddLogging(); + services.AddZbSecretsGrpcHubClient(HubConfig(new Dictionary + { + ["Secrets:GrpcHub:FallbackEndpoints:0"] = "https://central-b:5001", + ["Secrets:GrpcHub:FallbackEndpoints:1"] = "https://central-c:5001", + })); + + using ServiceProvider provider = services.BuildServiceProvider(); + + Assert.IsType(provider.GetRequiredService()); + + GrpcChannel primary = provider.GetRequiredKeyedService( + SecretsGrpcHubClientExtensions.ChannelServiceKey); + GrpcChannel fallback0 = provider.GetRequiredKeyedService( + $"{SecretsGrpcHubClientExtensions.ChannelServiceKey}:fallback:0"); + GrpcChannel fallback1 = provider.GetRequiredKeyedService( + $"{SecretsGrpcHubClientExtensions.ChannelServiceKey}:fallback:1"); + + // Each channel dials its own endpoint — three distinct singletons, container-owned. + Assert.Equal("central-a:5001", primary.Target); + Assert.Equal("central-b:5001", fallback0.Target); + Assert.Equal("central-c:5001", fallback1.Target); + } + + [Fact] + public void Registration_refuses_a_malformed_fallback_endpoint_at_startup() + { + InvalidOperationException ex = Assert.Throws(() => + new ServiceCollection().AddZbSecretsGrpcHubClient(HubConfig(new Dictionary + { + ["Secrets:GrpcHub:FallbackEndpoints:0"] = "not a uri", + }))); + + Assert.Contains("Secrets:GrpcHub:FallbackEndpoints", ex.Message, StringComparison.Ordinal); + } + + // A minimal valid hub-client configuration, extendable per test. + private static IConfiguration HubConfig(Dictionary? extra = null) + { + var values = new Dictionary + { + ["Secrets:GrpcHub:Endpoint"] = "https://central-a:5001", + ["Secrets:GrpcHub:BearerToken"] = "token", + }; + + foreach ((string key, string? value) in extra ?? []) + { + values[key] = value; + } + + return new ConfigurationBuilder().AddInMemoryCollection(values).Build(); + } + // Runs the hosted service through one startup sweep and shuts it down, asserting that nothing // escaped ExecuteAsync. The long sync interval means exactly one sweep happens. private async Task RunOneStartupSweepAsync(Func sweepObserved) diff --git a/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/SecretsGrpcHubClientOptionsTests.cs b/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/SecretsGrpcHubClientOptionsTests.cs index cec924d..3e207c6 100644 --- a/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/SecretsGrpcHubClientOptionsTests.cs +++ b/ZB.MOM.WW.Secrets/tests/ZB.MOM.WW.Secrets.Replicator.Grpc.Tests/SecretsGrpcHubClientOptionsTests.cs @@ -75,6 +75,8 @@ public sealed class SecretsGrpcHubClientOptionsTests o => o.BearerToken = string.Empty, o => o.SyncInterval = TimeSpan.Zero, o => o.CallDeadline = TimeSpan.FromSeconds(-1), + o => o.FallbackEndpoints.Add("not a uri"), + o => o.FallbackEndpoints.Add("https://central:5001"), ]; [Theory] @@ -116,6 +118,64 @@ public sealed class SecretsGrpcHubClientOptionsTests Assert.Contains("Secrets:GrpcHub:CallDeadline", ex.Message, StringComparison.Ordinal); } + [Fact] + public void Zero_fallback_endpoints_is_valid_and_the_default() + { + SecretsGrpcHubClientOptions options = Valid(); + + Assert.Empty(options.FallbackEndpoints); + options.Validate(); + } + + [Fact] + public void A_well_formed_fallback_endpoint_validates() + { + SecretsGrpcHubClientOptions options = Valid(); + options.FallbackEndpoints.Add("https://central-b:5001"); + options.FallbackEndpoints.Add("http://central-c:5001"); + + options.Validate(); + } + + [Theory] + [InlineData("")] + [InlineData(" ")] + [InlineData("central-b:5001")] + [InlineData("/relative/path")] + [InlineData("ftp://central-b:5001")] + public void A_fallback_that_is_not_an_absolute_http_uri_names_its_key(string fallback) + { + SecretsGrpcHubClientOptions options = Valid(); + options.FallbackEndpoints.Add(fallback); + + InvalidOperationException ex = Assert.Throws(() => options.Validate()); + Assert.Contains("Secrets:GrpcHub:FallbackEndpoints", ex.Message, StringComparison.Ordinal); + } + + [Theory] + [InlineData("https://central:5001")] + [InlineData("HTTPS://CENTRAL:5001")] + public void A_fallback_duplicating_the_primary_endpoint_names_its_key(string fallback) + { + // A duplicated endpoint silently halves the failover the operator thinks they configured. + SecretsGrpcHubClientOptions options = Valid(); + options.FallbackEndpoints.Add(fallback); + + InvalidOperationException ex = Assert.Throws(() => options.Validate()); + Assert.Contains("Secrets:GrpcHub:FallbackEndpoints", ex.Message, StringComparison.Ordinal); + } + + [Fact] + public void A_fallback_duplicating_another_fallback_names_its_key() + { + SecretsGrpcHubClientOptions options = Valid(); + options.FallbackEndpoints.Add("https://central-b:5001"); + options.FallbackEndpoints.Add("HTTPS://central-B:5001"); + + InvalidOperationException ex = Assert.Throws(() => options.Validate()); + Assert.Contains("Secrets:GrpcHub:FallbackEndpoints", ex.Message, StringComparison.Ordinal); + } + [Fact] public void Messages_name_the_section_the_caller_actually_bound() {