Phase 3 PR 72 -- Multi-endpoint failover for OPC UA Client driver. Adds OpcUaClientDriverOptions.EndpointUrls ordered list + PerEndpointConnectTimeout knob. On InitializeAsync the driver walks the candidate list in order via ResolveEndpointCandidates and returns the session from the first endpoint that successfully connects. Captures per-URL failure reasons in a List<string> and, if every candidate fails, throws AggregateException whose message names every URL + its failure class (e.g. 'opc.tcp://primary:4840 -> TimeoutException: ...'). That's critical diag for field debugging -- without it 'failover picked the wrong one' surfaces as a mystery. Single-URL backwards compat: EndpointUrl field retained as a one-URL shortcut. When EndpointUrls is null or empty the driver falls through to a single-candidate list of [EndpointUrl], so every existing single-endpoint config keeps working without migration. When both are provided, EndpointUrls wins + EndpointUrl is ignored -- documented on the field xml-doc. Per-endpoint connect budget: PerEndpointConnectTimeout (default 3s) caps each attempt so a sweep over several dead servers can't blow the overall init budget. Applied via CancellationTokenSource.CreateLinkedTokenSource + CancelAfter inside OpenSessionOnEndpointAsync (the extracted single-endpoint connect helper) so the cap is independent of the outer Options.Timeout which governs steady-state ops. BuildUserIdentity extracted out of InitializeAsync so the failover loop builds the UserIdentity ONCE and reuses it across every endpoint attempt -- generating it N times would re-unlock the user cert's private key N times, wasteful + keeps the password in memory longer. HostName now reflects the endpoint that actually connected via _connectedEndpointUrl instead of always returning opts.EndpointUrl -- so the Admin /hosts dashboard shows which of the configured endpoints is currently serving traffic (primary vs backup). Falls back to the first candidate pre-connect so the dashboard has a sensible identity before the first connect, and resets to null on ShutdownAsync. Use case: an OPC UA hot-standby server pair (primary 4840 + backup 4841) where either can serve the same address space. Operator configures EndpointUrls=[primary, backup]; driver tries primary first, falls over to backup on primary failure with a clean AggregateException describing both attempts if both are down. Unit tests (OpcUaClientFailoverTests, 5 facts): ResolveEndpointCandidates_prefers_EndpointUrls_when_provided (list trumps single), ResolveEndpointCandidates_falls_back_to_single_EndpointUrl_when_list_empty (legacy config compat), ResolveEndpointCandidates_empty_list_treated_as_fallback (explicit empty list also falls back -- otherwise we'd produce a zero-candidate sweep that throws with nothing tried), HostName_uses_first_candidate_before_connect (dashboard rendering pre-connect), Initialize_against_all_unreachable_endpoints_throws_AggregateException_listing_each (three loopback dead ports, asserts each URL appears in the aggregate message + driver flips to Faulted). 31/31 OpcUaClient.Tests pass. dotnet build clean. OPC UA Client driver security/auth/availability feature set now complete per driver-specs.md \u00A78: policy-filtered endpoint selection (PR 70), Anonymous+Username+Certificate auth (PR 71), multi-endpoint failover (this PR).

2026-04-19 01:52:31 -04:00
parent 3f7b4d05e6
commit 24435712c4
3 changed files with 212 additions and 44 deletions
--- a/tests/ZB.MOM.WW.OtOpcUa.Driver.OpcUaClient.Tests/OpcUaClientFailoverTests.cs
+++ b/tests/ZB.MOM.WW.OtOpcUa.Driver.OpcUaClient.Tests/OpcUaClientFailoverTests.cs
@@ -0,0 +1,81 @@
+using Shouldly;
+using Xunit;
+using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
+
+namespace ZB.MOM.WW.OtOpcUa.Driver.OpcUaClient.Tests;
+
+[Trait("Category", "Unit")]
+public sealed class OpcUaClientFailoverTests
+{
+    [Fact]
+    public void ResolveEndpointCandidates_prefers_EndpointUrls_when_provided()
+    {
+        var opts = new OpcUaClientDriverOptions
+        {
+            EndpointUrl = "opc.tcp://fallback:4840",
+            EndpointUrls = ["opc.tcp://primary:4840", "opc.tcp://backup:4841"],
+        };
+        var list = OpcUaClientDriver.ResolveEndpointCandidates(opts);
+        list.Count.ShouldBe(2);
+        list[0].ShouldBe("opc.tcp://primary:4840");
+        list[1].ShouldBe("opc.tcp://backup:4841");
+    }
+
+    [Fact]
+    public void ResolveEndpointCandidates_falls_back_to_single_EndpointUrl_when_list_empty()
+    {
+        var opts = new OpcUaClientDriverOptions { EndpointUrl = "opc.tcp://only:4840" };
+        var list = OpcUaClientDriver.ResolveEndpointCandidates(opts);
+        list.Count.ShouldBe(1);
+        list[0].ShouldBe("opc.tcp://only:4840");
+    }
+
+    [Fact]
+    public void ResolveEndpointCandidates_empty_list_treated_as_fallback_to_EndpointUrl()
+    {
+        // Explicit empty list should still fall back to the single-URL shortcut rather than
+        // producing a zero-candidate sweep that would immediately throw with no URLs tried.
+        var opts = new OpcUaClientDriverOptions
+        {
+            EndpointUrl = "opc.tcp://single:4840",
+            EndpointUrls = [],
+        };
+        OpcUaClientDriver.ResolveEndpointCandidates(opts).Count.ShouldBe(1);
+    }
+
+    [Fact]
+    public void HostName_uses_first_candidate_before_connect()
+    {
+        var opts = new OpcUaClientDriverOptions
+        {
+            EndpointUrls = ["opc.tcp://primary:4840", "opc.tcp://backup:4841"],
+        };
+        using var drv = new OpcUaClientDriver(opts, "opcua-host");
+        drv.HostName.ShouldBe("opc.tcp://primary:4840",
+            "pre-connect the dashboard should show the first candidate URL so operators can link back");
+    }
+
+    [Fact]
+    public async Task Initialize_against_all_unreachable_endpoints_throws_AggregateException_listing_each()
+    {
+        // Port 1 + port 2 + port 3 on loopback are all guaranteed closed (TCP RST immediate).
+        // Failover sweep should attempt all three and throw AggregateException naming each URL
+        // so operators see exactly which candidates were tried.
+        var opts = new OpcUaClientDriverOptions
+        {
+            EndpointUrls = ["opc.tcp://127.0.0.1:1", "opc.tcp://127.0.0.1:2", "opc.tcp://127.0.0.1:3"],
+            PerEndpointConnectTimeout = TimeSpan.FromMilliseconds(500),
+            Timeout = TimeSpan.FromMilliseconds(500),
+            AutoAcceptCertificates = true,
+        };
+        using var drv = new OpcUaClientDriver(opts, "opcua-failover");
+
+        var ex = await Should.ThrowAsync<AggregateException>(async () =>
+            await drv.InitializeAsync("{}", TestContext.Current.CancellationToken));
+
+        ex.Message.ShouldContain("127.0.0.1:1");
+        ex.Message.ShouldContain("127.0.0.1:2");
+        ex.Message.ShouldContain("127.0.0.1:3");
+        drv.GetHealth().State.ShouldBe(DriverState.Faulted);
+    }
+}