feat(historian-sidecar): live aahClientManaged alarm-event write path (C.1)

SdkAlarmHistorianWriteBackend.WriteBatchAsync replaces the RetryPlease
placeholder with the real entry point — HistorianAccess.AddStreamedValue
(HistorianEvent, out HistorianAccessError) in aahClientManaged, pinned by
decompiling the installed SDK.

The write path opens its own ReadOnly=false connection: the query-side
HistorianDataSource opens ReadOnly sessions and AddStreamedValue fails on
those with WriteToReadOnlyFile. IHistorianConnectionFactory gains a readOnly
parameter (default true, query path unchanged); BuildConnectionArgs is
extracted as a pure helper. HistorianClusterEndpointPicker is shared for
node failover; connection-class errors abort the batch as RetryPlease and
reset the connection, malformed-input codes map to PermanentFail.

Tests: connection-unavailable batch deferral, ClassifyOutcome error-code
table, BuildConnectionArgs read-vs-write shaping (80 pass, 2 rig-skipped).
Live_* round-trip tests stay Skip-gated for the D.1 rollout smoke.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Joseph Doherty
2026-05-18 16:08:32 -04:00
parent 419eda256b
commit cd2306db66
6 changed files with 544 additions and 142 deletions

View File

@@ -3,6 +3,7 @@ using System.Collections.Generic;
using System.Linq;
using System.Threading;
using System.Threading.Tasks;
using ArchestrA;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend;
@@ -11,42 +12,42 @@ using ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Ipc;
namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Host.Tests
{
/// <summary>
/// PR C.1 — pins the <see cref="SdkAlarmHistorianWriteBackend"/> contract:
/// PR C.1 — covers <see cref="SdkAlarmHistorianWriteBackend"/>, the aahClientManaged-bound
/// alarm-event writer. The SDK-touching batch loop itself is exercised by the rig-gated
/// <c>Live_*</c> tests (D.1); the unit tests below pin the parts that are SDK-type-free:
/// <list type="bullet">
/// <item><description>
/// Unit: the placeholder backend returns <see cref="AlarmHistorianWriteOutcome.RetryPlease"/>
/// for every slot so the lmxopcua-side store-and-forward sink retains events rather than
/// dropping them while D.1 is unresolved.
/// </description></item>
/// <item><description>
/// Integration (rig-gated): once D.1 pins the live SDK entry point the Skip attribute is
/// removed. The live test writes a synthetic batch to a real AVEVA Historian and asserts
/// the cluster picker rotates from a broken primary to a healthy secondary.
/// </description></item>
/// <item><description>connection-unavailable → whole batch deferred as RetryPlease;</description></item>
/// <item><description><see cref="SdkAlarmHistorianWriteBackend.ClassifyOutcome"/> error-code mapping;</description></item>
/// <item><description><see cref="SdkHistorianConnectionFactory.BuildConnectionArgs"/> read-only-vs-write shaping.</description></item>
/// </list>
/// </summary>
[Trait("Category", "Unit")]
public sealed class SdkAlarmHistorianWriteBackendTests
{
// ── Placeholder-mode tests (no rig required) ─────────────────────────
// ── Connection-unavailable path (deterministic, no SDK load) ──────────
[Fact]
public async Task Placeholder_returns_RetryPlease_for_every_slot_so_queue_is_preserved()
public async Task Empty_batch_returns_empty_array()
{
// The SDK call-site in SdkAlarmHistorianWriteBackend is not yet pinned (PR D.1).
// Until D.1 swaps in the live call, the backend must return RetryPlease for every
// event so the lmxopcua-side SqliteStoreAndForwardSink retains the rows instead of
// dropping them — same effect as the NullAlarmHistorianSink fallback, but each
// slot is individually addressable for the drain worker.
var cfg = new HistorianConfiguration { ServerName = "placeholder-test", Enabled = true };
var backend = new SdkAlarmHistorianWriteBackend(cfg);
var backend = new SdkAlarmHistorianWriteBackend(
Config("any"), new ThrowingConnectionFactory());
var events = new[]
{
AlarmEvent("E1"),
AlarmEvent("E2"),
AlarmEvent("E3"),
};
var outcomes = await backend.WriteBatchAsync(
Array.Empty<AlarmHistorianEventDto>(), CancellationToken.None);
outcomes.ShouldBeEmpty();
}
[Fact]
public async Task Unreachable_node_defers_whole_batch_as_RetryPlease()
{
// No node can be connected — the backend must defer every event so the
// lmxopcua-side SQLite store-and-forward sink retains the rows rather than
// dropping them.
var backend = new SdkAlarmHistorianWriteBackend(
Config("unreachable"), new ThrowingConnectionFactory());
var events = new[] { AlarmEvent("E1"), AlarmEvent("E2"), AlarmEvent("E3") };
var outcomes = await backend.WriteBatchAsync(events, CancellationToken.None);
outcomes.Length.ShouldBe(events.Length);
@@ -54,23 +55,12 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Host.Tests
}
[Fact]
public async Task Placeholder_returns_empty_array_for_empty_batch()
public async Task Unreachable_node_large_batch_returns_one_outcome_per_event()
{
var cfg = new HistorianConfiguration { ServerName = "placeholder-test", Enabled = true };
var backend = new SdkAlarmHistorianWriteBackend(cfg);
var outcomes = await backend.WriteBatchAsync(Array.Empty<AlarmHistorianEventDto>(), CancellationToken.None);
outcomes.ShouldBeEmpty();
}
[Fact]
public async Task Placeholder_returns_same_count_as_input_for_large_batch()
{
// Guards against an off-by-one error in the placeholder array allocation —
// WriteBatchAsync must always return exactly as many outcomes as input events.
var cfg = new HistorianConfiguration { ServerName = "placeholder-test", Enabled = true };
var backend = new SdkAlarmHistorianWriteBackend(cfg);
// Guards the outcome-array allocation: WriteBatchAsync must always return exactly
// as many outcomes as input events, even on the whole-batch-deferred path.
var backend = new SdkAlarmHistorianWriteBackend(
Config("unreachable"), new ThrowingConnectionFactory());
var batch = Enumerable.Range(0, 1000).Select(i => AlarmEvent($"E{i}")).ToArray();
var outcomes = await backend.WriteBatchAsync(batch, CancellationToken.None);
@@ -79,22 +69,91 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Host.Tests
outcomes.ShouldAllBe(o => o == AlarmHistorianWriteOutcome.RetryPlease);
}
[Fact]
public async Task Connect_failure_marks_node_failed_in_picker()
{
// Every connect attempt throws → the picker should record the failure so the
// node enters cooldown (cluster-failover plumbing).
var cfg = Config("node-a");
var picker = new HistorianClusterEndpointPicker(cfg);
var backend = new SdkAlarmHistorianWriteBackend(cfg, new ThrowingConnectionFactory(), picker);
await backend.WriteBatchAsync(new[] { AlarmEvent("E1") }, CancellationToken.None);
picker.HealthyNodeCount.ShouldBe(0, "the only node failed to connect and is now in cooldown");
}
// ── ClassifyOutcome — error-code → outcome mapping ────────────────────
[Theory]
[InlineData(HistorianAccessError.ErrorValue.Success, AlarmHistorianWriteOutcome.Ack)]
[InlineData(HistorianAccessError.ErrorValue.FailedToConnect, AlarmHistorianWriteOutcome.RetryPlease)]
[InlineData(HistorianAccessError.ErrorValue.FailedToCreateSession, AlarmHistorianWriteOutcome.RetryPlease)]
[InlineData(HistorianAccessError.ErrorValue.NoReply, AlarmHistorianWriteOutcome.RetryPlease)]
[InlineData(HistorianAccessError.ErrorValue.NotReady, AlarmHistorianWriteOutcome.RetryPlease)]
[InlineData(HistorianAccessError.ErrorValue.Failure, AlarmHistorianWriteOutcome.RetryPlease)]
[InlineData(HistorianAccessError.ErrorValue.NoData, AlarmHistorianWriteOutcome.RetryPlease)]
[InlineData(HistorianAccessError.ErrorValue.InvalidArgument, AlarmHistorianWriteOutcome.PermanentFail)]
[InlineData(HistorianAccessError.ErrorValue.ValidationFailed, AlarmHistorianWriteOutcome.PermanentFail)]
[InlineData(HistorianAccessError.ErrorValue.NullPointerArgument, AlarmHistorianWriteOutcome.PermanentFail)]
[InlineData(HistorianAccessError.ErrorValue.WriteToReadOnlyFile, AlarmHistorianWriteOutcome.PermanentFail)]
[InlineData(HistorianAccessError.ErrorValue.NotImplemented, AlarmHistorianWriteOutcome.PermanentFail)]
public void ClassifyOutcome_maps_error_code_to_expected_outcome(
HistorianAccessError.ErrorValue code, AlarmHistorianWriteOutcome expected)
{
SdkAlarmHistorianWriteBackend.ClassifyOutcome(code).ShouldBe(expected);
}
// ── BuildConnectionArgs — read-only vs write shaping ──────────────────
[Fact]
public void BuildConnectionArgs_write_connection_is_not_read_only()
{
// The alarm-event write path must open ReadOnly=false; AddStreamedValue on a
// read-only session fails with WriteToReadOnlyFile.
var args = SdkHistorianConnectionFactory.BuildConnectionArgs(
Config("h1"), HistorianConnectionType.Event, readOnly: false);
args.ReadOnly.ShouldBeFalse();
args.ConnectionType.ShouldBe(HistorianConnectionType.Event);
args.ServerName.ShouldBe("h1");
}
[Fact]
public void BuildConnectionArgs_query_connection_is_read_only()
{
var args = SdkHistorianConnectionFactory.BuildConnectionArgs(
Config("h1"), HistorianConnectionType.Process, readOnly: true);
args.ReadOnly.ShouldBeTrue();
args.ConnectionType.ShouldBe(HistorianConnectionType.Process);
}
[Fact]
public void BuildConnectionArgs_non_integrated_security_carries_credentials()
{
var cfg = Config("h1");
cfg.IntegratedSecurity = false;
cfg.UserName = "histuser";
cfg.Password = "histpass";
var args = SdkHistorianConnectionFactory.BuildConnectionArgs(
cfg, HistorianConnectionType.Event, readOnly: false);
args.IntegratedSecurity.ShouldBeFalse();
args.UserName.ShouldBe("histuser");
args.Password.ShouldBe("histpass");
}
// ── Rig-gated integration tests ───────────────────────────────────────
//
// The tests below need a live AVEVA Historian install and are gated with
// Skip="rig-required". Once PR D.1 pins the SDK entry point, remove the
// Skip attribute and add them to the integration test run profile.
// The entry point (HistorianAccess.AddStreamedValue) is pinned and implemented;
// these need a live AVEVA Historian and are un-skipped during the PR D.1 smoke.
[Fact(Skip = "rig-required: needs a live AVEVA Historian + aahClientManaged SDK — enable in PR D.1")]
[Fact(Skip = "rig-required: needs a live AVEVA Historian — un-skip during the PR D.1 rollout smoke")]
public async Task Live_single_event_roundtrip_returns_Ack()
{
// Spec (PR C.1, Tests): "1 / 100 / 1000 events through a fake aahClientManaged
// writer; assert per-row outcome list parallel to input order."
//
// This slice exercises the *live* SDK path. The fake-backend variant at
// AahClientManagedAlarmEventWriterTests covers the same assertion without the rig.
var cfg = BuildRigConfig();
var backend = new SdkAlarmHistorianWriteBackend(cfg);
var backend = new SdkAlarmHistorianWriteBackend(BuildRigConfig());
var outcomes = await backend.WriteBatchAsync(new[] { AlarmEvent("rig-E1") }, CancellationToken.None);
@@ -102,19 +161,13 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Host.Tests
outcomes[0].ShouldBe(AlarmHistorianWriteOutcome.Ack);
}
[Fact(Skip = "rig-required: needs a live AVEVA Historian cluster (two nodes) — enable in PR D.1")]
[Fact(Skip = "rig-required: needs a live AVEVA Historian cluster (two nodes) — un-skip during the PR D.1 rollout smoke")]
public async Task Live_cluster_failover_primary_bad_rotates_to_secondary()
{
// Spec (PR C.1, Tests): "Cluster failover: primary node returns
// BadCommunicationError; picker rotates to secondary; assert eventual success."
//
// Configure the first server name to point at a deliberately unreachable node
// and the second to the real Historian; the picker should mark the first node
// failed and succeed via the second.
var cfg = new HistorianConfiguration
{
Enabled = true,
ServerNames = new System.Collections.Generic.List<string>
ServerNames = new List<string>
{
"invalid-primary-node-deliberately-unreachable",
Environment.GetEnvironmentVariable("OTOPCUA_HISTORIAN_SERVER") ?? "localhost",
@@ -128,18 +181,29 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Host.Tests
var outcomes = await backend.WriteBatchAsync(new[] { AlarmEvent("rig-failover-E1") }, CancellationToken.None);
// The backend must succeed (Ack) via the secondary even though the primary was bad.
outcomes.Length.ShouldBe(1);
outcomes[0].ShouldBe(AlarmHistorianWriteOutcome.Ack);
}
// ── helpers ───────────────────────────────────────────────────────────
private static HistorianConfiguration Config(string server) => new HistorianConfiguration
{
Enabled = true,
ServerName = server,
Port = 32568,
IntegratedSecurity = true,
CommandTimeoutSeconds = 30,
FailureCooldownSeconds = 60,
};
private static AlarmHistorianEventDto AlarmEvent(string id) => new AlarmHistorianEventDto
{
EventId = id,
SourceName = "TestSource",
ConditionId = "TestSource.Level.HiHi",
AlarmType = "AnalogLimitAlarm.HiHi",
Message = "C.1 integration test alarm",
Message = "C.1 test alarm",
Severity = 500,
EventTimeUtcTicks = DateTime.UtcNow.Ticks,
AckComment = null,
@@ -160,5 +224,16 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Host.Tests
var raw = Environment.GetEnvironmentVariable(envName);
return int.TryParse(raw, out var parsed) ? parsed : defaultValue;
}
/// <summary>
/// Fake factory whose every connect attempt throws — drives the
/// connection-unavailable path without loading the native SDK.
/// </summary>
private sealed class ThrowingConnectionFactory : IHistorianConnectionFactory
{
public HistorianAccess CreateAndConnect(
HistorianConfiguration config, HistorianConnectionType type, bool readOnly = true)
=> throw new InvalidOperationException($"simulated connect failure to {config.ServerName}");
}
}
}

View File

@@ -24,4 +24,14 @@
<ProjectReference Include="..\..\..\src\Drivers\ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware\ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.csproj"/>
</ItemGroup>
<ItemGroup>
<!-- Wonderware Historian SDK — SdkAlarmHistorianWriteBackendTests pins the
error-code (HistorianAccessError.ErrorValue) and connection-arg shaping;
a DLL <Reference> doesn't flow transitively through the ProjectReference. -->
<Reference Include="aahClientManaged">
<HintPath>..\..\..\lib\aahClientManaged.dll</HintPath>
<EmbedInteropTypes>false</EmbedInteropTypes>
</Reference>
</ItemGroup>
</Project>