fix(audit-log): reconciliation pulls fail over to site NodeB when NodeA is unreachable
SiteEntry gains an additive FallbackGrpcEndpoint; SiteEnumerator now picks NodeA
else NodeB as primary (a NodeB-only site is no longer skipped) and carries a
distinct NodeB as the fallback. Both GrpcPull{AuditEvents,SiteCalls} clients dial
the primary first and, on a transport fault (Unavailable/DeadlineExceeded/
Cancelled/HttpRequestException/SocketException/OperationCanceled), fail over to
NodeB once before collapsing to empty — a mapping/unexpected fault does NOT fail
over. Keeps the reconciliation loss-recovery net available during a NodeA outage.
This commit is contained in:
@@ -71,6 +71,26 @@ public class GrpcPullAuditEventsClientTests
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Per-endpoint fake invoker (Task 18): routes dials by endpoint string so a
|
||||
/// NodeA-down / NodeB-up failover can be scripted. Records dialed endpoints.
|
||||
/// </summary>
|
||||
private sealed class PerEndpointInvoker : GrpcPullAuditEventsClient.IPullAuditEventsInvoker
|
||||
{
|
||||
private readonly Dictionary<string, Func<ProtoPullResponse>> _byEndpoint;
|
||||
public List<string> Dialed { get; } = new();
|
||||
|
||||
public PerEndpointInvoker(Dictionary<string, Func<ProtoPullResponse>> byEndpoint) =>
|
||||
_byEndpoint = byEndpoint;
|
||||
|
||||
public Task<ProtoPullResponse> InvokeAsync(
|
||||
string endpoint, ProtoPullRequest request, CancellationToken ct)
|
||||
{
|
||||
Dialed.Add(endpoint);
|
||||
return Task.FromResult(_byEndpoint[endpoint]());
|
||||
}
|
||||
}
|
||||
|
||||
private static AuditEventDto Dto(Guid id, DateTime occurredAtUtc) =>
|
||||
AuditEventDtoMapper.ToDto(ScadaBridgeAuditEventFactory.Create(
|
||||
eventId: id,
|
||||
@@ -212,4 +232,48 @@ public class GrpcPullAuditEventsClientTests
|
||||
Assert.Empty(result.Events);
|
||||
Assert.False(result.MoreAvailable);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public async Task PullAsync_fails_over_to_NodeB_when_primary_raises_transport_fault()
|
||||
{
|
||||
// Task 18: NodeA (primary) is unreachable, NodeB (fallback) answers — the
|
||||
// pull must return NodeB's events rather than collapsing to empty.
|
||||
var id = Guid.NewGuid();
|
||||
var fallbackResponse = new ProtoPullResponse { MoreAvailable = false };
|
||||
fallbackResponse.Events.Add(Dto(id, BaseTime));
|
||||
|
||||
var invoker = new PerEndpointInvoker(new Dictionary<string, Func<ProtoPullResponse>>
|
||||
{
|
||||
["http://node-a:8083"] = () => throw new RpcException(new Status(StatusCode.Unavailable, "node A down")),
|
||||
["http://node-b:8083"] = () => fallbackResponse,
|
||||
});
|
||||
var sut = new GrpcPullAuditEventsClient(
|
||||
new StaticEnumerator(new SiteEntry("site-a", "http://node-a:8083", "http://node-b:8083")),
|
||||
invoker,
|
||||
NullLogger<GrpcPullAuditEventsClient>.Instance);
|
||||
|
||||
var result = await sut.PullAsync("site-a", BaseTime, batchSize: 256, CancellationToken.None);
|
||||
|
||||
Assert.Equal(new[] { "http://node-a:8083", "http://node-b:8083" }, invoker.Dialed);
|
||||
var evt = Assert.Single(result.Events);
|
||||
Assert.Equal(id, evt.EventId);
|
||||
}
|
||||
|
||||
[Fact]
|
||||
public async Task PullAsync_does_not_fail_over_when_no_fallback_configured()
|
||||
{
|
||||
var invoker = new PerEndpointInvoker(new Dictionary<string, Func<ProtoPullResponse>>
|
||||
{
|
||||
["http://node-a:8083"] = () => throw new RpcException(new Status(StatusCode.Unavailable, "node A down")),
|
||||
});
|
||||
var sut = new GrpcPullAuditEventsClient(
|
||||
new StaticEnumerator(new SiteEntry("site-a", "http://node-a:8083")), // no fallback
|
||||
invoker,
|
||||
NullLogger<GrpcPullAuditEventsClient>.Instance);
|
||||
|
||||
var result = await sut.PullAsync("site-a", BaseTime, batchSize: 256, CancellationToken.None);
|
||||
|
||||
Assert.Empty(result.Events);
|
||||
Assert.Equal(new[] { "http://node-a:8083" }, invoker.Dialed);
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user