dohertj2/ScadaBridge
1
0
Fork 0
Code Issues 1 Pull Requests 1 Actions Packages Projects Releases Wiki Activity

test(failover): unskip FailoverTimingTests on the two-node rig at production timings — measured 33.7s vs ~25s design envelope (plan R2-01 T4; covers report-08 NF2)

Browse Source
This commit is contained in:
Joseph Doherty
2026-07-13 10:38:19 -04:00
parent 30356803e7
commit 65e0f770d1
3 changed files with 73 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/ZB.MOM.WW.ScadaBridge.IntegrationTests/Cluster/TwoNodeClusterFixture.cs
+12 -6
View File
@@ -13,6 +13,10 @@ namespace ZB.MOM.WW.ScadaBridge.IntegrationTests.Cluster;
/// singleton host). CrashNode() terminates a node WITHOUT cluster-leave
/// (coordinated-shutdown by-terminate disabled on both nodes) to simulate
/// a hard crash — the scenario review 01 found untested.
///
/// Timing knobs default to scaled test values; pass production values
/// (2s heartbeat / 10s failure-detection / 15s stable-after) to measure the
/// real failover envelope (FailoverTimingTests).
/// </summary>
public sealed class TwoNodeClusterFixture : IAsyncDisposable
{
@@ -23,21 +27,23 @@ public sealed class TwoNodeClusterFixture : IAsyncDisposable
public static async Task<TwoNodeClusterFixture> StartAsync(
string role = "Central", TimeSpan? stableAfter = null,
int? portA = null, int? portB = null)
int? portA = null, int? portB = null,
TimeSpan? heartbeatInterval = null, TimeSpan? failureDetectionThreshold = null)
{
var f = new TwoNodeClusterFixture();
f.PortA = portA ?? GetFreeTcpPort();
f.PortB = portB ?? GetFreeTcpPort();
f.NodeA = f.StartNode(f.PortA, role, stableAfter);
f.NodeA = f.StartNode(f.PortA, role, stableAfter, heartbeatInterval, failureDetectionThreshold);
await WaitForMembersUp(f.NodeA, 1, TimeSpan.FromSeconds(20));
f.NodeB = f.StartNode(f.PortB, role, stableAfter);
f.NodeB = f.StartNode(f.PortB, role, stableAfter, heartbeatInterval, failureDetectionThreshold);
await WaitForMembersUp(f.NodeA, 2, TimeSpan.FromSeconds(20));
await WaitForMembersUp(f.NodeB, 2, TimeSpan.FromSeconds(20));
return f;
}
/// <summary>Starts a node from production HOCON; used by StartAsync and by restart-scenarios.</summary>
public ActorSystem StartNode(int port, string role, TimeSpan? stableAfter = null)
public ActorSystem StartNode(int port, string role, TimeSpan? stableAfter = null,
TimeSpan? heartbeatInterval = null, TimeSpan? failureDetectionThreshold = null)
{
var nodeOptions = new NodeOptions { Role = role, NodeHostname = "127.0.0.1", RemotingPort = port };
var clusterOptions = new ClusterOptions
@@ -49,8 +55,8 @@ public sealed class TwoNodeClusterFixture : IAsyncDisposable
},
SplitBrainResolverStrategy = "keep-oldest",
StableAfter = stableAfter ?? TimeSpan.FromSeconds(3),
HeartbeatInterval = TimeSpan.FromMilliseconds(500),
FailureDetectionThreshold = TimeSpan.FromSeconds(2),
HeartbeatInterval = heartbeatInterval ?? TimeSpan.FromMilliseconds(500),
FailureDetectionThreshold = failureDetectionThreshold ?? TimeSpan.FromSeconds(2),
MinNrOfMembers = 1,
DownIfAlone = true,
};