feat(mesh-phase4): register ConfigDb only on admin-role nodes
Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW
This commit is contained in:
@@ -17,21 +17,37 @@ public static class HealthEndpoints
|
||||
{
|
||||
/// <summary>
|
||||
/// Registers the shared ZB.MOM.WW health probes. Tier semantics preserved: configdb + akka on
|
||||
/// ready+active; admin-leader on active only.
|
||||
/// ready+active; admin-leader on active only. The configdb probe is admin-only (per-cluster mesh
|
||||
/// Phase 4): a driver-only node holds no ConfigDb, so it is registered iff <paramref name="hasAdmin"/>.
|
||||
/// </summary>
|
||||
/// <param name="services">The service collection to register the health checks on.</param>
|
||||
/// <param name="hasAdmin">
|
||||
/// Whether this node carries the <c>admin</c> role. When <c>false</c> (a driver-only node) the
|
||||
/// <c>configdb</c> probe is skipped — the node registers no <see cref="OtOpcUaConfigDbContext"/>
|
||||
/// factory, so probing it would throw when the readiness endpoint resolves the factory. Defaults to
|
||||
/// <c>true</c> so admin/fused callers (including the test harnesses) keep the probe unchanged.
|
||||
/// </param>
|
||||
/// <returns>The same service collection, for chaining.</returns>
|
||||
public static IServiceCollection AddOtOpcUaHealth(this IServiceCollection services)
|
||||
public static IServiceCollection AddOtOpcUaHealth(this IServiceCollection services, bool hasAdmin = true)
|
||||
{
|
||||
services.AddHealthChecks()
|
||||
.AddTypeActivatedCheck<DatabaseHealthCheck<OtOpcUaConfigDbContext>>(
|
||||
var checks = services.AddHealthChecks();
|
||||
|
||||
// configdb probe is admin-only (per-cluster mesh Phase 4). A driver-only node gets its config
|
||||
// from central via ConfigSource:Mode=FetchAndCache and never registers the ConfigDb factory, so
|
||||
// the type-activated DatabaseHealthCheck would throw resolving it. Admin + fused nodes: unchanged.
|
||||
if (hasAdmin)
|
||||
{
|
||||
checks.AddTypeActivatedCheck<DatabaseHealthCheck<OtOpcUaConfigDbContext>>(
|
||||
"configdb",
|
||||
failureStatus: null,
|
||||
tags: new[] { ZbHealthTags.Ready, ZbHealthTags.Active },
|
||||
args: new DatabaseHealthCheckOptions<OtOpcUaConfigDbContext>
|
||||
{
|
||||
ProbeQuery = static (db, ct) => db.Deployments.AsNoTracking().Take(1).ToListAsync(ct),
|
||||
})
|
||||
});
|
||||
}
|
||||
|
||||
checks
|
||||
.AddTypeActivatedCheck<AkkaClusterHealthCheck>(
|
||||
"akka",
|
||||
failureStatus: null,
|
||||
@@ -42,11 +58,10 @@ public static class HealthEndpoints
|
||||
failureStatus: null,
|
||||
tags: new[] { ZbHealthTags.Active },
|
||||
args: "admin")
|
||||
// Registered unconditionally, not driver-gated. AddOtOpcUaHealth takes no role argument
|
||||
// and runs on every node; the check itself resolves ISyncStatus optionally and reports
|
||||
// Healthy when LocalDb is absent (admin-only graphs) or replication is default-OFF, so a
|
||||
// plain node is never degraded by it. A factory registration keeps this no-arg signature
|
||||
// while still reading ISyncStatus + options + the sync port from the container.
|
||||
// Registered on every node regardless of role (unlike the admin-only configdb probe above):
|
||||
// the check itself resolves ISyncStatus optionally and reports Healthy when LocalDb is absent
|
||||
// (admin-only graphs) or replication is default-OFF, so a plain node is never degraded by it.
|
||||
// A factory registration reads ISyncStatus + options + the sync port from the container.
|
||||
.Add(new HealthCheckRegistration(
|
||||
"localdb-replication",
|
||||
sp => new LocalDbReplicationHealthCheck(
|
||||
|
||||
@@ -122,8 +122,16 @@ builder.AddZbSerilog(o => o.ServiceName = "otopcua");
|
||||
// Windows-service registration is handled at install time by scripts/install/Install-Services.ps1
|
||||
// rather than in-process, so the binary stays cross-platform-compilable.
|
||||
|
||||
// Shared services — always registered regardless of role. ConfigDb is required for everything.
|
||||
builder.Services.AddOtOpcUaConfigDb(builder.Configuration);
|
||||
// ConfigDb is admin-only now (per-cluster mesh Phase 4). Only the admin role owns a ConfigDb
|
||||
// connection string; a driver-only node holds none at all and gets its deployed configuration from
|
||||
// central over the Phase-3 fetch-and-cache path (ConfigSource:Mode=FetchAndCache). Registering it
|
||||
// unconditionally would throw on a driver-only node, since AddOtOpcUaConfigDb requires the string.
|
||||
// A fused admin+driver node keeps ConfigDb via its admin role — byte-for-byte unaffected.
|
||||
if (hasAdmin)
|
||||
builder.Services.AddOtOpcUaConfigDb(builder.Configuration);
|
||||
else
|
||||
Log.Information("Driver-only node — no ConfigDb registered; configuration via ConfigSource:Mode=FetchAndCache");
|
||||
|
||||
builder.Services.AddOtOpcUaCluster(builder.Configuration);
|
||||
|
||||
// Validate LdapOptions unconditionally so ANY role node (admin-only, driver-only, or fused)
|
||||
@@ -392,7 +400,9 @@ if (hasAdmin)
|
||||
// Cluster replication is opt-in behind Secrets:Replication:Enabled (default false) — see SecretsRegistration.
|
||||
builder.Services.AddOtOpcUaSecrets(builder.Configuration);
|
||||
|
||||
builder.Services.AddOtOpcUaHealth();
|
||||
// hasAdmin gates the configdb probe: a driver-only node registers no ConfigDb factory (see above), so
|
||||
// probing it would throw when the readiness endpoint resolves the factory.
|
||||
builder.Services.AddOtOpcUaHealth(hasAdmin);
|
||||
builder.Services.AddOtOpcUaObservability(builder.Configuration);
|
||||
|
||||
// gRPC server plumbing shared by two endpoints: the LocalDb passive sync endpoint (driver-role,
|
||||
|
||||
Reference in New Issue
Block a user