dc9c0c950c
Apply the ZB.MOM.WW. prefix to all gateway-side projects, folders,
.csproj/.sln contents, C# namespaces, using directives, generated proto
C# (csharp_namespace + checked-in generated files), InternalsVisibleTo
attributes, project-name string literals (LoadProject, .sln lookups,
worker exe paths, staticwebassets manifest), and the install/script/doc
references that point at any of the above. Migrate the solution from
.sln to .slnx via `dotnet sln migrate` and delete the old file.
External-runtime identifiers are intentionally NOT prefixed so external
configuration keeps working:
- GatewayMetrics.cs MeterName ("MxGateway.Server")
- DashboardAuthenticationDefaults Scheme/Policy ("MxGateway.Dashboard")
- GatewayRequestLoggingMiddleware logger category ("MxGateway.Request")
- StaRuntime thread name ("MxGateway.Worker.STA")
- appsettings.json root section "MxGateway" + env-var prefix
MxGateway__... and secret-name MxGateway:ApiKeyPepper
- C:\ProgramData\MxGateway\ data dir paths
Also fixes two tests that were not rename-related but became visible
while validating the rename:
- WorkerLiveMxAccessSmokeTests.ShutDownAsync: cancellation that the
gateway service correctly maps to RpcException(Cancelled) per gRPC
convention was being misclassified as a stream fault. Added a sibling
catch on RpcException with StatusCode.Cancelled.
- IntegrationTestEnvironment.ResolveRepositoryRoot: extracted IsRepositoryRoot
and made it accept either a .git marker OR a .sln/.slnx next to src/
so the worker-exe walker works in non-git working copies.
clients/proto/proto-inputs.json's protoRoot updated to point at
src/ZB.MOM.WW.MxGateway.Contracts/Protos.
Verified by `dotnet build` and a full `dotnet test` of the .slnx with
MXGATEWAY_RUN_LIVE_{MXACCESS,LDAP,GALAXY}_TESTS=1:
Tests: 472/472 pass
Worker.Tests: 280/280 pass (4 dev-rig [Fact(Skip=...)] skipped)
IntegrationTests: 18/18 pass
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
89 lines
4.0 KiB
C#
89 lines
4.0 KiB
C#
using System;
|
||
|
||
namespace ZB.MOM.WW.MxGateway.Worker.Ipc;
|
||
|
||
/// <summary>Configuration options for worker pipe sessions including heartbeat parameters.</summary>
|
||
public sealed class WorkerPipeSessionOptions
|
||
{
|
||
/// <summary>Default heartbeat interval (5 seconds).</summary>
|
||
public static readonly TimeSpan DefaultHeartbeatInterval = TimeSpan.FromSeconds(5);
|
||
/// <summary>Default heartbeat grace period (15 seconds).</summary>
|
||
public static readonly TimeSpan DefaultHeartbeatGrace = TimeSpan.FromSeconds(15);
|
||
/// <summary>
|
||
/// Default defensive ceiling beyond which the watchdog fires
|
||
/// <see cref="ZB.MOM.WW.MxGateway.Contracts.Proto.WorkerFaultCategory.StaHung"/>
|
||
/// even while a command is in flight (75 seconds = 5 ×
|
||
/// <see cref="DefaultHeartbeatGrace"/>). See <see cref="HeartbeatStuckCeiling"/>
|
||
/// for the rationale.
|
||
/// </summary>
|
||
public static readonly TimeSpan DefaultHeartbeatStuckCeiling = TimeSpan.FromSeconds(75);
|
||
|
||
/// <summary>Initializes a new instance of the WorkerPipeSessionOptions class with default values.</summary>
|
||
public WorkerPipeSessionOptions()
|
||
{
|
||
HeartbeatInterval = DefaultHeartbeatInterval;
|
||
HeartbeatGrace = DefaultHeartbeatGrace;
|
||
HeartbeatStuckCeiling = DefaultHeartbeatStuckCeiling;
|
||
}
|
||
|
||
/// <summary>Gets or sets the heartbeat interval.</summary>
|
||
public TimeSpan HeartbeatInterval { get; set; }
|
||
|
||
/// <summary>Gets or sets the heartbeat grace period.</summary>
|
||
public TimeSpan HeartbeatGrace { get; set; }
|
||
|
||
/// <summary>
|
||
/// Gets or sets the defensive upper bound on how long the watchdog
|
||
/// will suppress its <c>StaHung</c> fault while a command is in
|
||
/// flight. Worker-017 suppresses the watchdog when the heartbeat
|
||
/// snapshot's <c>CurrentCommandCorrelationId</c> is non-empty so a
|
||
/// legitimately slow command (e.g. <c>ReadBulk</c> against many
|
||
/// uncached tags) does not self-fault — but a truly stuck
|
||
/// synchronous COM call against a dead MXAccess provider leaves
|
||
/// <c>CurrentCommandCorrelationId</c> non-empty forever and would
|
||
/// permanently defeat the watchdog. <c>HeartbeatStuckCeiling</c> is
|
||
/// the upper bound on that suppression: once
|
||
/// <c>LastStaActivityUtc</c> has been stale for longer than this
|
||
/// ceiling, the watchdog DOES fire <c>StaHung</c> even with a
|
||
/// command in flight, on the assumption that no legitimate STA
|
||
/// command should run that long without periodically refreshing
|
||
/// activity. Default is <see cref="DefaultHeartbeatStuckCeiling"/>
|
||
/// (75 seconds = 5 × <see cref="DefaultHeartbeatGrace"/>); raise
|
||
/// for deployments that run very long bulk operations.
|
||
/// </summary>
|
||
public TimeSpan HeartbeatStuckCeiling { get; set; }
|
||
|
||
/// <summary>Validates the session options.</summary>
|
||
public void Validate()
|
||
{
|
||
if (HeartbeatInterval <= TimeSpan.Zero)
|
||
{
|
||
throw new ArgumentOutOfRangeException(
|
||
nameof(HeartbeatInterval),
|
||
"Worker heartbeat interval must be greater than zero.");
|
||
}
|
||
|
||
if (HeartbeatGrace <= TimeSpan.Zero)
|
||
{
|
||
throw new ArgumentOutOfRangeException(
|
||
nameof(HeartbeatGrace),
|
||
"Worker heartbeat grace must be greater than zero.");
|
||
}
|
||
|
||
if (HeartbeatStuckCeiling <= TimeSpan.Zero)
|
||
{
|
||
throw new ArgumentOutOfRangeException(
|
||
nameof(HeartbeatStuckCeiling),
|
||
"Worker heartbeat stuck ceiling must be greater than zero.");
|
||
}
|
||
|
||
if (HeartbeatStuckCeiling <= HeartbeatGrace)
|
||
{
|
||
throw new ArgumentOutOfRangeException(
|
||
nameof(HeartbeatStuckCeiling),
|
||
"Worker heartbeat stuck ceiling must be greater than HeartbeatGrace; "
|
||
+ "otherwise it would fire before the in-flight-command suppression had any effect.");
|
||
}
|
||
}
|
||
}
|