rename: prefix gateway projects/namespaces with ZB.MOM.WW + sln→slnx
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>
This commit is contained in:
Joseph Doherty
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,63 @@
|
||||
using System.Diagnostics.CodeAnalysis;
|
||||
using ZB.MOM.WW.MxGateway.Contracts.Proto;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public interface ISessionManager
|
||||
{
|
||||
/// <summary>Opens a new gateway session and launches a worker process.</summary>
|
||||
/// <param name="request">Request payload.</param>
|
||||
/// <param name="clientIdentity">Client identity string.</param>
|
||||
/// <param name="cancellationToken">Token to cancel the asynchronous operation.</param>
|
||||
/// <returns>The newly opened session.</returns>
|
||||
Task<GatewaySession> OpenSessionAsync(
|
||||
SessionOpenRequest request,
|
||||
string? clientIdentity,
|
||||
CancellationToken cancellationToken);
|
||||
|
||||
/// <summary>Attempts to retrieve a session by ID.</summary>
|
||||
/// <param name="sessionId">Identifier of the session.</param>
|
||||
/// <param name="session">The retrieved session, if found.</param>
|
||||
/// <returns>True if the session exists; otherwise false.</returns>
|
||||
bool TryGetSession(
|
||||
string sessionId,
|
||||
[MaybeNullWhen(false)] out GatewaySession session);
|
||||
|
||||
/// <summary>Invokes a command on the worker for the specified session.</summary>
|
||||
/// <param name="sessionId">Identifier of the session.</param>
|
||||
/// <param name="command">Command to invoke.</param>
|
||||
/// <param name="cancellationToken">Token to cancel the asynchronous operation.</param>
|
||||
/// <returns>The command reply from the worker.</returns>
|
||||
Task<WorkerCommandReply> InvokeAsync(
|
||||
string sessionId,
|
||||
WorkerCommand command,
|
||||
CancellationToken cancellationToken);
|
||||
|
||||
/// <summary>Reads events streamed from the worker for the specified session.</summary>
|
||||
/// <param name="sessionId">Identifier of the session.</param>
|
||||
/// <param name="cancellationToken">Token to cancel the asynchronous operation.</param>
|
||||
/// <returns>Events emitted by the worker.</returns>
|
||||
IAsyncEnumerable<WorkerEvent> ReadEventsAsync(
|
||||
string sessionId,
|
||||
CancellationToken cancellationToken);
|
||||
|
||||
/// <summary>Closes a session and terminates its worker process.</summary>
|
||||
/// <param name="sessionId">Identifier of the session to close.</param>
|
||||
/// <param name="cancellationToken">Token to cancel the asynchronous operation.</param>
|
||||
/// <returns>The result of closing the session.</returns>
|
||||
Task<SessionCloseResult> CloseSessionAsync(
|
||||
string sessionId,
|
||||
CancellationToken cancellationToken);
|
||||
|
||||
/// <summary>Closes all sessions with expired leases at the specified time.</summary>
|
||||
/// <param name="now">The current time to evaluate expiration against.</param>
|
||||
/// <param name="cancellationToken">Token to cancel the asynchronous operation.</param>
|
||||
/// <returns>The number of sessions closed.</returns>
|
||||
Task<int> CloseExpiredLeasesAsync(
|
||||
DateTimeOffset now,
|
||||
CancellationToken cancellationToken);
|
||||
|
||||
/// <summary>Shuts down all sessions and the session manager.</summary>
|
||||
/// <param name="cancellationToken">Token to cancel the asynchronous operation.</param>
|
||||
Task ShutdownAsync(CancellationToken cancellationToken);
|
||||
}
|
||||
@@ -0,0 +1,48 @@
|
||||
using System.Diagnostics.CodeAnalysis;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
/// <summary>
|
||||
/// Registry for managing active gateway sessions.
|
||||
/// </summary>
|
||||
public interface ISessionRegistry
|
||||
{
|
||||
/// <summary>
|
||||
/// Total number of sessions (open or closed) in the registry.
|
||||
/// </summary>
|
||||
int Count { get; }
|
||||
|
||||
/// <summary>
|
||||
/// Number of sessions currently in an active (open) state.
|
||||
/// </summary>
|
||||
int ActiveCount { get; }
|
||||
|
||||
/// <summary>
|
||||
/// Attempts to add a session to the registry; returns false if session ID already exists.
|
||||
/// </summary>
|
||||
/// <param name="session">Session to add.</param>
|
||||
/// <returns>True if added; false if session ID already exists.</returns>
|
||||
bool TryAdd(GatewaySession session);
|
||||
|
||||
/// <summary>
|
||||
/// Attempts to retrieve a session by ID; returns false if not found.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Identifier of the session.</param>
|
||||
/// <param name="session">The retrieved session, if found.</param>
|
||||
/// <returns>True if found; false otherwise.</returns>
|
||||
bool TryGet(string sessionId, [MaybeNullWhen(false)] out GatewaySession session);
|
||||
|
||||
/// <summary>
|
||||
/// Attempts to remove a session by ID; returns false if not found.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Identifier of the session to remove.</param>
|
||||
/// <param name="session">The removed session, if found.</param>
|
||||
/// <returns>True if removed; false if not found.</returns>
|
||||
bool TryRemove(string sessionId, [MaybeNullWhen(false)] out GatewaySession session);
|
||||
|
||||
/// <summary>
|
||||
/// Returns a snapshot of all sessions in the registry.
|
||||
/// </summary>
|
||||
/// <returns>A read-only collection of all sessions.</returns>
|
||||
IReadOnlyCollection<GatewaySession> Snapshot();
|
||||
}
|
||||
@@ -0,0 +1,17 @@
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
/// <summary>
|
||||
/// Creates worker client instances for gateway sessions.
|
||||
/// </summary>
|
||||
public interface ISessionWorkerClientFactory
|
||||
{
|
||||
/// <summary>
|
||||
/// Creates a worker client for the specified session.
|
||||
/// </summary>
|
||||
/// <param name="session">Session to create a worker client for.</param>
|
||||
/// <param name="cancellationToken">Token to cancel the asynchronous operation.</param>
|
||||
/// <returns>A worker client connected to the worker process.</returns>
|
||||
Task<ZB.MOM.WW.MxGateway.Server.Workers.IWorkerClient> CreateAsync(
|
||||
GatewaySession session,
|
||||
CancellationToken cancellationToken);
|
||||
}
|
||||
@@ -0,0 +1,8 @@
|
||||
using ZB.MOM.WW.MxGateway.Contracts.Proto;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public sealed record SessionCloseResult(
|
||||
string SessionId,
|
||||
SessionState FinalState,
|
||||
bool AlreadyClosed);
|
||||
@@ -0,0 +1,14 @@
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
internal sealed class SessionCloseStartedException : Exception
|
||||
{
|
||||
/// <summary>Initializes a new instance of the <see cref="SessionCloseStartedException"/> class.</summary>
|
||||
/// <param name="message">The exception message.</param>
|
||||
/// <param name="innerException">The exception that caused this error.</param>
|
||||
public SessionCloseStartedException(
|
||||
string message,
|
||||
Exception innerException)
|
||||
: base(message, innerException)
|
||||
{
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,6 @@
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public sealed record SessionItemRegistration(
|
||||
int ServerHandle,
|
||||
int ItemHandle,
|
||||
string TagAddress);
|
||||
@@ -0,0 +1,45 @@
|
||||
using Microsoft.Extensions.Hosting;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using Microsoft.Extensions.Options;
|
||||
using ZB.MOM.WW.MxGateway.Server.Configuration;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public sealed class SessionLeaseMonitorHostedService(
|
||||
ISessionManager sessionManager,
|
||||
IOptions<GatewayOptions> options,
|
||||
ILogger<SessionLeaseMonitorHostedService> logger,
|
||||
TimeProvider? timeProvider = null) : BackgroundService
|
||||
{
|
||||
private readonly TimeProvider _timeProvider = timeProvider ?? TimeProvider.System;
|
||||
|
||||
protected override async Task ExecuteAsync(CancellationToken stoppingToken)
|
||||
{
|
||||
TimeSpan interval = TimeSpan.FromSeconds(Math.Max(1, options.Value.Sessions.LeaseSweepIntervalSeconds));
|
||||
using PeriodicTimer timer = new(interval, _timeProvider);
|
||||
|
||||
try
|
||||
{
|
||||
while (await timer.WaitForNextTickAsync(stoppingToken).ConfigureAwait(false))
|
||||
{
|
||||
try
|
||||
{
|
||||
await sessionManager
|
||||
.CloseExpiredLeasesAsync(_timeProvider.GetUtcNow(), stoppingToken)
|
||||
.ConfigureAwait(false);
|
||||
}
|
||||
catch (OperationCanceledException) when (stoppingToken.IsCancellationRequested)
|
||||
{
|
||||
return;
|
||||
}
|
||||
catch (Exception exception)
|
||||
{
|
||||
logger.LogWarning(exception, "Session lease sweep failed.");
|
||||
}
|
||||
}
|
||||
}
|
||||
catch (OperationCanceledException) when (stoppingToken.IsCancellationRequested)
|
||||
{
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,411 @@
|
||||
using System.Diagnostics.CodeAnalysis;
|
||||
using System.Security.Cryptography;
|
||||
using Google.Protobuf.WellKnownTypes;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using Microsoft.Extensions.Logging.Abstractions;
|
||||
using Microsoft.Extensions.Options;
|
||||
using ZB.MOM.WW.MxGateway.Contracts;
|
||||
using ZB.MOM.WW.MxGateway.Contracts.Proto;
|
||||
using ZB.MOM.WW.MxGateway.Server.Configuration;
|
||||
using ZB.MOM.WW.MxGateway.Server.Metrics;
|
||||
using ZB.MOM.WW.MxGateway.Server.Workers;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public sealed class SessionManager : ISessionManager
|
||||
{
|
||||
public const string DefaultCloseReason = "client-close";
|
||||
public const string GatewayShutdownReason = "gateway-shutdown";
|
||||
public const string LeaseExpiredReason = "lease-expired";
|
||||
|
||||
private readonly ISessionRegistry _registry;
|
||||
private readonly ISessionWorkerClientFactory _workerClientFactory;
|
||||
private readonly GatewayMetrics _metrics;
|
||||
private readonly TimeProvider _timeProvider;
|
||||
private readonly ILogger<SessionManager> _logger;
|
||||
private readonly GatewayOptions _options;
|
||||
private readonly SemaphoreSlim _sessionSlots;
|
||||
|
||||
/// <summary>
|
||||
/// Initializes a new instance of <see cref="SessionManager"/>.
|
||||
/// </summary>
|
||||
/// <param name="registry">Session registry.</param>
|
||||
/// <param name="workerClientFactory">Worker client factory.</param>
|
||||
/// <param name="options">Gateway options.</param>
|
||||
/// <param name="metrics">Gateway metrics.</param>
|
||||
/// <param name="timeProvider">Time provider for timestamps.</param>
|
||||
/// <param name="logger">Logger.</param>
|
||||
public SessionManager(
|
||||
ISessionRegistry registry,
|
||||
ISessionWorkerClientFactory workerClientFactory,
|
||||
IOptions<GatewayOptions> options,
|
||||
GatewayMetrics metrics,
|
||||
TimeProvider? timeProvider = null,
|
||||
ILogger<SessionManager>? logger = null)
|
||||
{
|
||||
_registry = registry ?? throw new ArgumentNullException(nameof(registry));
|
||||
_workerClientFactory = workerClientFactory ?? throw new ArgumentNullException(nameof(workerClientFactory));
|
||||
ArgumentNullException.ThrowIfNull(options);
|
||||
_metrics = metrics ?? throw new ArgumentNullException(nameof(metrics));
|
||||
_timeProvider = timeProvider ?? TimeProvider.System;
|
||||
_logger = logger ?? NullLogger<SessionManager>.Instance;
|
||||
_options = options.Value;
|
||||
_sessionSlots = new SemaphoreSlim(_options.Sessions.MaxSessions, _options.Sessions.MaxSessions);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Opens a new gateway session and connects to the worker.
|
||||
/// </summary>
|
||||
/// <param name="request">Session open request.</param>
|
||||
/// <param name="clientIdentity">Client authentication identity.</param>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
/// <returns>Opened gateway session.</returns>
|
||||
public async Task<GatewaySession> OpenSessionAsync(
|
||||
SessionOpenRequest request,
|
||||
string? clientIdentity,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
ArgumentNullException.ThrowIfNull(request);
|
||||
EnsureSessionCapacity();
|
||||
|
||||
GatewaySession? session = null;
|
||||
bool sessionOpenedRecorded = false;
|
||||
try
|
||||
{
|
||||
session = CreateSession(request, clientIdentity);
|
||||
if (!_registry.TryAdd(session))
|
||||
{
|
||||
throw new SessionManagerException(
|
||||
SessionManagerErrorCode.OpenFailed,
|
||||
$"Session id collision while opening session {session.SessionId}.");
|
||||
}
|
||||
|
||||
session.TransitionTo(SessionState.StartingWorker);
|
||||
IWorkerClient workerClient = await _workerClientFactory
|
||||
.CreateAsync(session, cancellationToken)
|
||||
.ConfigureAwait(false);
|
||||
|
||||
session.AttachWorkerClient(workerClient);
|
||||
session.MarkReady();
|
||||
_metrics.SessionOpened();
|
||||
sessionOpenedRecorded = true;
|
||||
|
||||
return session;
|
||||
}
|
||||
catch (Exception exception)
|
||||
{
|
||||
session?.MarkFaulted(exception.Message);
|
||||
if (session is not null)
|
||||
{
|
||||
_registry.TryRemove(session.SessionId, out _);
|
||||
await session.DisposeAsync().ConfigureAwait(false);
|
||||
}
|
||||
|
||||
// If SessionOpened() already incremented the open-session gauge,
|
||||
// a failure after that point (e.g. auto-subscribe rejection) must
|
||||
// decrement it again so mxgateway.sessions.open does not leak.
|
||||
if (sessionOpenedRecorded)
|
||||
{
|
||||
_metrics.SessionRemoved();
|
||||
}
|
||||
|
||||
ReleaseSessionSlot();
|
||||
_metrics.Fault(SessionManagerErrorCode.OpenFailed.ToString());
|
||||
_logger.LogWarning(
|
||||
exception,
|
||||
"Failed to open gateway session {SessionId}.",
|
||||
session?.SessionId ?? "<not-created>");
|
||||
|
||||
throw new SessionManagerException(
|
||||
SessionManagerErrorCode.OpenFailed,
|
||||
session is null ? "Failed to create session." : $"Failed to open session {session.SessionId}.",
|
||||
exception);
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Attempts to retrieve a session by ID.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Session identifier.</param>
|
||||
/// <param name="session">The session if found.</param>
|
||||
/// <returns>True if session found; otherwise false.</returns>
|
||||
public bool TryGetSession(
|
||||
string sessionId,
|
||||
[MaybeNullWhen(false)] out GatewaySession session)
|
||||
{
|
||||
return _registry.TryGet(sessionId, out session);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Invokes a worker command on a session asynchronously.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Session identifier.</param>
|
||||
/// <param name="command">Worker command.</param>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
/// <returns>Command reply.</returns>
|
||||
public async Task<WorkerCommandReply> InvokeAsync(
|
||||
string sessionId,
|
||||
WorkerCommand command,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
GatewaySession session = GetRequiredSession(sessionId);
|
||||
|
||||
try
|
||||
{
|
||||
return await session.InvokeAsync(command, cancellationToken).ConfigureAwait(false);
|
||||
}
|
||||
catch (SessionManagerException)
|
||||
{
|
||||
throw;
|
||||
}
|
||||
catch (Exception exception)
|
||||
{
|
||||
if (session.WorkerClient?.State == WorkerClientState.Faulted)
|
||||
{
|
||||
session.MarkFaulted(exception.Message);
|
||||
}
|
||||
|
||||
throw;
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Reads events from a session's event stream asynchronously.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Session identifier.</param>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
/// <returns>Async enumerable of worker events.</returns>
|
||||
public IAsyncEnumerable<WorkerEvent> ReadEventsAsync(
|
||||
string sessionId,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
GatewaySession session = GetRequiredSession(sessionId);
|
||||
|
||||
return session.ReadEventsAsync(cancellationToken);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Closes a gateway session asynchronously.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Session identifier.</param>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
/// <returns>Session close result.</returns>
|
||||
public async Task<SessionCloseResult> CloseSessionAsync(
|
||||
string sessionId,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
GatewaySession session = GetRequiredSession(sessionId);
|
||||
SessionCloseResult result = await CloseSessionCoreAsync(
|
||||
session,
|
||||
DefaultCloseReason,
|
||||
cancellationToken).ConfigureAwait(false);
|
||||
|
||||
return result;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Closes all sessions with expired leases asynchronously.
|
||||
/// </summary>
|
||||
/// <param name="now">Current time for lease expiration check.</param>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
/// <returns>Count of sessions closed.</returns>
|
||||
public async Task<int> CloseExpiredLeasesAsync(
|
||||
DateTimeOffset now,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
int closedCount = 0;
|
||||
foreach (GatewaySession session in _registry.Snapshot())
|
||||
{
|
||||
if (!session.IsLeaseExpired(now))
|
||||
{
|
||||
continue;
|
||||
}
|
||||
|
||||
await CloseSessionCoreAsync(session, LeaseExpiredReason, cancellationToken).ConfigureAwait(false);
|
||||
closedCount++;
|
||||
}
|
||||
|
||||
return closedCount;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Shuts down all active sessions gracefully asynchronously.
|
||||
/// </summary>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
/// <returns>Completed task.</returns>
|
||||
public async Task ShutdownAsync(CancellationToken cancellationToken)
|
||||
{
|
||||
foreach (GatewaySession session in _registry.Snapshot())
|
||||
{
|
||||
try
|
||||
{
|
||||
await CloseSessionCoreAsync(session, GatewayShutdownReason, cancellationToken).ConfigureAwait(false);
|
||||
}
|
||||
catch (Exception exception)
|
||||
{
|
||||
_logger.LogWarning(
|
||||
exception,
|
||||
"Graceful shutdown failed for session {SessionId}; killing worker.",
|
||||
session.SessionId);
|
||||
if (_registry.TryGet(session.SessionId, out _))
|
||||
{
|
||||
session.KillWorker(GatewayShutdownReason);
|
||||
await RemoveSessionAsync(session).ConfigureAwait(false);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
private async Task<SessionCloseResult> CloseSessionCoreAsync(
|
||||
GatewaySession session,
|
||||
string reason,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
bool wasClosed = session.State == SessionState.Closed;
|
||||
try
|
||||
{
|
||||
SessionCloseResult result = await session.CloseAsync(reason, cancellationToken).ConfigureAwait(false);
|
||||
if (!wasClosed && !result.AlreadyClosed)
|
||||
{
|
||||
_metrics.SessionClosed();
|
||||
}
|
||||
|
||||
await RemoveSessionAsync(session).ConfigureAwait(false);
|
||||
return result;
|
||||
}
|
||||
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
|
||||
{
|
||||
throw;
|
||||
}
|
||||
catch (SessionCloseStartedException exception)
|
||||
{
|
||||
session.MarkFaulted(exception.Message);
|
||||
if (!wasClosed)
|
||||
{
|
||||
_metrics.SessionRemoved();
|
||||
}
|
||||
|
||||
_metrics.Fault(SessionManagerErrorCode.CloseFailed.ToString());
|
||||
await RemoveSessionAsync(session).ConfigureAwait(false);
|
||||
throw new SessionManagerException(
|
||||
SessionManagerErrorCode.CloseFailed,
|
||||
$"Failed to close session {session.SessionId}.",
|
||||
exception);
|
||||
}
|
||||
}
|
||||
|
||||
private GatewaySession GetRequiredSession(string sessionId)
|
||||
{
|
||||
if (!_registry.TryGet(sessionId, out GatewaySession? session) || session is null)
|
||||
{
|
||||
throw new SessionManagerException(
|
||||
SessionManagerErrorCode.SessionNotFound,
|
||||
$"Session {sessionId} was not found.");
|
||||
}
|
||||
|
||||
return session;
|
||||
}
|
||||
|
||||
private void EnsureSessionCapacity()
|
||||
{
|
||||
if (!_sessionSlots.Wait(0))
|
||||
{
|
||||
throw new SessionManagerException(
|
||||
SessionManagerErrorCode.SessionLimitExceeded,
|
||||
$"Gateway session limit {_options.Sessions.MaxSessions} has been reached.");
|
||||
}
|
||||
}
|
||||
|
||||
private async Task RemoveSessionAsync(GatewaySession session)
|
||||
{
|
||||
if (!_registry.TryRemove(session.SessionId, out GatewaySession? removedSession))
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
_metrics.RemoveSessionEvents(session.SessionId);
|
||||
ReleaseSessionSlot();
|
||||
await removedSession.DisposeAsync().ConfigureAwait(false);
|
||||
}
|
||||
|
||||
private void ReleaseSessionSlot()
|
||||
{
|
||||
try
|
||||
{
|
||||
_sessionSlots.Release();
|
||||
}
|
||||
catch (SemaphoreFullException)
|
||||
{
|
||||
}
|
||||
}
|
||||
|
||||
private GatewaySession CreateSession(
|
||||
SessionOpenRequest request,
|
||||
string? clientIdentity)
|
||||
{
|
||||
string sessionId = CreateSessionId();
|
||||
string backendName = string.IsNullOrWhiteSpace(request.RequestedBackend)
|
||||
? GatewayContractInfo.DefaultBackendName
|
||||
: request.RequestedBackend!;
|
||||
TimeSpan commandTimeout = ResolveCommandTimeout(request.CommandTimeout);
|
||||
TimeSpan startupTimeout = TimeSpan.FromSeconds(_options.Worker.StartupTimeoutSeconds);
|
||||
TimeSpan shutdownTimeout = TimeSpan.FromSeconds(_options.Worker.ShutdownTimeoutSeconds);
|
||||
TimeSpan leaseDuration = TimeSpan.FromSeconds(_options.Sessions.DefaultLeaseSeconds);
|
||||
string pipeName = $"mxaccess-gateway-{Environment.ProcessId}-{sessionId}";
|
||||
string nonce = CreateNonce();
|
||||
DateTimeOffset openedAt = _timeProvider.GetUtcNow();
|
||||
string clientCorrelationId = CreateClientCorrelationId(request.ClientSessionName, sessionId);
|
||||
|
||||
return new GatewaySession(
|
||||
sessionId,
|
||||
backendName,
|
||||
pipeName,
|
||||
nonce,
|
||||
clientIdentity,
|
||||
request.ClientSessionName,
|
||||
clientCorrelationId,
|
||||
commandTimeout,
|
||||
startupTimeout,
|
||||
shutdownTimeout,
|
||||
leaseDuration,
|
||||
openedAt);
|
||||
}
|
||||
|
||||
private static string CreateClientCorrelationId(
|
||||
string? clientSessionName,
|
||||
string sessionId)
|
||||
{
|
||||
string clientName = string.IsNullOrWhiteSpace(clientSessionName)
|
||||
? "client"
|
||||
: clientSessionName!;
|
||||
|
||||
return $"{clientName}-{sessionId}";
|
||||
}
|
||||
|
||||
private TimeSpan ResolveCommandTimeout(Duration? requestedTimeout)
|
||||
{
|
||||
if (requestedTimeout is null)
|
||||
{
|
||||
return TimeSpan.FromSeconds(_options.Sessions.DefaultCommandTimeoutSeconds);
|
||||
}
|
||||
|
||||
TimeSpan timeout = requestedTimeout.ToTimeSpan();
|
||||
return timeout <= TimeSpan.Zero
|
||||
? TimeSpan.FromSeconds(_options.Sessions.DefaultCommandTimeoutSeconds)
|
||||
: timeout;
|
||||
}
|
||||
|
||||
private static string CreateSessionId()
|
||||
{
|
||||
return $"session-{Guid.NewGuid():N}";
|
||||
}
|
||||
|
||||
private static string CreateNonce()
|
||||
{
|
||||
Span<byte> bytes = stackalloc byte[32];
|
||||
RandomNumberGenerator.Fill(bytes);
|
||||
|
||||
return Convert.ToBase64String(bytes);
|
||||
}
|
||||
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public enum SessionManagerErrorCode
|
||||
{
|
||||
SessionNotFound,
|
||||
SessionNotReady,
|
||||
EventSubscriberAlreadyActive,
|
||||
EventQueueOverflow,
|
||||
SessionLimitExceeded,
|
||||
OpenFailed,
|
||||
CloseFailed,
|
||||
}
|
||||
@@ -0,0 +1,37 @@
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public sealed class SessionManagerException : Exception
|
||||
{
|
||||
/// <summary>
|
||||
/// Initializes a new instance of <see cref="SessionManagerException"/>.
|
||||
/// </summary>
|
||||
/// <param name="errorCode">Session manager error code.</param>
|
||||
/// <param name="message">Exception message.</param>
|
||||
public SessionManagerException(
|
||||
SessionManagerErrorCode errorCode,
|
||||
string message)
|
||||
: base(message)
|
||||
{
|
||||
ErrorCode = errorCode;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Initializes a new instance of <see cref="SessionManagerException"/> with an inner exception.
|
||||
/// </summary>
|
||||
/// <param name="errorCode">Session manager error code.</param>
|
||||
/// <param name="message">Exception message.</param>
|
||||
/// <param name="innerException">Inner exception.</param>
|
||||
public SessionManagerException(
|
||||
SessionManagerErrorCode errorCode,
|
||||
string message,
|
||||
Exception innerException)
|
||||
: base(message, innerException)
|
||||
{
|
||||
ErrorCode = errorCode;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Gets the session manager error code.
|
||||
/// </summary>
|
||||
public SessionManagerErrorCode ErrorCode { get; }
|
||||
}
|
||||
@@ -0,0 +1,24 @@
|
||||
using Google.Protobuf.WellKnownTypes;
|
||||
using ZB.MOM.WW.MxGateway.Contracts.Proto;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
public sealed record SessionOpenRequest(
|
||||
string? RequestedBackend,
|
||||
string? ClientSessionName,
|
||||
string? ClientCorrelationId,
|
||||
Duration? CommandTimeout)
|
||||
{
|
||||
/// <summary>Creates a SessionOpenRequest from a gRPC OpenSessionRequest contract.</summary>
|
||||
/// <param name="request">Request payload.</param>
|
||||
public static SessionOpenRequest FromContract(OpenSessionRequest request)
|
||||
{
|
||||
ArgumentNullException.ThrowIfNull(request);
|
||||
|
||||
return new SessionOpenRequest(
|
||||
request.RequestedBackend,
|
||||
request.ClientSessionName,
|
||||
request.ClientCorrelationId,
|
||||
request.CommandTimeout);
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,66 @@
|
||||
using System.Collections.Concurrent;
|
||||
using System.Diagnostics.CodeAnalysis;
|
||||
using ZB.MOM.WW.MxGateway.Contracts.Proto;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
/// <summary>
|
||||
/// Thread-safe registry of active gateway sessions.
|
||||
/// </summary>
|
||||
public sealed class SessionRegistry : ISessionRegistry
|
||||
{
|
||||
private readonly ConcurrentDictionary<string, GatewaySession> _sessions = new(StringComparer.Ordinal);
|
||||
|
||||
/// <summary>
|
||||
/// Gets the total count of sessions in the registry.
|
||||
/// </summary>
|
||||
public int Count => _sessions.Count;
|
||||
|
||||
/// <summary>
|
||||
/// Gets the count of non-closed sessions.
|
||||
/// </summary>
|
||||
public int ActiveCount => _sessions.Values.Count(session => session.State is not SessionState.Closed);
|
||||
|
||||
/// <summary>
|
||||
/// Adds a session to the registry.
|
||||
/// </summary>
|
||||
/// <param name="session">Gateway session to add.</param>
|
||||
public bool TryAdd(GatewaySession session)
|
||||
{
|
||||
ArgumentNullException.ThrowIfNull(session);
|
||||
|
||||
return _sessions.TryAdd(session.SessionId, session);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Retrieves a session by identifier.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Identifier of the session.</param>
|
||||
/// <param name="session">The retrieved session if found.</param>
|
||||
public bool TryGet(
|
||||
string sessionId,
|
||||
[MaybeNullWhen(false)] out GatewaySession session)
|
||||
{
|
||||
return _sessions.TryGetValue(sessionId, out session);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Removes a session from the registry by identifier.
|
||||
/// </summary>
|
||||
/// <param name="sessionId">Identifier of the session.</param>
|
||||
/// <param name="session">The removed session if found.</param>
|
||||
public bool TryRemove(
|
||||
string sessionId,
|
||||
[MaybeNullWhen(false)] out GatewaySession session)
|
||||
{
|
||||
return _sessions.TryRemove(sessionId, out session);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Returns a snapshot of all sessions in the registry.
|
||||
/// </summary>
|
||||
public IReadOnlyCollection<GatewaySession> Snapshot()
|
||||
{
|
||||
return _sessions.Values.ToArray();
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
/// <summary>Service collection extensions for session management.</summary>
|
||||
public static class SessionServiceCollectionExtensions
|
||||
{
|
||||
/// <summary>Registers gateway session registry, manager, and factory services.</summary>
|
||||
/// <param name="services">Service collection to register services in.</param>
|
||||
/// <returns>The service collection for chaining.</returns>
|
||||
public static IServiceCollection AddGatewaySessions(this IServiceCollection services)
|
||||
{
|
||||
services.AddSingleton<ISessionRegistry, SessionRegistry>();
|
||||
services.AddSingleton<ISessionWorkerClientFactory, SessionWorkerClientFactory>();
|
||||
services.AddSingleton<ISessionManager, SessionManager>();
|
||||
services.AddHostedService<SessionLeaseMonitorHostedService>();
|
||||
services.AddHostedService<SessionShutdownHostedService>();
|
||||
|
||||
return services;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,29 @@
|
||||
using Microsoft.Extensions.Hosting;
|
||||
using Microsoft.Extensions.Logging;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
/// <summary>Hosted service that cleanly shuts down all gateway sessions on application shutdown.</summary>
|
||||
public sealed class SessionShutdownHostedService(
|
||||
ISessionManager sessionManager,
|
||||
ILogger<SessionShutdownHostedService> logger) : IHostedService
|
||||
{
|
||||
/// <inheritdoc />
|
||||
public Task StartAsync(CancellationToken cancellationToken)
|
||||
{
|
||||
return Task.CompletedTask;
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
public async Task StopAsync(CancellationToken cancellationToken)
|
||||
{
|
||||
try
|
||||
{
|
||||
await sessionManager.ShutdownAsync(cancellationToken).ConfigureAwait(false);
|
||||
}
|
||||
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
|
||||
{
|
||||
logger.LogWarning("Gateway session shutdown was canceled by host shutdown timeout.");
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,180 @@
|
||||
using System.IO.Pipes;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using Microsoft.Extensions.Options;
|
||||
using ZB.MOM.WW.MxGateway.Contracts;
|
||||
using ZB.MOM.WW.MxGateway.Contracts.Proto;
|
||||
using ZB.MOM.WW.MxGateway.Server.Configuration;
|
||||
using ZB.MOM.WW.MxGateway.Server.Metrics;
|
||||
using ZB.MOM.WW.MxGateway.Server.Workers;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Sessions;
|
||||
|
||||
/// <summary>Factory for creating worker clients and launching worker processes.</summary>
|
||||
public sealed class SessionWorkerClientFactory : ISessionWorkerClientFactory
|
||||
{
|
||||
private readonly IWorkerProcessLauncher _workerProcessLauncher;
|
||||
private readonly GatewayMetrics _metrics;
|
||||
private readonly TimeProvider _timeProvider;
|
||||
private readonly ILoggerFactory _loggerFactory;
|
||||
private readonly GatewayOptions _options;
|
||||
|
||||
/// <summary>Initializes a new instance of the SessionWorkerClientFactory class.</summary>
|
||||
/// <param name="workerProcessLauncher">Service for launching worker processes.</param>
|
||||
/// <param name="options">Configuration options.</param>
|
||||
/// <param name="metrics">Metrics collector for gateway events.</param>
|
||||
/// <param name="loggerFactory">Logger factory for creating loggers.</param>
|
||||
/// <param name="timeProvider">Optional time provider for testing; defaults to system time.</param>
|
||||
public SessionWorkerClientFactory(
|
||||
IWorkerProcessLauncher workerProcessLauncher,
|
||||
IOptions<GatewayOptions> options,
|
||||
GatewayMetrics metrics,
|
||||
ILoggerFactory loggerFactory,
|
||||
TimeProvider? timeProvider = null)
|
||||
{
|
||||
_workerProcessLauncher = workerProcessLauncher ?? throw new ArgumentNullException(nameof(workerProcessLauncher));
|
||||
ArgumentNullException.ThrowIfNull(options);
|
||||
_metrics = metrics ?? throw new ArgumentNullException(nameof(metrics));
|
||||
_loggerFactory = loggerFactory ?? throw new ArgumentNullException(nameof(loggerFactory));
|
||||
_timeProvider = timeProvider ?? TimeProvider.System;
|
||||
_options = options.Value;
|
||||
}
|
||||
|
||||
/// <summary>Creates a worker client and launches the worker process.</summary>
|
||||
/// <param name="session">The gateway session.</param>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
/// <returns>The created worker client.</returns>
|
||||
public async Task<IWorkerClient> CreateAsync(
|
||||
GatewaySession session,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
ArgumentNullException.ThrowIfNull(session);
|
||||
|
||||
NamedPipeServerStream? pipe = CreatePipe(session.PipeName);
|
||||
WorkerProcessHandle? processHandle = null;
|
||||
IWorkerClient? workerClient = null;
|
||||
using CancellationTokenSource startupCancellation =
|
||||
CancellationTokenSource.CreateLinkedTokenSource(cancellationToken);
|
||||
startupCancellation.CancelAfter(session.StartupTimeout);
|
||||
try
|
||||
{
|
||||
session.TransitionTo(SessionState.StartingWorker);
|
||||
processHandle = await _workerProcessLauncher
|
||||
.LaunchAsync(
|
||||
new WorkerProcessLaunchRequest(
|
||||
session.SessionId,
|
||||
session.PipeName,
|
||||
GatewayContractInfo.WorkerProtocolVersion,
|
||||
session.Nonce,
|
||||
pipe),
|
||||
startupCancellation.Token)
|
||||
.ConfigureAwait(false);
|
||||
|
||||
session.TransitionTo(SessionState.WaitingForPipe);
|
||||
await WaitForPipeConnectionAsync(pipe, startupCancellation.Token).ConfigureAwait(false);
|
||||
|
||||
session.TransitionTo(SessionState.Handshaking);
|
||||
WorkerFrameProtocolOptions frameOptions = new(
|
||||
session.SessionId,
|
||||
GatewayContractInfo.WorkerProtocolVersion,
|
||||
_options.Worker.MaxMessageBytes);
|
||||
WorkerClientConnection connection = new(
|
||||
session.SessionId,
|
||||
session.Nonce,
|
||||
pipe,
|
||||
frameOptions,
|
||||
processHandle);
|
||||
WorkerClientOptions clientOptions = new()
|
||||
{
|
||||
HeartbeatGrace = TimeSpan.FromSeconds(_options.Worker.HeartbeatGraceSeconds),
|
||||
HeartbeatCheckInterval = TimeSpan.FromSeconds(_options.Worker.HeartbeatIntervalSeconds),
|
||||
EventChannelCapacity = _options.Events.QueueCapacity,
|
||||
MaxPendingCommands = _options.Sessions.MaxPendingCommandsPerSession,
|
||||
};
|
||||
|
||||
workerClient = new WorkerClient(
|
||||
connection,
|
||||
clientOptions,
|
||||
_metrics,
|
||||
_timeProvider,
|
||||
_loggerFactory.CreateLogger<WorkerClient>());
|
||||
|
||||
pipe = null;
|
||||
processHandle = null;
|
||||
|
||||
session.TransitionTo(SessionState.InitializingWorker);
|
||||
await workerClient.StartAsync(startupCancellation.Token).ConfigureAwait(false);
|
||||
|
||||
return workerClient;
|
||||
}
|
||||
catch (Exception exception)
|
||||
{
|
||||
if (workerClient is not null)
|
||||
{
|
||||
try
|
||||
{
|
||||
workerClient.Kill("OpenSessionFailed");
|
||||
}
|
||||
catch
|
||||
{
|
||||
// Preserve the startup failure while still disposing below.
|
||||
}
|
||||
|
||||
await workerClient.DisposeAsync().ConfigureAwait(false);
|
||||
}
|
||||
else
|
||||
{
|
||||
if (processHandle is not null)
|
||||
{
|
||||
try
|
||||
{
|
||||
if (!processHandle.Process.HasExited)
|
||||
{
|
||||
processHandle.Process.Kill(entireProcessTree: true);
|
||||
_metrics.WorkerKilled("OpenSessionFailed");
|
||||
}
|
||||
}
|
||||
finally
|
||||
{
|
||||
processHandle.Dispose();
|
||||
}
|
||||
}
|
||||
|
||||
pipe?.Dispose();
|
||||
}
|
||||
|
||||
if (exception is OperationCanceledException
|
||||
&& startupCancellation.IsCancellationRequested
|
||||
&& !cancellationToken.IsCancellationRequested)
|
||||
{
|
||||
throw new TimeoutException(
|
||||
$"Worker session {session.SessionId} did not complete startup within {session.StartupTimeout}.",
|
||||
exception);
|
||||
}
|
||||
|
||||
throw;
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>Creates a named pipe for worker communication.</summary>
|
||||
/// <param name="pipeName">The pipe name.</param>
|
||||
/// <returns>Named pipe server stream.</returns>
|
||||
private static NamedPipeServerStream CreatePipe(string pipeName)
|
||||
{
|
||||
return new NamedPipeServerStream(
|
||||
pipeName,
|
||||
PipeDirection.InOut,
|
||||
maxNumberOfServerInstances: 1,
|
||||
PipeTransmissionMode.Byte,
|
||||
PipeOptions.Asynchronous);
|
||||
}
|
||||
|
||||
/// <summary>Waits for a client to connect to the pipe.</summary>
|
||||
/// <param name="pipe">The named pipe.</param>
|
||||
/// <param name="cancellationToken">Cancellation token.</param>
|
||||
private static async Task WaitForPipeConnectionAsync(
|
||||
NamedPipeServerStream pipe,
|
||||
CancellationToken cancellationToken)
|
||||
{
|
||||
await pipe.WaitForConnectionAsync(cancellationToken).ConfigureAwait(false);
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user