fix(archreview): gateway core P0 remediation (GWC-01/02/03, TST-02, TST-12)
Interlocking changes across the gateway server (shared GatewaySession.cs / SessionManager.cs), committed together: - GWC-01 (Critical): alarm monitor now attaches as an internal (non-counted) distributor subscriber instead of a second raw drain of the single worker event channel; WorkerClient._events -> SingleReader with a claimed-once guard so a future dual-consumer regression throws loudly. - GWC-02 (High): faulted sessions are swept in CloseExpiredLeasesAsync (IsFaultedReapable + FaultedReason); new FaultedGraceSeconds (default 0). - GWC-03 (High): configurable MaxSparseArrayLength (default 1_000_000) enforced before allocation. - TST-02 (High, security): StreamEvents attach now enforces the opening key id -> PermissionDenied on owner mismatch. - TST-12 (Medium): CLAUDE.md retention-defaults sentence corrected. Verified: NonWindows build clean; targeted tests 135/135 on macOS, plus WorkerClientTests 18/18 on the Windows host.
This commit is contained in:
@@ -1,4 +1,5 @@
|
||||
using System.Diagnostics.CodeAnalysis;
|
||||
using System.Runtime.CompilerServices;
|
||||
using System.Security.Cryptography;
|
||||
using Google.Protobuf.WellKnownTypes;
|
||||
using Microsoft.Extensions.Logging;
|
||||
@@ -18,6 +19,7 @@ public sealed class SessionManager : ISessionManager
|
||||
public const string GatewayShutdownReason = "gateway-shutdown";
|
||||
public const string LeaseExpiredReason = "lease-expired";
|
||||
public const string DetachGraceExpiredReason = "detach-grace-expired";
|
||||
public const string FaultedReason = "faulted-reaped";
|
||||
|
||||
private readonly ISessionRegistry _registry;
|
||||
private readonly ISessionWorkerClientFactory _workerClientFactory;
|
||||
@@ -189,6 +191,22 @@ public sealed class SessionManager : ISessionManager
|
||||
return session.ReadEventsAsync(cancellationToken);
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
public async IAsyncEnumerable<MxEvent> ReadAlarmEventsAsync(
|
||||
string sessionId,
|
||||
[EnumeratorCancellation] CancellationToken cancellationToken)
|
||||
{
|
||||
GatewaySession session = GetRequiredSession(sessionId);
|
||||
using IEventSubscriberLease lease = session.AttachInternalEventSubscriber();
|
||||
|
||||
await foreach (MxEvent mxEvent in lease.Reader
|
||||
.ReadAllAsync(cancellationToken)
|
||||
.ConfigureAwait(false))
|
||||
{
|
||||
yield return mxEvent;
|
||||
}
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
public async Task<SessionCloseResult> CloseSessionAsync(
|
||||
string sessionId,
|
||||
@@ -259,22 +277,25 @@ public sealed class SessionManager : ISessionManager
|
||||
int closedCount = 0;
|
||||
foreach (GatewaySession session in _registry.Snapshot())
|
||||
{
|
||||
// A session is swept when its normal lease has expired OR its detach-grace
|
||||
// retention window has elapsed (last external subscriber dropped and no client
|
||||
// reconnected within DetachGraceSeconds). The detach-grace close is the same
|
||||
// teardown as a lease-expiry close; only the reason differs so operators can tell
|
||||
// a short reconnect-window expiry from a long idle-lease expiry in logs/metrics.
|
||||
// Lease-expiry takes PRECEDENCE over detach-grace when both conditions fire
|
||||
// simultaneously (reason will be lease-expired, not detach-grace-expired).
|
||||
// A session is swept when its normal lease has expired, it has FAULTED (a faulted
|
||||
// session is permanently unusable yet otherwise pins a session slot and a live x86
|
||||
// worker until its DefaultLeaseSeconds lease expires), OR its detach-grace retention
|
||||
// window has elapsed (last external subscriber dropped and no client reconnected
|
||||
// within DetachGraceSeconds). All three are the same teardown; only the reason differs
|
||||
// so operators can tell a fault reap from a short reconnect-window expiry from a long
|
||||
// idle-lease expiry in logs/metrics. Precedence when several fire simultaneously:
|
||||
// lease-expired, then faulted, then detach-grace.
|
||||
//
|
||||
// TOCTOU note: eligibility is re-verified atomically inside TryBeginCloseIfExpired
|
||||
// under _syncRoot, so a client that reattaches a subscriber between the check above
|
||||
// and the close call wins the race and the session is left open and usable.
|
||||
string? reason = session.IsLeaseExpired(now)
|
||||
? LeaseExpiredReason
|
||||
: session.IsDetachGraceExpired(now)
|
||||
? DetachGraceExpiredReason
|
||||
: null;
|
||||
: session.IsFaultedReapable(now)
|
||||
? FaultedReason
|
||||
: session.IsDetachGraceExpired(now)
|
||||
? DetachGraceExpiredReason
|
||||
: null;
|
||||
if (reason is null)
|
||||
{
|
||||
continue;
|
||||
@@ -457,7 +478,8 @@ public sealed class SessionManager : ISessionManager
|
||||
eventStreaming,
|
||||
TimeSpan.FromSeconds(Math.Max(0, _options.Sessions.DetachGraceSeconds)),
|
||||
TimeSpan.FromMilliseconds(Math.Max(0, _options.Sessions.WorkerReadyWaitTimeoutMs)),
|
||||
_addressNormalizer);
|
||||
_addressNormalizer,
|
||||
TimeSpan.FromSeconds(Math.Max(0, _options.Sessions.FaultedGraceSeconds)));
|
||||
}
|
||||
|
||||
private static string CreateClientCorrelationId(
|
||||
|
||||
Reference in New Issue
Block a user