fix: Fixes send-path backpressure: consume IORingGroup 1.0.8, stop dropping packets silently (#2551)

## Summary

Two related fixes on the outbound path:

1. Consume **IORingGroup 1.0.8**, which allows more than one send in flight per socket, and expose the two settings that go with it.
2. Stop `NetState.Send` silently discarding packets when the send buffer fills — including an out-of-bounds write reachable in that state.

## 1. Send-path stall (RIO)

RIO reports send completion on **acknowledgement**, not on copy, so a completion cannot arrive sooner than one round trip. With one send in flight, `PostSend` refused to post again until the previous completion arrived — capping a connection at **one send per RTT** whenever it had data queued.

Measured on a 50ms-RTT production shard:

| | before | after |
|---|---|---|
| in-game latency, data flowing | **101–146 ms** | **48–51 ms** |
| p95 | ~135 ms | 52.8 ms |
| samples > 70 ms | 20 | **0** |

The control that confirms the mechanism: server-side post→completion was **unchanged** at median 92ms across both runs. The ACK-binding is inherent to RIO and did not move; only its propagation into application latency did.

Two things worth recording, because they explain why this went unnoticed:

- As little as **6 bytes** of queued data held the gate shut, so it reproduced in empty areas, not just crowded ones.
- The same measurement at loopback RTT is **microseconds**, so local testing could never surface it.

New settings, both restart-time:

- **`network.maxOutstandingSends`** (default 32) — sends in flight per connection. Honoured by RIO only; other backends complete sends on copy and report 1. Costs a request-queue and completion-queue slot per send, **not another buffer**, since every outstanding send addresses a different range of the same registered buffer. Worst-case added latency is roughly `completion RTT / value`.
- **`network.sendBufferSize`** (default 256KB) — per-connection send buffer, coerced to a power of two of at least the platform allocation granularity. This is the lever for the disconnects below, and the per-connection memory ceiling.

## 2. Send buffer full

`NetState.Send` had three failure modes once the buffer filled, none of them visible:

| writable | behaviour |
|---|---|
| `0` | `GetSendBuffer` returned false → **packet dropped**, no log, no disconnect |
| `4 … needed-1` | `Compress` returned 0 → `CommitWrite(0)` → **packet dropped** the same way |
| `1 … 3` | `safeOutputLength = (nuint)output.Length - 4` **underflows** → hot-loop bounds check never trips → **writes past the span** |

The first two leave a client connected while quietly missing game state, which is undiagnosable from either end. The third corrupts the in-flight region of the ring buffer, and is reachable precisely when a connection is congested, since callers only check for non-zero space.

`Compress` now refuses an output too small to bound, and `Send` reports exhaustion instead of dropping — logging and disconnecting with **needed / writable / unacked / capacity**. Those numbers separate a slow client holding the buffer from a buffer genuinely too small for the shard, which is the case that warrants raising `network.sendBufferSize`.

## Testing

`NetworkCompressionBoundsTests` covers the underflow using sentinel bytes around the output window. **Verified to fail without the guard** (4 failures from overwritten sentinels), confirming the out-of-bounds writes were real rather than theoretical.

Full suites green: **788 Server.Tests**, **597 UOContent.Tests**, Release build clean against the published 1.0.8.

## Notes for reviewers

- Upstream change: modernuo/IORingGroup#9.
- The buffer-full path is now *loud* where it used to be silent. If a shard has been quietly dropping packets under load, this will surface as disconnects — that is the intended outcome, and the log line says which setting to raise.
- Follow-up under discussion: promoting a connection to a larger buffer instead of disconnecting, which looks feasible on a live connection since buffers are referenced per-operation rather than bound to the request queue.

Projects/Server/Network/NetState/NetState.Network.cs

@@ -19,6 +19,7 @@ using System.Linq;
 using System.Net;
 using System.Net.NetworkInformation;
 using System.Network;
+using System.Numerics;
 
 namespace Server.Network;
 
@@ -28,9 +29,10 @@ namespace Server.Network;
 public partial class NetState
 {
     // Buffer sizes
-    private const int RecvBufferSize = 1024 * 64;   // 64KB recv buffers
-    private const int SendBufferSize = 1024 * 256;  // 256KB send buffers
-    private const int MaxConnections = 4096;        // Max concurrent connections
+    private const int RecvBufferSize = 1024 * 64;    // 64KB recv buffers
+    private const int DefaultSendBufferSize = 1024 * 256;  // 256KB send buffers
+    private const int MinSendBufferSize = 1024 * 64;       // Platform allocation granularity
+    private const int MaxConnections = 4096;         // Max concurrent connections
 
     private static readonly Queue<NetState> _disposed = [];
     private static readonly TimeSpan ConnectingSocketIdleLimit = TimeSpan.FromMilliseconds(5000); // 5 seconds
@@ -41,7 +43,9 @@ public partial class NetState
     // NetState storage indexed by RingSocket.Id
     private static readonly NetState[] _netStates = new NetState[MaxConnections];
 
-    // Events buffer for ProcessCompletions
+    // Events buffer for ProcessCompletions. Bounded by one event per peeked completion
+    // (maxSockets), doubled for headroom. Undersizing drops DataReceived events whose bytes were
+    // already committed, leaving them unparsed until the next recv completes.
     private static readonly RingSocketEvent[] _events = new RingSocketEvent[MaxConnections * 2];
 
     // Listener management
@@ -88,20 +92,61 @@ public partial class NetState
         // Initialize IP rate limiter
         _ipRateLimiter = new IPRateLimiter(10, 10000, 1000, 2.0, 3_600_000, Core.ClosingTokenSource.Token);
 
+        // Sends in flight per connection; honoured by RIO only (see IIORingGroup). Costs a
+        // request-queue and completion-queue slot per send, not another buffer. Worst-case added
+        // latency is roughly completion RTT / this value.
+        var maxOutstandingSends = ServerConfiguration.GetOrUpdateSetting("network.maxOutstandingSends", 32);
+
         // Initialize IORingGroup
-        var ring = IORingGroup.Create(queueSize: MaxConnections * 2, maxConnections: MaxConnections);
+        var ring = IORingGroup.Create(
+            queueSize: MaxConnections * 2,
+            maxConnections: MaxConnections,
+            maxOutstandingSends: maxOutstandingSends
+        );
+
+        // Per-connection send buffer: the lever for "send buffer exhausted" disconnects, and the
+        // per-connection memory ceiling.
+        var sendBufferSize = GetSendBufferSize();
 
         // Create socket manager which handles buffer pools and socket lifecycle
         _socketManager = new RingSocketManager(
             ring,
             maxSockets: MaxConnections,
             recvBufferSize: RecvBufferSize,
-            sendBufferSize: SendBufferSize,
+            sendBufferSize: sendBufferSize,
             initialBufferSlabs: 8,
             maxBufferSlabs: 32
         );
     }
 
+    /// <summary>
+    /// Reads the configured send buffer size, coerced to a power of two of at least the platform
+    /// allocation granularity. IORingBuffer requires this and would otherwise throw at socket
+    /// creation rather than at startup.
+    /// </summary>
+    private static int GetSendBufferSize()
+    {
+        var configured = ServerConfiguration.GetOrUpdateSetting("network.sendBufferSize", DefaultSendBufferSize);
+        var size = Math.Max(MinSendBufferSize, configured);
+
+        if (!BitOperations.IsPow2(size))
+        {
+            size = (int)BitOperations.RoundUpToPowerOf2((uint)size);
+        }
+
+        if (size != configured)
+        {
+            logger.Warning(
+                "network.sendBufferSize {Configured} is not a power of two of at least {Minimum}; using {Adjusted}",
+                configured,
+                MinSendBufferSize,
+                size
+            );
+        }
+
+        return size;
+    }
+
     /// <summary>
     /// Starts the network server on configured listening addresses.
     /// </summary>