From 1a53b8082a2c0dc778dade03b1a79519a59e48eb Mon Sep 17 00:00:00 2001
From: Joseph Doherty <dohejw01@gmail.com>
Date: Wed, 8 Jul 2026 17:45:11 -0400
Subject: [PATCH] perf(store-and-forward): bound retry sweep with
 SweepBatchLimit (default 500) on the due-rows query

---
 .../StoreAndForwardOptions.cs                 |  7 +++++
 .../StoreAndForwardService.cs                 |  2 +-
 .../StoreAndForwardStorage.cs                 |  9 ++++++-
 .../StoreAndForwardOptionsTests.cs            |  4 +++
 .../StoreAndForwardStorageTests.cs            | 27 +++++++++++++++++++
 5 files changed, 47 insertions(+), 2 deletions(-)

diff --git a/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardOptions.cs b/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardOptions.cs
index b1f5927c..7546e942 100644
--- a/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardOptions.cs
+++ b/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardOptions.cs
@@ -22,4 +22,11 @@ public class StoreAndForwardOptions
 
     /// <summary>Interval for the background retry timer sweep.</summary>
     public TimeSpan RetryTimerInterval { get; set; } = TimeSpan.FromSeconds(10);
+
+    /// <summary>
+    /// Maximum due rows loaded per retry sweep. Bounds sweep memory and duration
+    /// under backlog; the remainder is picked up on the next tick (10 s).
+    /// 0 = unlimited (legacy).
+    /// </summary>
+    public int SweepBatchLimit { get; set; } = 500;
 }
diff --git a/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardService.cs b/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardService.cs
index 77527dd5..afeee811 100644
--- a/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardService.cs
+++ b/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardService.cs
@@ -601,7 +601,7 @@ public class StoreAndForwardService
                 }
             }
 
-            var messages = await _storage.GetMessagesForRetryAsync();
+            var messages = await _storage.GetMessagesForRetryAsync(_options.SweepBatchLimit);
             if (messages.Count == 0) return;
 
             _logger.LogDebug("Retry sweep: {Count} messages due for retry", messages.Count);
diff --git a/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardStorage.cs b/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardStorage.cs
index 2348395b..b84a0347 100644
--- a/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardStorage.cs
+++ b/src/ZB.MOM.WW.ScadaBridge.StoreAndForward/StoreAndForwardStorage.cs
@@ -180,7 +180,7 @@ public class StoreAndForwardStorage
     /// Gets all messages that are due for retry (Pending status, last attempt older than retry interval).
     /// </summary>
     /// <returns>A task that resolves to the list of messages due for retry, ordered by creation time ascending.</returns>
-    public async Task<List<StoreAndForwardMessage>> GetMessagesForRetryAsync()
+    public async Task<List<StoreAndForwardMessage>> GetMessagesForRetryAsync(int limit = 0)
     {
         await using var connection = new SqliteConnection(_connectionString);
         await connection.OpenAsync();
@@ -197,6 +197,13 @@ public class StoreAndForwardStorage
                    OR (julianday('now') - julianday(last_attempt_at)) * 86400000 >= retry_interval_ms)
             ORDER BY created_at ASC";
 
+        // Bound the sweep batch (oldest-first). 0 = unlimited (legacy).
+        if (limit > 0)
+        {
+            cmd.CommandText += "\n            LIMIT @limit";
+            cmd.Parameters.AddWithValue("@limit", limit);
+        }
+
         cmd.Parameters.AddWithValue("@pending", (int)StoreAndForwardMessageStatus.Pending);
 
         return await ReadMessagesAsync(cmd);
diff --git a/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardOptionsTests.cs b/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardOptionsTests.cs
index 90f26f02..1da1c996 100644
--- a/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardOptionsTests.cs
+++ b/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardOptionsTests.cs
@@ -34,4 +34,8 @@ public class StoreAndForwardOptionsTests
         Assert.Equal(TimeSpan.FromMinutes(5), options.DefaultRetryInterval);
         Assert.Equal(100, options.DefaultMaxRetries);
     }
+
+    [Fact]
+    public void SweepBatchLimit_Defaults_To_500() =>
+        Assert.Equal(500, new StoreAndForwardOptions().SweepBatchLimit);
 }
diff --git a/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardStorageTests.cs b/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardStorageTests.cs
index ae66182f..e7d0f704 100644
--- a/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardStorageTests.cs
+++ b/tests/ZB.MOM.WW.ScadaBridge.StoreAndForward.Tests/StoreAndForwardStorageTests.cs
@@ -587,6 +587,33 @@ public class StoreAndForwardStorageTests : IAsyncLifetime, IDisposable
         Assert.Null(retrieved!.ParentExecutionId);
     }
 
+    // ── Task 7 (arch review 02, Performance): bounded due-rows query ──
+
+    [Fact]
+    public async Task GetMessagesForRetry_HonorsLimit_OldestFirst()
+    {
+        var baseTime = DateTimeOffset.UtcNow.AddMinutes(-10);
+        for (var i = 0; i < 5; i++)
+        {
+            await _storage.EnqueueAsync(new StoreAndForwardMessage
+            {
+                Id = $"m{i}",
+                Category = StoreAndForwardCategory.ExternalSystem,
+                Target = "t",
+                PayloadJson = "{}",
+                RetryCount = 0,
+                MaxRetries = 50,
+                RetryIntervalMs = 0, // always due
+                CreatedAt = baseTime.AddSeconds(i),
+                Status = StoreAndForwardMessageStatus.Pending
+            });
+        }
+
+        var page = await _storage.GetMessagesForRetryAsync(limit: 3);
+        Assert.Equal(3, page.Count);
+        Assert.Equal(new[] { "m0", "m1", "m2" }, page.Select(m => m.Id));
+    }
+
     private static StoreAndForwardMessage CreateMessage(string id, StoreAndForwardCategory category)
     {
         return new StoreAndForwardMessage