perf(sitelog): batched event-log commits and sliced retention purge

src/ZB.MOM.WW.ScadaBridge.SiteEventLogging/EventLogPurgeService.cs

@@ -30,6 +30,9 @@ public class EventLogPurgeService : BackgroundService
     /// <summary>Number of events deleted per cap-purge batch.</summary>
     private const int CapPurgeBatchSize = 1000;
 
+    /// <summary>Number of events deleted per retention-purge batch — same size as <see cref="CapPurgeBatchSize"/>.</summary>
+    private const int RetentionPurgeBatchSize = 1000;
+
     private readonly SiteEventLogger _eventLogger;
     private readonly SiteEventLogOptions _options;
     private readonly ILogger<EventLogPurgeService> _logger;
@@ -118,21 +121,46 @@ public class EventLogPurgeService : BackgroundService
         }
     }
 
+    /// <summary>
+    /// Deletes events older than the retention window, in bounded
+    /// <see cref="RetentionPurgeBatchSize"/>-row slices per DELETE statement rather than
+    /// one unbounded DELETE for the whole expired set — mirroring the batching already
+    /// used a few lines below in <see cref="PurgeByStorageCap"/> (<see cref="CapPurgeBatchSize"/>).
+    /// An expired backlog in the tens/hundreds of thousands of rows would otherwise hold a
+    /// single SQLite write transaction (and the shared <c>_writeLock</c>) open for the
+    /// whole delete, blocking every concurrent <see cref="SiteEventLogger.LogEventAsync"/>
+    /// writer-loop flush for that entire duration.
+    /// </summary>
     private void PurgeByRetention()
     {
         var cutoff = DateTimeOffset.UtcNow.AddDays(-_options.RetentionDays).ToString("o");
+        var totalDeleted = 0;
 
-        var deleted = _eventLogger.WithConnection(connection =>
+        while (true)
         {
-            using var cmd = connection.CreateCommand();
-            cmd.CommandText = "DELETE FROM site_events WHERE timestamp < $cutoff";
-            cmd.Parameters.AddWithValue("$cutoff", cutoff);
-            return cmd.ExecuteNonQuery();
-        });
+            var deleted = _eventLogger.WithConnection(connection =>
+            {
+                using var cmd = connection.CreateCommand();
+                cmd.CommandText = $"""
+                    DELETE FROM site_events WHERE id IN (
+                        SELECT id FROM site_events
+                        WHERE timestamp < $cutoff
+                        LIMIT {RetentionPurgeBatchSize}
+                    )
+                    """;
+                cmd.Parameters.AddWithValue("$cutoff", cutoff);
+                return cmd.ExecuteNonQuery();
+            });
 
-        if (deleted > 0)
+            totalDeleted += deleted;
+
+            if (deleted < RetentionPurgeBatchSize)
+                break;
+        }
+
+        if (totalDeleted > 0)
         {
-            _logger.LogInformation("Purged {Count} events older than {Days} days", deleted, _options.RetentionDays);
+            _logger.LogInformation("Purged {Count} events older than {Days} days", totalDeleted, _options.RetentionDays);
         }
     }