perf(kpi-history): time-sliced batched purge replaces the single daily mega-DELETE

src/ZB.MOM.WW.ScadaBridge.Commons/Interfaces/Repositories/IKpiHistoryRepository.cs

@@ -42,7 +42,9 @@ public interface IKpiHistoryRepository
 
     /// <summary>
     /// Bulk-deletes rows whose <see cref="KpiSample.CapturedAtUtc"/> is strictly older
-    /// than <paramref name="before"/> (retention purge).
+    /// than <paramref name="before"/> (retention purge). Implementations slice the
+    /// purge into time-windowed DELETE batches so a large catch-up (e.g. after an
+    /// outage) never runs as a single lock/log-heavy transaction (arch-review 04, P4).
     /// </summary>
     /// <param name="before">UTC cut-off; rows captured before this instant are deleted.</param>
     /// <param name="cancellationToken">Cancellation token.</param>

src/ZB.MOM.WW.ScadaBridge.ConfigurationDatabase/Repositories/KpiHistoryRepository.cs

@@ -64,9 +64,22 @@ public sealed class KpiHistoryRepository : IKpiHistoryRepository
     /// <inheritdoc />
     public async Task<int> PurgeOlderThanAsync(DateTime before, CancellationToken cancellationToken = default)
     {
-        // Set-based delete — no entity materialisation; returns the rows affected.
-        return await _context.KpiSamples
-            .Where(s => s.CapturedAtUtc < before)
-            .ExecuteDeleteAsync(cancellationToken);
+        // Time-sliced batches: each DELETE covers at most one hour of samples, capping the
+        // lock/log footprint per statement (arch-review 04, P4 — steady state is ~1 day of
+        // rows/day; after an outage the catch-up would otherwise be one giant transaction).
+        var total = 0;
+        var floor = await _context.KpiSamples.Where(s => s.CapturedAtUtc < before)
+            .MinAsync(s => (DateTime?)s.CapturedAtUtc, cancellationToken);
+        while (floor is not null && floor < before)
+        {
+            var ceiling = floor.Value.AddHours(1) < before ? floor.Value.AddHours(1) : before;
+            total += await _context.KpiSamples
+                .Where(s => s.CapturedAtUtc < ceiling)
+                .ExecuteDeleteAsync(cancellationToken);
+            floor = await _context.KpiSamples.Where(s => s.CapturedAtUtc < before)
+                .MinAsync(s => (DateTime?)s.CapturedAtUtc, cancellationToken);
+        }
+
+        return total;
     }
 }