feat(audit): M5.5 per-channel retention overrides via purge-role bounded delete (T3)

This commit is contained in:
Joseph Doherty
2026-06-16 21:47:50 -04:00
parent 55630b48b6
commit 50b674accc
13 changed files with 583 additions and 3 deletions
@@ -167,6 +167,9 @@ public class AuditLogPurgeActor : ReceiveActor
if (boundaries.Count == 0)
{
// No whole-month partitions are eligible, but per-channel overrides may
// still expire rows earlier than the global window — run them below.
await RunPerChannelOverridesAsync(repository).ConfigureAwait(false);
return;
}
@@ -202,6 +205,80 @@ public class AuditLogPurgeActor : ReceiveActor
sw.ElapsedMilliseconds);
}
}
// M5.5 (T3): after the channel-blind global partition switch-out, apply any
// per-channel retention overrides that are SHORTER than the global window via
// a bounded, batched row DELETE on the same maintenance path. The global
// switch-out has already dropped whole months older than RetentionDays; these
// deletes only ever expire rows EARLIER than that, so they run last and are a
// strict tightening.
await RunPerChannelOverridesAsync(repository).ConfigureAwait(false);
}
/// <summary>
/// M5.5 (T3): runs each per-channel retention override whose window is strictly
/// shorter than the global <see cref="AuditLogOptions.RetentionDays"/>, deleting
/// rows of that channel older than the channel-specific threshold via a bounded,
/// batched maintenance-path DELETE. Each channel runs inside its own try/catch so
/// one bad channel does not abandon the others on the same tick, mirroring the
/// per-boundary error isolation of the partition switch-out loop.
/// </summary>
/// <param name="repository">The repository resolved for this tick's DI scope.</param>
private async Task RunPerChannelOverridesAsync(IAuditLogRepository repository)
{
var overrides = _auditOptions.PerChannelRetentionDays;
if (overrides is null || overrides.Count == 0)
{
return;
}
var globalDays = _auditOptions.RetentionDays;
foreach (var (channel, days) in overrides)
{
// Only act when the per-channel window is strictly shorter than the global
// one. Equal/longer windows are already covered by the global partition
// switch-out, so a row DELETE would be redundant work (and a longer window
// is meaningless — the partition is dropped on the global schedule).
if (days >= globalDays)
{
continue;
}
var channelThreshold = DateTime.UtcNow - TimeSpan.FromDays(days);
var sw = Stopwatch.StartNew();
try
{
var rowsDeleted = await repository
.PurgeChannelOlderThanAsync(channel, channelThreshold, _purgeOptions.ChannelPurgeBatchSize)
.ConfigureAwait(false);
sw.Stop();
if (rowsDeleted > 0)
{
_logger.LogInformation(
"Purged {RowsDeleted} AuditLog rows for channel {Channel} older than {Threshold:o} " +
"(per-channel override {Days}d < global {GlobalDays}d) in {DurationMs} ms.",
rowsDeleted,
channel,
channelThreshold,
days,
globalDays,
sw.ElapsedMilliseconds);
}
}
catch (Exception ex)
{
sw.Stop();
_logger.LogError(
ex,
"Failed to apply per-channel retention override for channel {Channel} " +
"({Days}d); other channels continue. Elapsed {DurationMs} ms.",
channel,
days,
sw.ElapsedMilliseconds);
}
}
}
/// <summary>Self-tick triggering a purge pass across all eligible partitions.</summary>