Add per-webhook event retention reaper (closes #63)
All checks were successful
check / check (push) Successful in 5s

This commit is contained in:
2026-08-07 20:19:01 +07:00
parent 752d6beead
commit f6abc9b392
5 changed files with 604 additions and 5 deletions

View File

@@ -0,0 +1,252 @@
package database
import (
"context"
"fmt"
"log/slog"
"sync"
"time"
"go.uber.org/fx"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/config"
"sneak.berlin/go/webhooker/internal/logger"
)
// hoursPerDay converts a RetentionDays count into hours for cutoff
// computation.
const hoursPerDay = 24
// RetentionReaperParams holds the fx dependencies for the
// RetentionReaper.
type RetentionReaperParams struct {
fx.In
Config *config.Config
Database *Database
DBManager *WebhookDBManager
Logger *logger.Logger
}
// RetentionReaper periodically deletes expired events (and their
// dependent deliveries and delivery results) from each per-webhook
// database, enforcing every webhook's RetentionDays. Rows are removed
// permanently so that per-webhook SQLite files do not grow without
// bound.
type RetentionReaper struct {
db *Database
dbManager *WebhookDBManager
log *slog.Logger
interval time.Duration
cancel context.CancelFunc
wg sync.WaitGroup
}
// NewRetentionReaper creates the retention reaper and registers its
// fx lifecycle hooks. The background sweep loop starts on OnStart and
// stops cleanly on OnStop via context cancellation.
func NewRetentionReaper(
lc fx.Lifecycle,
params RetentionReaperParams,
) *RetentionReaper {
r := &RetentionReaper{
db: params.Database,
dbManager: params.DBManager,
log: params.Logger.Get(),
interval: params.Config.RetentionSweepInterval,
}
lc.Append(fx.Hook{
OnStart: func(ctx context.Context) error {
r.start(ctx)
return nil
},
OnStop: func(_ context.Context) error {
r.stop()
return nil
},
})
return r
}
func (r *RetentionReaper) start(ctx context.Context) {
ctx, cancel := context.WithCancel(ctx)
r.cancel = cancel
r.wg.Add(1)
go r.run(ctx)
r.log.Info(
"retention reaper started",
"interval", r.interval.String(),
)
}
func (r *RetentionReaper) stop() {
r.log.Info("retention reaper stopping")
if r.cancel != nil {
r.cancel()
}
r.wg.Wait()
r.log.Info("retention reaper stopped")
}
func (r *RetentionReaper) run(ctx context.Context) {
defer r.wg.Done()
ticker := time.NewTicker(r.interval)
defer ticker.Stop()
for {
select {
case <-ctx.Done():
return
case <-ticker.C:
r.sweep(ctx)
}
}
}
// sweep lists every webhook from the main database and reaps expired
// rows from each per-webhook database whose RetentionDays is positive.
func (r *RetentionReaper) sweep(ctx context.Context) {
var webhooks []Webhook
err := r.db.DB().
Model(&Webhook{}).
Find(&webhooks).Error
if err != nil {
r.log.Error(
"retention sweep: failed to list webhooks",
"error", err,
)
return
}
for i := range webhooks {
select {
case <-ctx.Done():
return
default:
}
wh := webhooks[i]
// RetentionDays of zero or less means retain forever.
if wh.RetentionDays <= 0 {
continue
}
// Nothing to reap if the per-webhook database has never
// been created.
if !r.dbManager.DBExists(wh.ID) {
continue
}
r.reapWebhook(wh.ID, wh.RetentionDays)
}
}
// reapWebhook removes every expired event (and its dependents) from a
// single webhook's database.
func (r *RetentionReaper) reapWebhook(
webhookID string,
retentionDays int,
) {
db, err := r.dbManager.GetDB(webhookID)
if err != nil {
r.log.Error(
"retention sweep: failed to open webhook database",
"webhook_id", webhookID,
"error", err,
)
return
}
cutoff := time.Now().Add(
-time.Duration(retentionDays*hoursPerDay) * time.Hour,
)
deleted, err := reapExpired(db, cutoff)
if err != nil {
r.log.Error(
"retention sweep: failed to reap expired events",
"webhook_id", webhookID,
"error", err,
)
return
}
if deleted > 0 {
r.log.Info(
"retention sweep: reaped expired events",
"webhook_id", webhookID,
"retention_days", retentionDays,
"events_deleted", deleted,
)
}
}
// reapExpired hard-deletes, in foreign-key-safe order, the delivery
// results, deliveries, and events associated with events older than
// cutoff. Deletes are unscoped so rows are physically removed rather
// than soft-deleted, reclaiming disk. It returns the number of events
// deleted.
func reapExpired(db *gorm.DB, cutoff time.Time) (int64, error) {
// Fresh subqueries are built per statement to avoid reusing a
// mutated builder across executions.
expiredEventIDs := func() *gorm.DB {
return db.Model(&Event{}).
Select("id").
Where("created_at < ?", cutoff)
}
expiredDeliveryIDs := func() *gorm.DB {
return db.Model(&Delivery{}).
Select("id").
Where("event_id IN (?)", expiredEventIDs())
}
// 1. Delivery results whose delivery belongs to an expired event.
res := db.Unscoped().
Where("delivery_id IN (?)", expiredDeliveryIDs()).
Delete(&DeliveryResult{})
if res.Error != nil {
return 0, fmt.Errorf(
"deleting expired delivery results: %w",
res.Error,
)
}
// 2. Deliveries belonging to an expired event.
del := db.Unscoped().
Where("event_id IN (?)", expiredEventIDs()).
Delete(&Delivery{})
if del.Error != nil {
return 0, fmt.Errorf(
"deleting expired deliveries: %w",
del.Error,
)
}
// 3. The expired events themselves.
ev := db.Unscoped().
Where("created_at < ?", cutoff).
Delete(&Event{})
if ev.Error != nil {
return 0, fmt.Errorf(
"deleting expired events: %w",
ev.Error,
)
}
return ev.RowsAffected, nil
}