All checks were successful
check / check (push) Successful in 2m43s
RetentionDays carried gorm:"default:30", so GORM substituted 30 for a zero value while building the insert. A webhook could therefore never be configured to keep its events indefinitely: the reaper's retain-forever branch existed but was unreachable from the normal create and edit flows. Introduce database.RetentionForeverDays = 365 * 1000 as the sentinel for "retain forever" and a Webhook.BeforeSave hook that rewrites any non-positive RetentionDays to it. The rewrite has to live in the hook rather than at the call sites: GORM applies the column default while converting the model to insert values, which happens after BeforeSave, so anything later loses that race. Putting it on the model also means a future call site, such as the planned REST API, cannot bypass it. The reaper now skips a webhook when Webhook.RetainsForever reports true, which recognises the sentinel and keeps honouring the old <= 0 values for rows written before it existed. Without this the sentinel, being positive, would have produced a cutoff a thousand years in the past and a DELETE matching nothing on every sweep. Bound the finite retention range, which was previously unbounded on the server. The reaper computes its cutoff as a time.Duration, an int64 nanosecond count, so a day count above 106751 overflows, wraps the span negative, and moves the cutoff into the far future — where it matches every row and the sweep deletes every event, delivery, and delivery result the webhook has, including ones created seconds ago. Nothing rejected such a value: parseRetention accepted any v > 0, and max="365" was a client-side attribute a direct POST ignored, so the wipe was already reachable on main and removing that attribute would have made it reachable by ordinary use. The bound is database.MaxFiniteRetentionDays, derived from the arithmetic itself as math.MaxInt64 / time.Hour / hoursPerDay rather than picked as a round number, and a finite value above it is now a 400 that names the ceiling. retentionCutoff additionally clamps the day count it is given and reports whether any cutoff applies at all, so a row written by an older version, a migration, or a future call site cannot reach the overflow either. A value at or above the retain-forever sentinel stays accepted, because that is what the edit form pre-fills for a retain-forever webhook. Form handling is shared by create and edit through parseRetentionDays so the two cannot drift: an empty field keeps the previous behaviour (default on create, unchanged on edit), 0 is honoured, and an unparseable, negative, or out-of-range value is a 400 that re-renders the form rather than a silently substituted default. The two rejection reasons are distinct sentinel errors so the message can name the ceiling, and the create form now carries the submitted name and description back into the re-rendered inputs, which the edit form already did. The retention inputs drop max="365". That cap was not cosmetic: the edit form pre-fills the stored value, so a retain-forever webhook rendered 365000 into an input capped at 365 and browser validation would have blocked saving any edit to it. min becomes 0 with a hint explaining what 0 does, and the list and detail views render a RetentionLabel of "forever" instead of a raw day count. All three Webhook methods take pointer receivers, so there is no receiver mix and no lint suppression: BeforeSave must take a pointer to mutate the record, and the handlers hand templates a *Webhook because html/template cannot call a pointer method on a value held in a map. The 30-day default is consolidated into database.DefaultRetentionDays, referenced from the handler and from the create form's pre-filled value, with a test asserting it agrees with the struct tag that cannot reference it.
291 lines
6.8 KiB
Go
291 lines
6.8 KiB
Go
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 that has a finite retention
|
|
// policy. Webhooks set to retain forever are skipped entirely.
|
|
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]
|
|
|
|
// Skip retain-forever webhooks before building any query.
|
|
// RetainsForever covers both the RetentionForeverDays
|
|
// sentinel and the non-positive values that predate it: the
|
|
// sentinel is a positive number, so without this the reaper
|
|
// would compute a cutoff a thousand years in the past and
|
|
// issue a DELETE matching nothing on every single sweep.
|
|
if wh.RetainsForever() {
|
|
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, ok := retentionCutoff(time.Now(), retentionDays)
|
|
if !ok {
|
|
return
|
|
}
|
|
|
|
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,
|
|
)
|
|
}
|
|
}
|
|
|
|
// retentionCutoff returns the timestamp before which a webhook's
|
|
// events have expired, and whether any cutoff applies at all. It
|
|
// reports false for a retain-forever policy, so no DELETE is issued.
|
|
//
|
|
// The day count is clamped to MaxFiniteRetentionDays first. This is
|
|
// defense in depth rather than decoration: a time.Duration is an int64
|
|
// nanosecond count, so an unclamped multiplication overflows above
|
|
// that ceiling and wraps the span negative. Subtracting a negative
|
|
// span moves the cutoff into the far future, where it matches every
|
|
// row in the database: the sweep then deletes every event, delivery,
|
|
// and delivery result, including ones created seconds ago. Rejecting
|
|
// out-of-range input at the form is the primary guard; saturating here
|
|
// means an old row, a migration, or a future call site cannot turn a
|
|
// too-large retention into total data loss.
|
|
func retentionCutoff(
|
|
now time.Time,
|
|
retentionDays int,
|
|
) (time.Time, bool) {
|
|
if retainsForever(retentionDays) {
|
|
return time.Time{}, false
|
|
}
|
|
|
|
if retentionDays > MaxFiniteRetentionDays {
|
|
retentionDays = MaxFiniteRetentionDays
|
|
}
|
|
|
|
return now.Add(
|
|
-time.Duration(retentionDays*hoursPerDay) * time.Hour,
|
|
), true
|
|
}
|
|
|
|
// 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
|
|
}
|