Files
webhooker/internal/database/webhook_db_manager.go
clawbot 9a70afb8b7
All checks were successful
check / check (push) Successful in 3m3s
Make SQLite durable under concurrent readers and stop re-delivering stranded webhooks (closes #256)
An operator running `sqlite3 <db> .dump` against their own per-webhook
database wedged it: inbound webhooks rejected with HTTP 500, delivered
webhooks stranded at `pending`, and every one of them POSTed a second
time on the next restart while the event log recorded a single attempt.

Durability. Every SQLite file — main, per-webhook, and archive — now
opens through one path, `internal/database/sqlite_open.go`, in WAL
journal mode with a 10-second busy timeout, `BEGIN IMMEDIATE`
transactions, and a bounded connection pool. WAL is what stops a reader
blocking writers at all. `_txlock=immediate` is what stops a `COMMIT`
failing while its transaction stays open on a pooled connection, which
is how four `database is locked` errors became 593 `cannot start a
transaction within a transaction`. `cache=shared` is gone, because
under it an in-process conflict is SQLITE_LOCKED, which the busy
handler does not retry. The busy timeout is applied before
journal_mode: the driver runs DSN pragmas in order on every new
connection, and `PRAGMA journal_mode` takes a lock, so the reverse
order leaves the one pragma that can block uncovered by the handler
meant to cover it.

Eligibility. `internal/delivery/inflight.go` holds the set of
deliveries the engine owns — taken when a task is queued, when a
target schedules a retry, and by every recovery path before it
re-dispatches; dropped when the worker that ran the task returns.
Recovery and both sweep arms re-dispatch only what the set does not
hold. Nothing decides that from a row's age: a delivery waiting in a
10000-deep channel is arbitrarily old and perfectly healthy, and
reasoning from age re-sends it. `takeForRedispatch` is the single gate
every re-dispatch goes through — ownership first, then a conditional
update confirming the row is still in the status the batch read.

Bookkeeping. `recordResult` and `updateDeliveryStatus` return their
errors instead of logging and dropping them, and a caller whose
bookkeeping write failed writes nothing at all: the delivery keeps
whichever non-terminal status it already held, and the sweeps recover
it. Every recovery path — pending and retrying alike — first settles
any delivery that already holds a successful `DeliveryResult` rather
than sending it again. Recovery continues each delivery's own attempt
numbering instead of restarting at 1. The sweep gains a
`pending`-with-age-bound arm, so a stranded delivery no longer waits
for a restart.

Docs. WAL produces `-wal`/`-shm` sidecars, so the backup and restore
procedures in README.md are corrected against measurement: both
documented procedures were re-run against a live instance, a `-wal`
left by a crash carries data the `.db` alone does not, and an archive
file normally holds its rows in a `-wal` rather than in the `.db`.
2026-08-24 01:02:01 +00:00

303 lines
6.2 KiB
Go

package database
import (
"context"
"errors"
"fmt"
"log/slog"
"os"
"path/filepath"
"sync"
"go.uber.org/fx"
"gorm.io/driver/sqlite"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/config"
"sneak.berlin/go/webhooker/internal/gormlog"
"sneak.berlin/go/webhooker/internal/logger"
)
// WebhookDBManagerParams holds the fx dependencies for
// WebhookDBManager.
type WebhookDBManagerParams struct {
fx.In
Config *config.Config
Logger *logger.Logger
}
// errInvalidCachedDBType indicates a type assertion failure
// when retrieving a cached database connection.
var errInvalidCachedDBType = errors.New(
"invalid cached database type",
)
// WebhookDBManager manages per-webhook SQLite database files
// for event storage. Each webhook gets its own dedicated
// database containing Events, Deliveries, and DeliveryResults.
// Database connections are opened lazily and cached.
type WebhookDBManager struct {
dataDir string
dbs sync.Map // map[webhookID]*gorm.DB
log *slog.Logger
}
// NewWebhookDBManager creates a new WebhookDBManager and
// registers lifecycle hooks.
func NewWebhookDBManager(
lc fx.Lifecycle,
params WebhookDBManagerParams,
) (*WebhookDBManager, error) {
m := &WebhookDBManager{
dataDir: params.Config.DataDir,
log: params.Logger.Get(),
}
// Create data directory if it doesn't exist
err := os.MkdirAll(m.dataDir, dataDirPerm)
if err != nil {
return nil, fmt.Errorf(
"creating data directory %s: %w",
m.dataDir,
err,
)
}
lc.Append(fx.Hook{
OnStop: func(_ context.Context) error {
return m.CloseAll()
},
})
m.log.Info(
"webhook database manager initialized",
"data_dir", m.dataDir,
)
return m, nil
}
// GetDB returns the database connection for a webhook,
// creating the database file lazily if it doesn't exist.
func (m *WebhookDBManager) GetDB(
webhookID string,
) (*gorm.DB, error) {
// Fast path: already open
if val, ok := m.dbs.Load(webhookID); ok {
cachedDB, castOK := val.(*gorm.DB)
if !castOK {
return nil, fmt.Errorf(
"%w for webhook %s",
errInvalidCachedDBType,
webhookID,
)
}
return cachedDB, nil
}
// Slow path: open/create the database
db, err := m.openDB(webhookID)
if err != nil {
return nil, err
}
// Store it; if another goroutine beat us, close ours
actual, loaded := m.dbs.LoadOrStore(webhookID, db)
if loaded {
// Another goroutine created it first; close our duplicate
sqlDB, closeErr := db.DB()
if closeErr == nil {
_ = sqlDB.Close()
}
existingDB, castOK := actual.(*gorm.DB)
if !castOK {
return nil, fmt.Errorf(
"%w for webhook %s",
errInvalidCachedDBType,
webhookID,
)
}
return existingDB, nil
}
return db, nil
}
// CreateDB explicitly creates a new per-webhook database file
// and runs migrations.
func (m *WebhookDBManager) CreateDB(
webhookID string,
) error {
_, err := m.GetDB(webhookID)
return err
}
// DBExists checks if a per-webhook database file exists on
// disk.
func (m *WebhookDBManager) DBExists(
webhookID string,
) bool {
_, err := os.Stat(m.dbPath(webhookID))
return err == nil
}
// DeleteDB closes the connection and deletes the database file
// for a webhook. The file is permanently removed.
func (m *WebhookDBManager) DeleteDB(
webhookID string,
) error {
// Close and remove from cache
if val, ok := m.dbs.LoadAndDelete(webhookID); ok {
if gormDB, castOK := val.(*gorm.DB); castOK {
sqlDB, err := gormDB.DB()
if err == nil {
_ = sqlDB.Close()
}
}
}
// Delete the main DB file and WAL/SHM files
path := m.dbPath(webhookID)
for _, suffix := range []string{"", "-wal", "-shm"} {
err := os.Remove(path + suffix)
if err != nil && !os.IsNotExist(err) {
return fmt.Errorf(
"deleting webhook database file %s%s: %w",
path, suffix, err,
)
}
}
m.log.Info(
"deleted per-webhook database",
"webhook_id", webhookID,
)
return nil
}
// CloseAll closes all open per-webhook database connections.
// Called during application shutdown.
func (m *WebhookDBManager) CloseAll() error {
var lastErr error
m.dbs.Range(func(key, value any) bool {
if gormDB, castOK := value.(*gorm.DB); castOK {
sqlDB, err := gormDB.DB()
if err == nil {
closeErr := sqlDB.Close()
if closeErr != nil {
lastErr = closeErr
m.log.Error(
"failed to close webhook database",
"webhook_id", key,
"error", closeErr,
)
}
}
}
m.dbs.Delete(key)
return true
})
return lastErr
}
// DBPath returns the filesystem path for a webhook's database
// file.
func (m *WebhookDBManager) DBPath(
webhookID string,
) string {
return m.dbPath(webhookID)
}
func (m *WebhookDBManager) dbPath(
webhookID string,
) string {
return filepath.Join(
m.dataDir,
fmt.Sprintf("events-%s.db", webhookID),
)
}
// openDB opens (or creates) a per-webhook SQLite database and
// runs migrations.
func (m *WebhookDBManager) openDB(
webhookID string,
) (*gorm.DB, error) {
path := m.dbPath(webhookID)
// See sqlite_open.go: WAL, a busy timeout, immediate-transaction
// locking, and a bounded pool, all of which this file needs most —
// it is the one every delivery worker writes to concurrently.
sqlDB, err := OpenSQLite(path, SQLiteModeCreate)
if err != nil {
return nil, fmt.Errorf(
"opening webhook database %s: %w",
webhookID, err,
)
}
db, err := gorm.Open(sqlite.Dialector{
Conn: sqlDB,
}, &gorm.Config{
// Never leave this at GORM's default. See internal/gormlog.
Logger: gormlog.New(m.log),
})
if err != nil {
_ = sqlDB.Close()
return nil, fmt.Errorf(
"connecting to webhook database %s: %w",
webhookID, err,
)
}
// Keep main-database rows out of this file. See
// event_db_isolation.go.
err = omitAssociations(db)
if err != nil {
_ = sqlDB.Close()
return nil, fmt.Errorf(
"guarding webhook database %s: %w",
webhookID, err,
)
}
err = purgeTargetRows(db, m.log, webhookID)
if err != nil {
_ = sqlDB.Close()
return nil, err
}
// Run migrations for event-tier models only
err = db.AutoMigrate(
&Event{}, &Delivery{}, &DeliveryResult{},
)
if err != nil {
_ = sqlDB.Close()
return nil, fmt.Errorf(
"migrating webhook database %s: %w",
webhookID, err,
)
}
m.log.Info(
"opened per-webhook database",
"webhook_id", webhookID,
"path", path,
)
return db, nil
}