Name each database target's archive for its webhook and target (closes #376)
check / check (push) Waiting to run

Each database target now has its own archive file,
archive-WEBHOOKNAME-TARGETNAME-TARGETID.db, instead of one
archive-WEBHOOKID.db per webhook. delivery.ArchiveFileName builds the
name.

A change of webhook or target name renames its archive files under the
archive writer's lock, before the new name is saved, and back again if
the save fails. Webhook edits, target edits and target creation run one
at a time, so no two of them interleave. A rename never replaces a
file, and one that fails part way moves back what it moved. Deleting a
target evicts only that target's writer. Archive files are never
deleted, and nothing looks for files under the old name.

Model: opus-5-5
This commit is contained in:
2026-10-02 10:47:27 +00:00
committed by sneak
parent b14b27b78b
commit 71762d72d9
21 changed files with 1825 additions and 663 deletions
+200 -93
View File
@@ -4,6 +4,7 @@ import (
"context"
"fmt"
"path/filepath"
"strings"
"sync"
"time"
@@ -11,22 +12,75 @@ import (
"sneak.berlin/go/webhooker/internal/database"
)
// databaseTarget is a no-retry target that archives the
// full inbound event into a per-webhook archive SQLite file,
// separate from the per-webhook event database. The event is
// already persisted in the per-webhook event DB by the time
// delivery runs; the database target additionally writes a
// durable long-term copy into archive-{webhookID}.db and then
// records a single attempt whose outcome reflects whether the
// archive write succeeded. See archiveWriter for the
// close/reopen, auto-recreate, and expiry semantics.
// archiveNameMaxLen is how many characters of a webhook or target
// name an archive file name keeps.
const archiveNameMaxLen = 40
// databaseTarget is a no-retry target that archives the full
// inbound event into the target's own archive SQLite file, separate
// from the per-webhook event database. The event is already
// persisted in the per-webhook event DB by the time delivery runs;
// the database target additionally writes a durable long-term copy
// into the file ArchiveFileName names and then records a single
// attempt whose outcome reflects whether the archive write
// succeeded. See archiveWriter for the close/reopen, auto-recreate,
// and expiry semantics.
type databaseTarget struct {
eng *Engine
// writers holds one archive writer per database target, keyed
// by target ID.
mu sync.Mutex
writers map[string]*archiveWriter
}
// ArchiveFileName returns the file name of a database target's
// archive: archive-WEBHOOKNAME-TARGETNAME-TARGETID.db, with both
// names passed through archiveNamePart. The target ID keeps the
// name unique when two targets' names come out the same.
func ArchiveFileName(webhookName, targetName, targetID string) string {
return "archive-" + archiveNamePart(webhookName) + "-" +
archiveNamePart(targetName) + "-" + targetID + ".db"
}
// archiveNamePart makes a webhook or target name safe to put in a
// file name. It is lowercased; ASCII letters and digits are kept,
// every other run of characters becomes a single "-", and no "-" is
// left at either end. It is cut to archiveNameMaxLen characters, and
// a name with nothing left is "unnamed".
func archiveNamePart(name string) string {
var b strings.Builder
dash := false
for _, r := range strings.ToLower(name) {
if (r < 'a' || r > 'z') && (r < '0' || r > '9') {
dash = b.Len() > 0
continue
}
if dash {
b.WriteByte('-')
dash = false
}
b.WriteRune(r)
}
part := b.String()
if len(part) > archiveNameMaxLen {
part = strings.TrimRight(part[:archiveNameMaxLen], "-")
}
if part == "" {
return "unnamed"
}
return part
}
// Deliver implements Target. It archives the event, then
// records one successful attempt and marks the delivery
// delivered. An archiving error fails the delivery: the
@@ -92,7 +146,7 @@ func (t *databaseTarget) Deliver(
)
}
// archive writes the full event as a row into the webhook's
// archive writes the full event as a row into the target's
// archive database, honouring the optional per-target expiry
// parsed from the target config JSON.
func (t *databaseTarget) archive(d *database.Delivery) error {
@@ -106,7 +160,7 @@ func (t *databaseTarget) archive(d *database.Delivery) error {
return err
}
w, err := t.writerFor(webhookID)
w, err := t.writerFor(d.TargetID)
if err != nil {
return err
}
@@ -124,30 +178,31 @@ func (t *databaseTarget) archive(d *database.Delivery) error {
return w.write(row, expiry)
}
// writerFor returns the archiveWriter for a webhook, creating
// and caching it on first use. Each webhook has one writer so
// its close/reopen debounce state is shared across concurrent
// deliveries. The archive file lives beside the per-webhook
// event database in the data directory.
// writerFor returns the archive writer for a database target,
// creating and caching it on first use. Each target has one writer
// so its close/reopen debounce state is shared across concurrent
// deliveries, and so a rename and the idle sweep take the same lock
// as its writes.
func (t *databaseTarget) writerFor(
webhookID string,
targetID string,
) (*archiveWriter, error) {
path, err := t.archivePath(webhookID)
if err != nil {
return nil, err
}
t.mu.Lock()
defer t.mu.Unlock()
if t.writers == nil {
t.writers = make(map[string]*archiveWriter)
}
w, ok := t.writers[webhookID]
w, ok := t.writers[targetID]
if !ok {
w = newArchiveWriter(path, t.eng.log)
t.writers[webhookID] = w
var err error
w, err = t.newWriter(targetID)
if err != nil {
return nil, err
}
if t.writers == nil {
t.writers = make(map[string]*archiveWriter)
}
t.writers[targetID] = w
}
// A delivery claims the entry: even if the idle sweep created
@@ -159,40 +214,39 @@ func (t *databaseTarget) writerFor(
}
// sweepWriterFor returns the archive writer the idle sweep should
// prune a webhook through, together with whether the sweep itself
// created the registry entry.
// prune a target's archive through, together with whether the sweep
// itself created the registry entry.
//
// The sweep must route its prune through the registered writer so
// the writer's mutex orders it against concurrent writes, but it
// must never leave a registry entry behind: a sweep that ran
// concurrently with the webhook's deletion would otherwise
// concurrently with the target's deletion would otherwise
// re-create an entry that nothing will ever evict again, which is
// exactly the leak eviction exists to prevent. An entry the sweep
// creates is therefore marked sweep-owned and handed back to
// releaseSweepWriter when the sweep is done.
func (t *databaseTarget) sweepWriterFor(
webhookID string,
targetID string,
) (*archiveWriter, bool, error) {
path, err := t.archivePath(webhookID)
t.mu.Lock()
defer t.mu.Unlock()
w, ok := t.writers[targetID]
if ok {
return w, false, nil
}
w, err := t.newWriter(targetID)
if err != nil {
return nil, false, err
}
t.mu.Lock()
defer t.mu.Unlock()
if t.writers == nil {
t.writers = make(map[string]*archiveWriter)
}
w, ok := t.writers[webhookID]
if ok {
return w, false, nil
}
w = newArchiveWriter(path, t.eng.log)
w.sweepOwned = true
t.writers[webhookID] = w
t.writers[targetID] = w
return w, true, nil
}
@@ -209,57 +263,95 @@ func (t *databaseTarget) sweepWriterFor(
// delivery that adopted the writer keeps a registered, evictable
// one.
func (t *databaseTarget) releaseSweepWriter(
webhookID string, w *archiveWriter,
targetID string, w *archiveWriter,
) {
t.mu.Lock()
defer t.mu.Unlock()
cur, ok := t.writers[webhookID]
cur, ok := t.writers[targetID]
if !ok || cur != w || !cur.sweepOwned {
return
}
delete(t.writers, webhookID)
delete(t.writers, targetID)
}
// archivePath returns the archive file path for a webhook: it
// lives beside the per-webhook event database in the data
// directory. It does not touch the filesystem.
func (t *databaseTarget) archivePath(
webhookID string,
) (string, error) {
// newWriter builds the writer for a database target's archive. The
// file lives beside the webhook's event database in the data
// directory and is named for the webhook and the target as the main
// database has them now; from then on only rename changes the name
// the writer uses. It does not touch the archive file.
func (t *databaseTarget) newWriter(
targetID string,
) (*archiveWriter, error) {
if t.eng.dbManager == nil {
return "", errArchiveNoDataDir
return nil, errArchiveNoDataDir
}
dir := filepath.Dir(t.eng.dbManager.DBPath(webhookID))
var target database.Target
return filepath.Join(
dir, fmt.Sprintf("archive-%s.db", webhookID),
), nil
err := t.eng.database.DB().
Preload("Webhook").
First(&target, "id = ?", targetID).Error
if err != nil {
return nil, fmt.Errorf(
"loading database target %s: %w", targetID, err,
)
}
dir := filepath.Dir(t.eng.dbManager.DBPath(target.WebhookID))
name := ArchiveFileName(
target.Webhook.Name, target.Name, target.ID,
)
w := newArchiveWriter(filepath.Join(dir, name), t.eng.log)
w.webhookID = target.WebhookID
return w, nil
}
// evict drops a webhook's archive writer from the registry and
// closes its handle, so a deleted webhook does not leave a
// writer (and an open archive handle within its debounce
// window) alive for the process lifetime.
// rename moves a database target's archive file to the name for
// webhookName and targetName. It goes through the target's writer,
// so the move holds the lock that writes and the idle sweep take,
// and later writes use the new name.
//
// The writer is created if there is none, and it stays cached. The
// handlers rename before they save the new name, so until the save
// the main database still has the old one; a delivery in that window
// must find this writer rather than build one from the old name.
func (t *databaseTarget) rename(
targetID, webhookName, targetName string,
) error {
w, err := t.writerFor(targetID)
if err != nil {
return err
}
return w.rename(ArchiveFileName(webhookName, targetName, targetID))
}
// evict drops a database target's archive writer from the registry
// and closes its handle, so a deleted target does not leave a
// writer (and an open archive handle within its debounce window)
// alive for the process lifetime.
//
// The map entry is removed under the registry lock, which is
// then released before the handle is closed under the writer's
// own lock: that ordering keeps the registry available to other
// webhooks while an in-flight write on this one drains, and
// targets while an in-flight write on this one drains, and
// closing under the writer's lock means eviction can never race
// a write.
//
// Eviction is idempotent and silent for a webhook with no
// writer, which is the common case: a webhook with no database
// target never creates one. It never deletes the archive file.
func (t *databaseTarget) evict(webhookID string) {
// Eviction is idempotent and silent for a target with no writer,
// which is the common case: only a database target that has
// received an event or been renamed has one. It never deletes the
// archive file.
func (t *databaseTarget) evict(targetID string) {
t.mu.Lock()
w, ok := t.writers[webhookID]
w, ok := t.writers[targetID]
if ok {
delete(t.writers, webhookID)
delete(t.writers, targetID)
}
t.mu.Unlock()
@@ -272,13 +364,41 @@ func (t *databaseTarget) evict(webhookID string) {
t.eng.log.Info(
"evicted archive writer",
"webhook_id", webhookID,
"target_id", targetID,
"path", w.path,
)
}
// evictWebhook evicts, exactly as evict does, the writer of every
// database target of a webhook.
func (t *databaseTarget) evictWebhook(webhookID string) {
t.mu.Lock()
var gone []*archiveWriter
for targetID, w := range t.writers {
if w.webhookID == webhookID {
delete(t.writers, targetID)
gone = append(gone, w)
}
}
t.mu.Unlock()
for _, w := range gone {
w.evict()
t.eng.log.Info(
"evicted archive writer",
"webhook_id", webhookID,
"path", w.path,
)
}
}
// evictAll evicts every cached archive writer, exactly as evict
// does for one webhook. The engine calls it at shutdown, once its
// does for one target. The engine calls it at shutdown, once its
// workers have returned. Closing the last handle on an archive
// moves the contents of its -wal into the .db and removes the
// -wal, so a clean stop leaves each archive as a single file.
@@ -295,38 +415,25 @@ func (t *databaseTarget) evictAll() {
}
}
// sweepWebhook prunes one webhook's archive of rows older than
// expiry, without requiring a write. It returns nil (nothing to
// do) when the archive file does not exist, so a sweep never
// creates an archive for a webhook that has a database target
// but has never received an event.
// sweepArchive prunes one database target's archive of rows older
// than expiry, without requiring a write. A missing archive file is
// left missing (see sweepExpired), so a sweep never creates an
// archive for a target that has never received an event.
//
// It also never leaves a registry entry behind: an entry it had
// to create to reach the writer's mutex is released again once
// the prune is done, so a sweep racing a webhook deletion cannot
// the prune is done, so a sweep racing a target deletion cannot
// resurrect the writer the eviction just dropped.
func (t *databaseTarget) sweepWebhook(
webhookID string, expiry time.Duration,
func (t *databaseTarget) sweepArchive(
targetID string, expiry time.Duration,
) error {
path, err := t.archivePath(webhookID)
if err != nil {
return err
}
// Check before taking a writer at all: a webhook whose
// archive has never been created gets no writer, no handle,
// and no file.
if !fileExists(path) {
return nil
}
w, created, err := t.sweepWriterFor(webhookID)
w, created, err := t.sweepWriterFor(targetID)
if err != nil {
return err
}
if created {
defer t.releaseSweepWriter(webhookID, w)
defer t.releaseSweepWriter(targetID, w)
}
return w.sweepExpired(expiry)