Evict archive writers on deletion and sweep idle archives (closes #89)
All checks were successful
check / check (push) Successful in 3m10s

The per-webhook archiveWriter registry in the database delivery target
was never evicted, so a deleted webhook's writer -- and any archive
file handle open within its debounce window -- lingered for the process
lifetime. Separately, expiry pruning ran only when an archive was
(re)opened, and reopens only happen on writes, so an archive belonging
to a webhook that stopped receiving events kept its expired rows
forever.

Eviction: a new one-method delivery.WebhookEvictor interface (kept
separate from Notifier: archiving lifecycle is not notification) is
implemented by the Engine and injected into the handlers. Deleting a
webhook, or deleting its last database target, drops the writer from
the registry and closes its handle under the writer's own mutex, so
eviction can never race an in-flight write. An evicted writer refuses
further writes rather than reopening a file nothing holds. The archive
file is deliberately left on disk: it is long-term storage an operator
may want to keep or move away, and destroying it as a side effect of
deleting a webhook would be unrecoverable.

Idle sweep: a new ArchiveSweeper, modelled on the event RetentionReaper
(fx lifecycle hooks, cancellable context, WaitGroup, ticker loop),
prunes archives whose database target declares a positive expiry. It
reuses the existing RETENTION_SWEEP_INTERVAL rather than adding a
config key. It never creates an archive -- a missing file is skipped,
and the reopen uses SQLite mode=rw so the file cannot be conjured even
if it disappears mid-sweep -- routes the prune through the per-webhook
writer so its mutex orders the sweep against concurrent writes, and
leaves the archive closed so the move-the-file-away workflow keeps
working. A failure for one webhook is logged and the sweep continues.
Archives with no expiry or the expiry "never" are untouched.
This commit is contained in:
clawbot
2026-08-09 02:25:33 +00:00
parent 4f5ecb18e5
commit 190cabe0f2
15 changed files with 1514 additions and 11 deletions

View File

@@ -51,6 +51,7 @@ type HandlersParams struct {
Healthcheck *healthcheck.Healthcheck
Session *session.Session
Notifier delivery.Notifier
Evictor delivery.WebhookEvictor
}
// Handlers provides HTTP handler methods for all application
@@ -63,6 +64,7 @@ type Handlers struct {
dbMgr *database.WebhookDBManager
session *session.Session
notifier delivery.Notifier
evictor delivery.WebhookEvictor
templates map[string]*template.Template
}
@@ -97,6 +99,7 @@ func New(
s.dbMgr = params.WebhookDBMgr
s.session = params.Session
s.notifier = params.Notifier
s.evictor = params.Evictor
// Parse all page templates once at startup
s.templates = map[string]*template.Template{

View File

@@ -4,6 +4,7 @@ import (
"context"
"net/http"
"net/http/httptest"
"sync"
"testing"
"github.com/stretchr/testify/assert"
@@ -24,6 +25,32 @@ type noopNotifier struct{}
func (n *noopNotifier) Notify([]delivery.Task) {}
// recordingEvictor is a delivery.WebhookEvictor that records
// the webhook ids it was asked to evict, so a test can prove
// that a deletion path reached the delivery engine.
type recordingEvictor struct {
mu sync.Mutex
evicted []string
}
func (r *recordingEvictor) EvictWebhook(webhookID string) {
r.mu.Lock()
defer r.mu.Unlock()
r.evicted = append(r.evicted, webhookID)
}
// Evicted returns a copy of the recorded webhook ids.
func (r *recordingEvictor) Evicted() []string {
r.mu.Lock()
defer r.mu.Unlock()
out := make([]string, len(r.evicted))
copy(out, r.evicted)
return out
}
func newTestApp(
t *testing.T,
targets ...any,
@@ -47,6 +74,12 @@ func newTestApp(
func() delivery.Notifier {
return &noopNotifier{}
},
func() *recordingEvictor {
return &recordingEvictor{}
},
func(r *recordingEvictor) delivery.WebhookEvictor {
return r
},
handlers.New,
),
fx.Populate(targets...),

View File

@@ -0,0 +1,305 @@
package handlers_test
import (
"context"
"net/http"
"net/http/httptest"
"os"
"path/filepath"
"testing"
"github.com/go-chi/chi"
"github.com/stretchr/testify/assert"
"github.com/stretchr/testify/require"
"gorm.io/gorm/clause"
"sneak.berlin/go/webhooker/internal/database"
"sneak.berlin/go/webhooker/internal/handlers"
"sneak.berlin/go/webhooker/internal/session"
)
const (
deleteTestUserID = "test-user-id"
deleteTestUsername = "testuser"
// paramSourceID and paramTargetID are the chi URL parameter
// names the deletion handlers read.
paramSourceID = "sourceID"
paramTargetID = "targetID"
)
// seedWebhook inserts a webhook owned by the test user and
// returns it.
func seedWebhook(
t *testing.T,
db *database.Database,
) *database.Webhook {
t.Helper()
wh := &database.Webhook{
UserID: deleteTestUserID,
Name: "delete-me",
}
require.NoError(
t,
db.DB().Omit(clause.Associations).Create(wh).Error,
)
return wh
}
// seedTarget inserts a target of the given type for a webhook
// and returns it.
func seedTarget(
t *testing.T,
db *database.Database,
webhookID string,
targetType database.TargetType,
) *database.Target {
t.Helper()
tgt := &database.Target{
WebhookID: webhookID,
Name: "t-" + string(targetType),
Type: targetType,
Active: true,
}
require.NoError(
t,
db.DB().Omit(clause.Associations).Create(tgt).Error,
)
return tgt
}
// archivePathFor returns the archive database path the
// delivery engine would use for a webhook: beside the webhook's
// event database in the data directory.
func archivePathFor(
t *testing.T,
mgr *database.WebhookDBManager,
webhookID string,
) string {
t.Helper()
return filepath.Join(
filepath.Dir(mgr.DBPath(webhookID)),
"archive-"+webhookID+".db",
)
}
// writeArchivePlaceholder creates a stand-in archive file so a
// test can assert the file survives webhook deletion.
func writeArchivePlaceholder(path string) error {
return os.WriteFile(path, []byte("archive"), 0o600)
}
// postRequest builds an authenticated POST request carrying the
// given chi URL parameters.
func postRequest(
path string,
cookies []*http.Cookie,
params map[string]string,
) *http.Request {
req := httptest.NewRequestWithContext(
context.Background(), http.MethodPost, path, nil,
)
for _, c := range cookies {
req.AddCookie(c)
}
rctx := chi.NewRouteContext()
for k, v := range params {
rctx.URLParams.Add(k, v)
}
return req.WithContext(
context.WithValue(req.Context(), chi.RouteCtxKey, rctx),
)
}
// TestHandleSourceDelete_EvictsArchiveWriter proves that
// deleting a webhook reaches the delivery engine and releases
// the webhook's archive writer, exercised through the real
// deletion handler rather than by calling the evictor directly.
func TestHandleSourceDelete_EvictsArchiveWriter(t *testing.T) {
t.Parallel()
var (
h *handlers.Handlers
sess *session.Session
db *database.Database
ev *recordingEvictor
)
app := newTestApp(t, &h, &sess, &db, &ev)
app.RequireStart()
t.Cleanup(app.RequireStop)
wh := seedWebhook(t, db)
seedTarget(t, db, wh.ID, database.TargetTypeDatabase)
cookies := authenticatedCookies(
t, sess, deleteTestUserID, deleteTestUsername,
)
req := postRequest(
"/source/"+wh.ID+"/delete",
cookies,
map[string]string{paramSourceID: wh.ID},
)
w := httptest.NewRecorder()
h.HandleSourceDelete().ServeHTTP(w, req)
require.Equal(t, http.StatusSeeOther, w.Code)
assert.Equal(
t, []string{wh.ID}, ev.Evicted(),
"deleting a webhook should evict its archive writer",
)
}
// TestHandleSourceDelete_KeepsArchiveFile proves that deleting
// a webhook does not remove its archive database file: the
// archive is long-term storage the operator owns.
func TestHandleSourceDelete_KeepsArchiveFile(t *testing.T) {
t.Parallel()
var (
h *handlers.Handlers
sess *session.Session
db *database.Database
mgr *database.WebhookDBManager
)
app := newTestApp(t, &h, &sess, &db, &mgr)
app.RequireStart()
t.Cleanup(app.RequireStop)
wh := seedWebhook(t, db)
// Place an archive file where the delivery engine would.
archivePath := archivePathFor(t, mgr, wh.ID)
require.NoError(
t,
writeArchivePlaceholder(archivePath),
)
cookies := authenticatedCookies(
t, sess, deleteTestUserID, deleteTestUsername,
)
req := postRequest(
"/source/"+wh.ID+"/delete",
cookies,
map[string]string{paramSourceID: wh.ID},
)
w := httptest.NewRecorder()
h.HandleSourceDelete().ServeHTTP(w, req)
require.Equal(t, http.StatusSeeOther, w.Code)
assert.FileExists(
t, archivePath,
"webhook deletion must not destroy the archive file",
)
}
// TestHandleTargetDelete_EvictsWhenLastDatabaseTargetGone
// proves that removing the last database target releases the
// archive writer.
func TestHandleTargetDelete_EvictsWhenLastDatabaseTargetGone(
t *testing.T,
) {
t.Parallel()
var (
h *handlers.Handlers
sess *session.Session
db *database.Database
ev *recordingEvictor
)
app := newTestApp(t, &h, &sess, &db, &ev)
app.RequireStart()
t.Cleanup(app.RequireStop)
wh := seedWebhook(t, db)
tgt := seedTarget(
t, db, wh.ID, database.TargetTypeDatabase,
)
cookies := authenticatedCookies(
t, sess, deleteTestUserID, deleteTestUsername,
)
req := postRequest(
"/source/"+wh.ID+"/targets/"+tgt.ID+"/delete",
cookies,
map[string]string{
paramSourceID: wh.ID,
paramTargetID: tgt.ID,
},
)
w := httptest.NewRecorder()
h.HandleTargetDelete().ServeHTTP(w, req)
require.Equal(t, http.StatusSeeOther, w.Code)
assert.Equal(
t, []string{wh.ID}, ev.Evicted(),
"removing the last database target should evict",
)
}
// TestHandleTargetDelete_KeepsWriterWhileDatabaseTargetRemains
// proves that deleting an unrelated target, or one of several
// database targets, leaves a still-needed archive writer alone.
func TestHandleTargetDelete_KeepsWriterWhileDatabaseTargetRemains(
t *testing.T,
) {
t.Parallel()
var (
h *handlers.Handlers
sess *session.Session
db *database.Database
ev *recordingEvictor
)
app := newTestApp(t, &h, &sess, &db, &ev)
app.RequireStart()
t.Cleanup(app.RequireStop)
wh := seedWebhook(t, db)
seedTarget(t, db, wh.ID, database.TargetTypeDatabase)
other := seedTarget(t, db, wh.ID, database.TargetTypeLog)
cookies := authenticatedCookies(
t, sess, deleteTestUserID, deleteTestUsername,
)
req := postRequest(
"/source/"+wh.ID+"/targets/"+other.ID+"/delete",
cookies,
map[string]string{
paramSourceID: wh.ID,
paramTargetID: other.ID,
},
)
w := httptest.NewRecorder()
h.HandleTargetDelete().ServeHTTP(w, req)
require.Equal(t, http.StatusSeeOther, w.Code)
assert.Empty(
t, ev.Evicted(),
"a surviving database target must keep its writer",
)
}

View File

@@ -533,6 +533,13 @@ func (h *Handlers) deleteWebhookResources(
return
}
// Release the delivery engine's per-webhook archiving state
// so a deleted webhook's archive writer (and any handle open
// within its debounce window) does not linger for the
// process lifetime. The archive file itself is deliberately
// left on disk; see evictArchiveWriter.
h.evictArchiveWriter(webhook.ID)
err = h.dbMgr.DeleteDB(webhook.ID)
if err != nil {
h.log.Error(
@@ -551,6 +558,64 @@ func (h *Handlers) deleteWebhookResources(
http.Redirect(w, r, "/sources", http.StatusSeeOther)
}
// evictArchiveWriter asks the delivery engine to drop its
// cached archive writer for a webhook, closing the archive file
// handle.
//
// The archive database file is NOT deleted. Unlike the event
// database — which is per-webhook working storage and is
// hard-deleted with the webhook — an archive is explicitly
// long-term storage that an operator may want to keep or move
// away for offline retention. Destroying it as a side effect of
// deleting a webhook would be a surprising and unrecoverable
// data loss, so the file is left for the operator to handle.
func (h *Handlers) evictArchiveWriter(webhookID string) {
if h.evictor == nil {
return
}
h.evictor.EvictWebhook(webhookID)
}
// evictArchiveWriterIfUnused releases a webhook's archive
// writer once the webhook has no database target left to feed
// it.
//
// It is called after any child resource of a webhook is
// deleted, and is correct without knowing which kind was: it
// evicts only when no database target remains, so deleting one
// of several database targets — or deleting an unrelated
// target type — leaves a still-needed writer alone. When no
// database target ever existed there is no writer and eviction
// is a no-op. Soft-deleted targets are excluded by GORM's
// default scope, so the row just deleted is not counted.
func (h *Handlers) evictArchiveWriterIfUnused(webhookID string) {
var remaining int64
err := h.db.DB().
Model(&database.Target{}).
Where(
"webhook_id = ? AND type = ?",
webhookID, database.TargetTypeDatabase,
).
Count(&remaining).Error
if err != nil {
h.log.Error(
"failed to count remaining database targets",
"webhook_id", webhookID,
"error", err,
)
return
}
if remaining > 0 {
return
}
h.evictArchiveWriter(webhookID)
}
// HandleSourceLogs shows the request/response logs for a
// webhook.
func (h *Handlers) HandleSourceLogs() http.HandlerFunc {
@@ -1024,23 +1089,31 @@ func (h *Handlers) HandleEntrypointDelete() http.HandlerFunc {
return h.deleteChildResource(
"entrypointID", &database.Entrypoint{},
"failed to delete entrypoint",
nil,
)
}
// HandleTargetDelete handles deleting a target.
// HandleTargetDelete handles deleting a target. Deleting the
// last database target of a webhook leaves its archive writer
// with nothing to write, so the writer is evicted and its
// handle closed; the archive file is left on disk.
func (h *Handlers) HandleTargetDelete() http.HandlerFunc {
return h.deleteChildResource(
"targetID", &database.Target{},
"failed to delete target",
h.evictArchiveWriterIfUnused,
)
}
// deleteChildResource returns a handler that deletes a child
// resource (entrypoint or target) belonging to a webhook.
// resource (entrypoint or target) belonging to a webhook. The
// optional afterDelete hook runs with the webhook's id once the
// delete has succeeded, before the redirect.
func (h *Handlers) deleteChildResource(
idParam string,
model any,
errMsg string,
afterDelete func(webhookID string),
) http.HandlerFunc {
return func(w http.ResponseWriter, r *http.Request) {
userID, ok := h.getUserID(r)
@@ -1080,6 +1153,10 @@ func (h *Handlers) deleteChildResource(
return
}
if afterDelete != nil {
afterDelete(webhook.ID)
}
http.Redirect(
w, r,
"/source/"+webhook.ID,