Index the event-tier columns the sweeps, event log and retention scan (closes #314)

The per-webhook tables declared no secondary indexes, so the recovery
and sweep queries (by delivery status, every minute), the event log
(deliveries by event, results by delivery) and retention (events by
age) each scanned a whole table. Add indexes through GORM model tags so
AutoMigrate creates them on a fresh and on an existing per-webhook
database. events.created_at is indexed by overriding the embedded
BaseModel field on Event alone, leaving the other tables' created_at
unindexed. A test drops the indexes from an opened database, reopens it,
and asserts the open recreated them. The README Data Model section lists
the indexes.

Model: opus-4-8

README.md

@@ -1700,6 +1700,22 @@ retries) is individually logged for full observability.
 
 **Relations:** Belongs to Delivery.
 
+#### Event-tier indexes
+
+Beyond the primary keys, the per-webhook event databases carry secondary
+indexes on the columns the background work reads by, each created by
+`AutoMigrate` on a fresh and on an existing database:
+
+| Column                         | Serves |
+| ------------------------------ | ------ |
+| `deliveries.status`            | The recovery and sweep queries that select deliveries by status once a minute |
+| `deliveries.event_id`          | Loading a page of the event log, which reads deliveries by event |
+| `delivery_results.delivery_id` | Loading a page of the event log, which reads results by delivery |
+| `events.created_at`            | Retention, which deletes events by age |
+
+The `events.resubmitted_from_id` column is also indexed, to resolve the
+resubmit relationship both ways in the event log.
+
 #### Common Fields
 
 Every entity except `Setting` includes these fields from `BaseModel`.

internal/database/database.go

@@ -17,12 +17,12 @@ import (
 	"gorm.io/gorm"
 	"sneak.berlin/go/webhooker/internal/banner"
 	"sneak.berlin/go/webhooker/internal/config"
-	"sneak.berlin/go/webhooker/internal/datadir"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 	"sneak.berlin/go/webhooker/internal/logger"
 )
 
 const (
+	dataDirPerm       = 0750
 	randomPasswordLen = 16
 	sessionKeyLen     = 32
 )
@@ -185,9 +185,7 @@ func (d *Database) connect() error {
 // caller's decision.
 func (d *Database) connectTo(dataDir string) error {
 	// Ensure the data directory exists before opening the database.
-	// datadir.DirPerm is the single source of the directory mode; this
+	err := os.MkdirAll(dataDir, dataDirPerm)
-	// package creates the directory too, since either may run first.
-	err := os.MkdirAll(dataDir, datadir.DirPerm)
 	if err != nil {
 		return fmt.Errorf(
 			"creating data directory %s: %w",

internal/database/event_tier_indexes_test.go

@@ -0,0 +1,72 @@
+package database_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/google/uuid"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// indexedColumn names a secondary index by the model and struct field
+// GORM derives the index name from.
+type indexedColumn struct {
+	model any
+	field string
+}
+
+// eventTierIndexes are the columns the background work reads by: the
+// recovery and sweep queries (status), the event log (event_id and
+// delivery_id) and retention (created_at).
+var eventTierIndexes = []indexedColumn{
+	{&database.Delivery{}, "Status"},
+	{&database.Delivery{}, "EventID"},
+	{&database.DeliveryResult{}, "DeliveryID"},
+	{&database.Event{}, "CreatedAt"},
+}
+
+// TestWebhookDBManager_OpenAddsEventTierIndexes verifies that opening a
+// per-webhook database that predates these indexes creates them, so the
+// queries above stop scanning whole tables. It stands in for an older
+// database file by dropping the indexes AutoMigrate just created, then
+// reopening the same file.
+func TestWebhookDBManager_OpenAddsEventTierIndexes(t *testing.T) {
+	t.Parallel()
+
+	mgr, lc := setupTestWebhookDBManager(t)
+	ctx := context.Background()
+	require.NoError(t, lc.Start(ctx))
+
+	defer func() { require.NoError(t, lc.Stop(ctx)) }()
+
+	webhookID := uuid.New().String()
+
+	db, err := mgr.GetDB(webhookID)
+	require.NoError(t, err)
+
+	// A fresh database has them.
+	for _, ix := range eventTierIndexes {
+		require.True(t, db.Migrator().HasIndex(ix.model, ix.field))
+	}
+
+	// Stand in for a database file created before the indexes existed.
+	for _, ix := range eventTierIndexes {
+		require.NoError(t, db.Migrator().DropIndex(ix.model, ix.field))
+		require.False(t, db.Migrator().HasIndex(ix.model, ix.field))
+	}
+
+	// Drop the cached connection so the next open reopens the file and
+	// runs AutoMigrate against it, as a restart would.
+	require.NoError(t, mgr.CloseAll())
+
+	db, err = mgr.GetDB(webhookID)
+	require.NoError(t, err)
+
+	for _, ix := range eventTierIndexes {
+		assert.True(t, db.Migrator().HasIndex(ix.model, ix.field),
+			"opening the existing database should create the index on %s",
+			ix.field)
+	}
+}

internal/database/model_delivery.go

@@ -32,9 +32,9 @@ func (s DeliveryStatus) Terminal() bool {
 type Delivery struct {
 	BaseModel
 
-	EventID  string         `gorm:"type:uuid;not null"         json:"eventId"`
+	EventID  string         `gorm:"type:uuid;not null;index"         json:"eventId"`
-	TargetID string         `gorm:"type:uuid;not null"         json:"targetId"`
+	TargetID string         `gorm:"type:uuid;not null"               json:"targetId"`
-	Status   DeliveryStatus `gorm:"not null;default:'pending'" json:"status"`
+	Status   DeliveryStatus `gorm:"not null;default:'pending';index" json:"status"`
 
 	// Relations
 	Event           Event            `json:"event,omitzero"`

internal/database/model_delivery_result.go

@@ -4,7 +4,7 @@ package database
 type DeliveryResult struct {
 	BaseModel
 
-	DeliveryID   string `gorm:"type:uuid;not null"   json:"deliveryId"`
+	DeliveryID   string `gorm:"type:uuid;not null;index" json:"deliveryId"`
 	AttemptNum   int    `gorm:"not null"             json:"attemptNum"`
 	Success      bool   `json:"success"`
 	StatusCode   int    `json:"statusCode,omitempty"`

internal/database/model_event.go

@@ -1,9 +1,17 @@
 package database
 
+import "time"
+
 // Event represents a captured webhook event
 type Event struct {
 	BaseModel
 
+	// CreatedAt overrides BaseModel.CreatedAt only to add an index:
+	// retention deletes events by age, so events.created_at is queried
+	// on every sweep. The other tables keep the unindexed BaseModel
+	// field.
+	CreatedAt time.Time `gorm:"index" json:"createdAt"`
+
 	WebhookID    string `gorm:"type:uuid;not null" json:"webhookId"`
 	EntrypointID string `gorm:"type:uuid;not null" json:"entrypointId"`
 

internal/database/webhook_db_manager.go

@@ -13,7 +13,6 @@ import (
 	"gorm.io/driver/sqlite"
 	"gorm.io/gorm"
 	"sneak.berlin/go/webhooker/internal/config"
-	"sneak.berlin/go/webhooker/internal/datadir"
 	"sneak.berlin/go/webhooker/internal/gormlog"
 	"sneak.berlin/go/webhooker/internal/logger"
 )
@@ -54,9 +53,8 @@ func NewWebhookDBManager(
 		log:     params.Logger.Get(),
 	}
 
-	// Create data directory if it doesn't exist. datadir.DirPerm is the
+	// Create data directory if it doesn't exist
-	// single source of the directory mode; either package may run first.
+	err := os.MkdirAll(m.dataDir, dataDirPerm)
-	err := os.MkdirAll(m.dataDir, datadir.DirPerm)
 	if err != nil {
 		return nil, fmt.Errorf(
 			"creating data directory %s: %w",

internal/datadir/lock.go

@@ -29,11 +29,9 @@ import (
 // process that was killed with SIGKILL blocks nothing.
 const LockFileName = "webhooker.lock"
 
-// DirPerm is the mode DATA_DIR is created with. It is the single
+// dirPerm is the mode Acquire creates DATA_DIR with. It matches what
-// source of that mode: internal/database consumes it rather than
+// internal/database uses, since whichever runs first creates it.
-// keeping its own copy, so the two packages that both create the
+const dirPerm = 0o750
-// directory cannot drift into disagreeing about its permissions.
-const DirPerm = 0o750
 
 // ErrLocked reports that another live process holds the data
 // directory. Callers that need to know whether a deployment is running
@@ -66,7 +64,7 @@ func Acquire(dir string) (*Lock, error) {
 		return nil, ErrNoDir
 	}
 
-	err := os.MkdirAll(dir, DirPerm)
+	err := os.MkdirAll(dir, dirPerm)
 	if err != nil {
 		return nil, fmt.Errorf(
 			"creating data directory %s: %w", dir, err,