Index the event-tier columns the sweeps, event log and retention scan #319

Open
clawbot wants to merge 1 commits from issue-314-event-tier-indexes into next
5 changed files with 100 additions and 4 deletions
+16
View File
@@ -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`.
@@ -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)
}
}
+2 -2
View File
@@ -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"`
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"`
+1 -1
View File
@@ -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"`
+8
View File
@@ -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"`