Files
webhooker/internal/handlers/webhook_stats.go
T
clawbot 926d34b4b8
check / check (push) Successful in 3m33s
Add a statistics pane to the webhook page (closes #368)
Each webhook's event database keeps running totals: one row for its
events, with when the newest arrived, and one row per target for its
deliveries, delivered and failed, each with what retention removed.
Every write to them shares the transaction of the rows it counts, and
a delivery already delivered or failed is not settled again.
Deliveries get a finished_at column; it and target_id end the status
index, so each target's deliveries finished in a window come from one
index-range query grouped by target. Retention deletes 1000 expired
events per transaction, pausing 200 ms between them so other writers
get in, and stops between them on shutdown. The pane is its own
template, its figures in tables.

The schema changes in place with nothing back-filled, so an existing
database must be recreated.

Model: opus-5-5
2026-10-02 01:26:42 +00:00

260 lines
6.3 KiB
Go

package handlers
import (
"fmt"
"time"
"gorm.io/gorm"
"sneak.berlin/go/webhooker/internal/database"
)
// The spans of the two recent windows the statistics pane reports on:
// the last 10 minutes and the last 24 hours.
const (
shortWindow = 10 * time.Minute
longWindow = 24 * time.Hour
)
// percent turns a fraction into a percentage.
const percent = 100
// WebhookStats holds the figures in the statistics pane at the top of
// the webhook page.
type WebhookStats struct {
Entrypoints int
ActiveEntrypoints int
Targets int
ActiveTargets int
// Lifetime counts every event, delivery and failure the webhook
// has had, and WithinRetention those still stored.
Lifetime Counts
WithinRetention Counts
// InProgress counts the deliveries still pending or retrying.
InProgress int64
// LastEventAt is when the newest event arrived, or nil when none
// has. Retention does not change it.
LastEventAt *time.Time
Last10Minutes RecentWindow
Last24Hours RecentWindow
}
// Counts holds a number of events, of deliveries and of failed
// deliveries.
type Counts struct {
Events int64
Deliveries int64
Failures int64
}
// RecentWindow holds what happened in one recent window: the events
// received in it, and the deliveries that became delivered or failed in
// it.
type RecentWindow struct {
Events int64
Delivered int64
Failed int64
}
// TargetFinished is how many of one target's deliveries became
// delivered, and how many failed, in a recent window.
type TargetFinished struct {
TargetID string
Delivered int64
Failed int64
}
// FailurePercent is the share of the deliveries finished in the window
// that failed, or a dash when none finished. Deliveries still pending
// or retrying are not counted either way.
func (w RecentWindow) FailurePercent() string {
finished := w.Delivered + w.Failed
if finished == 0 {
return "—"
}
return fmt.Sprintf(
"%.1f%%", percent*float64(w.Failed)/float64(finished),
)
}
// loadWebhookStats gathers the figures for the statistics pane from the
// webhook's entrypoints and targets, as the page has already loaded
// them, and from its event database. It returns nil, and logs why, when
// the event database cannot be read.
func (h *Handlers) loadWebhookStats(
webhookID string,
entrypoints []database.Entrypoint,
targets []database.Target,
) *WebhookStats {
stats := &WebhookStats{
Entrypoints: len(entrypoints),
Targets: len(targets),
}
for i := range entrypoints {
if entrypoints[i].Active {
stats.ActiveEntrypoints++
}
}
for i := range targets {
if targets[i].Active {
stats.ActiveTargets++
}
}
// Opening an event database that does not exist would create it,
// and it would hold nothing to count.
if !h.dbMgr.DBExists(webhookID) {
return stats
}
webhookDB, err := h.dbMgr.GetDB(webhookID)
if err == nil {
err = readEventStats(webhookDB, time.Now(), stats)
}
if err != nil {
h.log.Error(
"failed to read webhook statistics",
"webhook_id", webhookID,
"error", err,
)
return nil
}
return stats
}
// readEventStats fills in the figures that come from the webhook's
// event database. None of them reads every stored row: the totals are
// one row for the events and one per target for the deliveries, and
// every other figure is read from an index, over only the rows it
// counts.
func readEventStats(
db *gorm.DB, now time.Time, stats *WebhookStats,
) error {
err := readTotals(db, stats)
if err != nil {
return err
}
err = db.Model(&database.Delivery{}).
Where("status IN ?", []database.DeliveryStatus{
database.DeliveryStatusPending,
database.DeliveryStatusRetrying,
}).
Count(&stats.InProgress).Error
if err != nil {
return fmt.Errorf("counting deliveries in progress: %w", err)
}
stats.Last10Minutes, err = readRecentWindow(
db, now.Add(-shortWindow),
)
if err != nil {
return err
}
stats.Last24Hours, err = readRecentWindow(
db, now.Add(-longWindow),
)
return err
}
// readTotals fills in the lifetime and within-retention figures, and
// when the last event arrived, from the running totals: the events'
// row, and the targets' rows summed.
func readTotals(db *gorm.DB, stats *WebhookStats) error {
var events database.EventTotals
err := db.Take(&events).Error
if err != nil {
return fmt.Errorf("reading event totals: %w", err)
}
var targets []database.TargetTotals
err = db.Find(&targets).Error
if err != nil {
return fmt.Errorf("reading target totals: %w", err)
}
stats.Lifetime.Events = events.Events
stats.WithinRetention.Events = events.Events - events.EventsRemoved
stats.LastEventAt = events.LastEventAt
for _, t := range targets {
stats.Lifetime.Deliveries += t.Deliveries
stats.Lifetime.Failures += t.Failed
stats.WithinRetention.Deliveries += t.Deliveries - t.DeliveriesRemoved
stats.WithinRetention.Failures += t.Failed - t.FailedRemoved
}
return nil
}
// readRecentWindow counts the events received, and the deliveries that
// became delivered or failed, since the given time.
func readRecentWindow(
db *gorm.DB, since time.Time,
) (RecentWindow, error) {
var w RecentWindow
err := db.Model(&database.Event{}).
Where("created_at >= ?", since).
Count(&w.Events).Error
if err != nil {
return w, fmt.Errorf("counting recent events: %w", err)
}
byTarget, err := finishedByTarget(db, since)
if err != nil {
return w, err
}
for _, f := range byTarget {
w.Delivered += f.Delivered
w.Failed += f.Failed
}
return w, nil
}
// finishedByTarget counts, for each target, the deliveries that became
// delivered and those that failed since the given time, in one query
// over just that window of the deliveries' status index. A target with
// neither is left out.
func finishedByTarget(
db *gorm.DB, since time.Time,
) ([]TargetFinished, error) {
var byTarget []TargetFinished
err := db.Model(&database.Delivery{}).
Select("target_id, "+
"count(CASE WHEN status = ? THEN 1 END) AS delivered, "+
"count(CASE WHEN status = ? THEN 1 END) AS failed",
database.DeliveryStatusDelivered,
database.DeliveryStatusFailed).
Where("status IN ? AND finished_at >= ?",
[]database.DeliveryStatus{
database.DeliveryStatusDelivered,
database.DeliveryStatusFailed,
}, since).
Group("target_id").
Find(&byTarget).Error
if err != nil {
return nil, fmt.Errorf(
"counting deliveries finished by target: %w", err,
)
}
return byTarget, nil
}