feat: sample recent business events

This commit is contained in:
2026-09-18 21:12:05 +08:00
parent 5284206731
commit 8ce9f4e1fa
14 changed files with 68 additions and 18 deletions

View File

@@ -8,6 +8,7 @@ import (
)
const operationalMetricSampleLimit = 10000
const operationalMetricEventWindow = 5 * time.Minute
// OperationalSnapshot 是进程观测使用的有限数据库快照。
// Counts 只包含固定状态的有界计数;达到上限时 Truncated 为 true,不能解释为精确总量。
@@ -26,12 +27,15 @@ type OperationalSnapshot struct {
WorkflowOldestAgeSeconds float64
// Truncated 表示至少一个状态达到有界采样上限。
Truncated bool
// RecentEvents 是固定事件类别在最近窗口内的有界数量。
RecentEvents map[string]uint64
}
var (
operationalTaskStates = []string{"WAITING", "LEASED", "RUNNING", "NEEDS_REVIEW", "SUCCEEDED", "FAILED", "CANCELLED"}
operationalDeliveryStates = []string{"PENDING", "LEASED", "ACKED", "EXPIRED"}
operationalWorkflowStates = []string{"RUNNING", "WAITING", "CANCELLING", "NEEDS_REVIEW", "SUCCEEDED", "FAILED", "CANCELLED"}
operationalEventTypes = []string{"task.accepted", "task.started", "task.succeeded", "task.failed", "task.needs_review", "task.requeued", "workflow.started", "workflow.advanced", "workflow.recovered", "workflow.blocked", "workflow.stopped"}
)
// ReadOperationalSnapshot performs only bounded, indexed reads. It is intended
@@ -68,11 +72,16 @@ func ReadOperationalSnapshot(ctx context.Context, db *sql.DB) (OperationalSnapsh
if err != nil {
return OperationalSnapshot{}, err
}
events, eventTruncated, err := boundedRecentEventCounts(ctx, db, now)
if err != nil {
return OperationalSnapshot{}, err
}
return OperationalSnapshot{
TaskStates: tasks, TaskOldestAgeSeconds: taskAge,
DeliveryStates: deliveries, DeliveryOldestAgeSeconds: deliveryAge,
WorkflowStates: workflows, WorkflowOldestAgeSeconds: workflowAge,
Truncated: taskTruncated || deliveryTruncated || workflowTruncated,
RecentEvents: events,
Truncated: taskTruncated || deliveryTruncated || workflowTruncated || eventTruncated,
}, nil
}
@@ -102,6 +111,25 @@ func boundedStateCounts(ctx context.Context, db *sql.DB, table, index string, st
return counts, truncated, nil
}
func boundedRecentEventCounts(ctx context.Context, db *sql.DB, now time.Time) (map[string]uint64, bool, error) {
counts := make(map[string]uint64, len(operationalEventTypes))
truncated := false
cutoff := now.Add(-operationalMetricEventWindow)
for _, eventType := range operationalEventTypes {
query := "SELECT COUNT(*) FROM (SELECT id FROM orbit_events FORCE INDEX (ix_event_observe_type_occurred) WHERE type=? AND occurred_at>=? LIMIT ?) AS bounded"
var n uint64
if err := db.QueryRowContext(ctx, query, eventType, cutoff, operationalMetricSampleLimit+1).Scan(&n); err != nil {
return nil, false, err
}
if n > operationalMetricSampleLimit {
n = operationalMetricSampleLimit
truncated = true
}
counts[eventType] = n
}
return counts, truncated, nil
}
func oldestAge(ctx context.Context, db *sql.DB, table, index string, states []string, column string, now time.Time) (float64, error) {
placeholders := "?"
args := make([]any, 0, len(states))