feat: sample workflow phase latency

This commit is contained in:
2026-09-19 19:44:21 +08:00
parent 0ac3f2f3f8
commit a5cef4dbe8
10 changed files with 190 additions and 7 deletions

View File

@@ -37,6 +37,18 @@ type BusinessSnapshot struct {
WorkflowTerminalLatencySeconds float64
// WorkflowTerminalLatencyMaxSeconds 最近窗口终态流程样本最大耗时。
WorkflowTerminalLatencyMaxSeconds float64
// TaskAcceptToStartLatencySeconds 最近窗口任务受理到开始的平均耗时样本。
TaskAcceptToStartLatencySeconds float64
// TaskAcceptToStartLatencyMaxSeconds 最近窗口任务受理到开始的最大耗时样本。
TaskAcceptToStartLatencyMaxSeconds float64
// TaskAcceptToTerminalLatencySeconds 最近窗口任务受理到确定终态的平均耗时样本。
TaskAcceptToTerminalLatencySeconds float64
// TaskAcceptToTerminalLatencyMaxSeconds 最近窗口任务受理到确定终态的最大耗时样本。
TaskAcceptToTerminalLatencyMaxSeconds float64
// WorkflowStartToTerminalLatencySeconds 最近窗口流程开始到停止的平均耗时样本。
WorkflowStartToTerminalLatencySeconds float64
// WorkflowStartToTerminalLatencyMaxSeconds 最近窗口流程开始到停止的最大耗时样本。
WorkflowStartToTerminalLatencyMaxSeconds float64
}
// RecordBusinessSnapshot records one bounded database sample. A failed sample
@@ -77,6 +89,12 @@ func (r *Registry) RecordBusinessSnapshot(snapshot BusinessSnapshot, started tim
r.SetGauge("orbit_pulse_task_terminal_latency_max_seconds", snapshot.TaskTerminalLatencyMaxSeconds, nil)
r.SetGauge("orbit_weave_workflow_terminal_latency_seconds", snapshot.WorkflowTerminalLatencySeconds, nil)
r.SetGauge("orbit_weave_workflow_terminal_latency_max_seconds", snapshot.WorkflowTerminalLatencyMaxSeconds, nil)
r.SetGauge("orbit_pulse_task_accept_to_start_latency_seconds", snapshot.TaskAcceptToStartLatencySeconds, nil)
r.SetGauge("orbit_pulse_task_accept_to_start_latency_max_seconds", snapshot.TaskAcceptToStartLatencyMaxSeconds, nil)
r.SetGauge("orbit_pulse_task_accept_to_terminal_latency_seconds", snapshot.TaskAcceptToTerminalLatencySeconds, nil)
r.SetGauge("orbit_pulse_task_accept_to_terminal_latency_max_seconds", snapshot.TaskAcceptToTerminalLatencyMaxSeconds, nil)
r.SetGauge("orbit_weave_workflow_start_to_terminal_latency_seconds", snapshot.WorkflowStartToTerminalLatencySeconds, nil)
r.SetGauge("orbit_weave_workflow_start_to_terminal_latency_max_seconds", snapshot.WorkflowStartToTerminalLatencyMaxSeconds, nil)
r.SetGauge("orbit_pulse_tasks_oldest_age_seconds", snapshot.TaskOldestAgeSeconds, nil)
r.SetGauge("orbit_result_delivery_oldest_age_seconds", snapshot.DeliveryOldestAgeSeconds, nil)
r.SetGauge("orbit_weave_workflow_oldest_age_seconds", snapshot.WorkflowOldestAgeSeconds, nil)

View File

@@ -10,7 +10,7 @@ var taskStates = []string{"WAITING", "LEASED", "RUNNING", "NEEDS_REVIEW", "SUCCE
var deliveryStates = []string{"PENDING", "LEASED", "ACKED", "EXPIRED"}
var workflowStates = []string{"RUNNING", "WAITING", "CANCELLING", "NEEDS_REVIEW", "SUCCEEDED", "FAILED", "CANCELLED"}
var inboxStates = []string{"PENDING", "LEASED", "PROCESSED", "QUARANTINED"}
var eventTypes = []string{"task.accepted", "task.started", "task.succeeded", "task.failed", "task.needs_review", "task.requeued", "workflow.started", "workflow.advanced", "workflow.recovered", "workflow.blocked", "workflow.stopped"}
var eventTypes = []string{"task.accepted", "task.started", "task.succeeded", "task.failed", "task.cancelled", "task.needs_review", "task.requeued", "workflow.started", "workflow.advanced", "workflow.recovered", "workflow.blocked", "workflow.stopped"}
// Every exported family is declared here, including each allowed label value.
// Adding a metric therefore requires a code review; no user identifier is valid.
@@ -51,6 +51,12 @@ func catalog() map[string]descriptor {
c["orbit_pulse_task_terminal_latency_max_seconds"] = descriptor{gauge, "Maximum sampled Pulse task create-to-terminal latency in seconds", nil}
c["orbit_weave_workflow_terminal_latency_seconds"] = descriptor{gauge, "Average sampled Weave workflow create-to-terminal latency in seconds", nil}
c["orbit_weave_workflow_terminal_latency_max_seconds"] = descriptor{gauge, "Maximum sampled Weave workflow create-to-terminal latency in seconds", nil}
c["orbit_pulse_task_accept_to_start_latency_seconds"] = descriptor{gauge, "Average sampled Pulse task accepted-to-start latency in seconds", nil}
c["orbit_pulse_task_accept_to_start_latency_max_seconds"] = descriptor{gauge, "Maximum sampled Pulse task accepted-to-start latency in seconds", nil}
c["orbit_pulse_task_accept_to_terminal_latency_seconds"] = descriptor{gauge, "Average sampled Pulse task accepted-to-terminal latency in seconds", nil}
c["orbit_pulse_task_accept_to_terminal_latency_max_seconds"] = descriptor{gauge, "Maximum sampled Pulse task accepted-to-terminal latency in seconds", nil}
c["orbit_weave_workflow_start_to_terminal_latency_seconds"] = descriptor{gauge, "Average sampled Weave workflow started-to-terminal latency in seconds", nil}
c["orbit_weave_workflow_start_to_terminal_latency_max_seconds"] = descriptor{gauge, "Maximum sampled Weave workflow started-to-terminal latency in seconds", nil}
c["orbit_business_snapshot_total"] = descriptor{counter, "Completed bounded business-state snapshots by outcome", map[string][]string{"outcome": {"success", "error", "timeout"}}}
c["orbit_business_snapshot_duration_seconds"] = descriptor{histogram, "Bounded business-state snapshot duration in seconds", nil}
c["orbit_business_snapshot_last_success_timestamp_seconds"] = descriptor{gauge, "Unix time of the last successful bounded business-state snapshot", nil}

View File

@@ -128,6 +128,9 @@ func TestBusinessSnapshotKeepsLastGoodStateOnFailure(t *testing.T) {
RecentEvents: map[string]uint64{"task.accepted": 5},
TaskTerminalLatencySeconds: 2.5, TaskTerminalLatencyMaxSeconds: 7.5,
WorkflowTerminalLatencySeconds: 3.5, WorkflowTerminalLatencyMaxSeconds: 9.5,
TaskAcceptToStartLatencySeconds: 1.5, TaskAcceptToStartLatencyMaxSeconds: 4.5,
TaskAcceptToTerminalLatencySeconds: 5.5, TaskAcceptToTerminalLatencyMaxSeconds: 8.5,
WorkflowStartToTerminalLatencySeconds: 6.5, WorkflowStartToTerminalLatencyMaxSeconds: 10.5,
Truncated: true,
}, started, nil)
first := r.Render()
@@ -139,6 +142,9 @@ func TestBusinessSnapshotKeepsLastGoodStateOnFailure(t *testing.T) {
`orbit_business_events_recent{event="task.accepted"} 5`,
"orbit_pulse_task_terminal_latency_seconds 2.5",
"orbit_weave_workflow_terminal_latency_max_seconds 9.5",
"orbit_pulse_task_accept_to_start_latency_seconds 1.5",
"orbit_pulse_task_accept_to_terminal_latency_max_seconds 8.5",
"orbit_weave_workflow_start_to_terminal_latency_seconds 6.5",
"orbit_pulse_tasks_oldest_age_seconds 12.5",
"orbit_weave_inbox_oldest_age_seconds 3.25",
"orbit_business_snapshot_truncated 1",