feat: sample terminal business latency
This commit is contained in:
@@ -81,7 +81,7 @@
|
||||
- A04须截留真实task.assign并独立确认LEASED/未授权，再强杀旧节点、Wait确认退出、新节点等原租约自然到期；不能把已送达未开始替代未送达。COMMIT故障工具只在测试二进制：BEFORE阻止COMMIT，AFTER核验真实MySQL成功包后丢确认；独立连接回读，原身份/候选恢复，禁止在生产增加故障开关或将HTTP丢回执替代数据库提交不明。
|
||||
- W16下一轮时钟只能在PENDING结果已保存等待后存在，三方竞争中的结果参与者是旧结果重放；新结果/未知/冲突另有在途查询回归。保持原受理时间、事件时间、截止与预算，不能凭有限入队顺序声称穷尽线程交错。
|
||||
|
||||
- P6进程观测使用internal/observability固定指标目录，拒绝未知名称、类型和动态标签，不能引入任务/租户/业务键/凭据维度。ORBIT_METRICS_ADDR默认空（关闭），显式启用独立采集监听；业务端口不得暴露全局指标。渲染和网络I/O不持有全局记录锁，每个直方图局部快照保持桶/count/sum一致，最多2个并发抓取。启用指标后的5秒后台采样使用000026/000027固定索引读取任务、交付、流程状态和固定事件类别，每个状态或事件最多10000条、事件窗口5分钟、900ms数据库截止；采样失败保留最后成功状态并独立记录错误/超时，不能影响业务事务或把有限样本当全局精确数。
|
||||
- P6进程观测使用internal/observability固定指标目录，拒绝未知名称、类型和动态标签，不能引入任务/租户/业务键/凭据维度。ORBIT_METRICS_ADDR默认空（关闭），显式启用独立采集监听；业务端口不得暴露全局指标。渲染和网络I/O不持有全局记录锁，每个直方图局部快照保持桶/count/sum一致，最多2个并发抓取。启用指标后的5秒后台采样使用000026–000028固定索引读取任务、交付、流程状态、固定事件类别和终态耗时，每个状态或事件最多10000条、事件窗口5分钟、900ms数据库截止；采样失败保留最后成功状态并独立记录错误/超时，不能影响业务事务或把有限样本当全局精确数。
|
||||
- HTTP成功升级在Hijack完成时记录握手，WS处理器存续计入独立连接指标；保持1xx临时响应、Flush、Hijack与原panic行为。DB池取本地Stats，抓取不查询业务库；后台批次success不是业务任务成功量。观测丢样或失败不得改变权威事务及恢复决定。
|
||||
- 进程指标、固定状态采样、格式验证、告警规则和标准回归证据见docs/reports/phase-6-observability.md及docs/reports/phase-6-business-observability.md。仍须补受理/授权/完成与流程推进延迟、持久吞吐/积压的全局聚合、重试/核查/恢复量、发送队列、实际采集告警及负载开销，不能把进程观测通过写成P6已完成。普通清理仍须保护有效幂等、未确认事件、未知结果和未终结流程。
|
||||
- 凭据轮换保留credential_id及订阅/Worker授权绑定，在同一事务替换摘要、固定到期时间、幂等回执和管理审计；新令牌必须重新建立会话，认证路径每次重新核对凭据状态。撤销必须让认证失效并保留原任务、订阅、交付、会话和审计证据，允许在应用或命名空间停用后执行；重复应用同一固定操作幂等返回。管理CLI先把固定操作文件写成0600，再提交；提交不明时保留文件并用原文件重放，不能重新生成秘密。日志、审计摘要、指标和业务表不得保存秘密原文或摘要。不要把轮换同一凭据ID解释成历史令牌仍有效，也不得级联删除订阅、任务或事件。
|
||||
|
||||
@@ -201,6 +201,8 @@ func run() error {
|
||||
DeliveryStates: snapshot.DeliveryStates, DeliveryOldestAgeSeconds: snapshot.DeliveryOldestAgeSeconds,
|
||||
WorkflowStates: snapshot.WorkflowStates, WorkflowOldestAgeSeconds: snapshot.WorkflowOldestAgeSeconds,
|
||||
RecentEvents: snapshot.RecentEvents,
|
||||
TaskTerminalLatencySeconds: snapshot.TaskTerminalLatencySeconds, TaskTerminalLatencyMaxSeconds: snapshot.TaskTerminalLatencyMaxSeconds,
|
||||
WorkflowTerminalLatencySeconds: snapshot.WorkflowTerminalLatencySeconds, WorkflowTerminalLatencyMaxSeconds: snapshot.WorkflowTerminalLatencyMaxSeconds,
|
||||
Truncated: snapshot.Truncated,
|
||||
}, started, err)
|
||||
if err != nil && metricsCtx.Err() == nil {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
# 数据模型与实现基线
|
||||
|
||||
更新：2026-09-18。数据库统一禁止外键。当前迁移版本为27；000026/000027只增加固定业务观测读取所需索引，不增加实体或字段。当前已实现任务执行、安全重试、运行中取消、计划调度、队列限速/背压和应用配额；优先级及节点公平领取已实现；可靠订阅核心、HTTP/WSS、管理与消费 SDK 已实现，独立 Inbox 场景已实现，流程编排继续开发。
|
||||
更新：2026-09-18。数据库统一禁止外键。当前迁移版本为28；000026–000028只增加固定业务观测读取所需索引，不增加实体或字段。当前已实现任务执行、安全重试、运行中取消、计划调度、队列限速/背压和应用配额；优先级及节点公平领取已实现；可靠订阅核心、HTTP/WSS、管理与消费 SDK 已实现，独立 Inbox 场景已实现，流程编排继续开发。
|
||||
|
||||
## 1. 模块与依赖
|
||||
|
||||
@@ -251,3 +251,5 @@ Event.WorkflowID为只读STORED生成列，从原不可变事件派生流程归
|
||||
000026只增加三组读取索引：`pulse_tasks(state,available_at,id)`、`orbit_deliveries(state,available_at,id)`和`weave_instances(state,updated_at,id)`。它们服务于后台有界观测，不改变任何模型字段、状态机、事务边界或授权规则，也不包含外键或级联。采样器只使用代码固定的表、索引、状态和列名，每个状态最多读取10000条；结果达到上限时必须通过指标暴露截断，不能把样本数解释为全库精确数量。迁移后仍要求服务层 `CheckSchema` 验证零外键，真实升级见[有界业务采样报告](reports/phase-6-business-observability.md)。
|
||||
|
||||
000027为`orbit_events(type,occurred_at,id)`增加固定事件窗口索引。采样器只读取代码列出的任务和流程事件类别、最近5分钟、每类最多10000条；未知事件类型不写入标签，事件指标只说明本节点有限趋势，不能代替审计查询、端到端阶段延迟或跨节点吞吐。索引不改变事件原文、不可变触发器、外键策略或事务边界。
|
||||
|
||||
000028为`pulse_tasks(state,completed_at,id)`和`weave_instances(state,completed_at,id)`增加终态耗时样本索引。采样器只读取最近5分钟内成功、失败或取消记录，最多10000条，计算创建到终态的平均/最大秒数并在截断时复用统一标记；不把该样本解释为端到端外部效果或全局SLO。
|
||||
|
||||
@@ -59,7 +59,7 @@ P4/P5定时等待与后续查询轮次的实现及回归记录见[时钟报告](
|
||||
### P6 首批实施顺序
|
||||
|
||||
1. 已补[首批可复现故障工具](reports/phase-6-fault-boundaries.md)：A04“派发已提交但消息尚未送达”、W01/W13事务提交结果不明，以及W16最终回执/旧PENDING结果重放/下一轮竞争。每个切点必须有实际数据库或进程证据，不能用响应错误推断事务是否已提交，也不能用普通SIGNAL竞争替代最终查询场景。
|
||||
2. 已实现[基础运行观测](api/observability.md)及[有界业务状态与事件采样](reports/phase-6-business-observability.md)：HTTP/WS、数据库连接池、后台批次、固定状态计数、最早年龄、最近事件类别、截断/新鲜度指标和可离线验证的告警规则；独立采集监听默认关闭，固定指标目录拒绝动态标签。仍需受理/授权/完成端到端阶段延迟与全局持久吞吐、流程推进延迟、全局发送队列、多节点聚合及生产采集/通知验证。
|
||||
2. 已实现[基础运行观测](api/observability.md)及[有界业务状态与事件采样](reports/phase-6-business-observability.md)：HTTP/WS、数据库连接池、后台批次、固定状态计数、最近事件类别、终态耗时样本、最早年龄、截断/新鲜度指标和可离线验证的告警规则；独立采集监听默认关闭，固定指标目录拒绝动态标签。仍需受理/授权阶段端到端延迟与全局持久吞吐、流程Inbox推进延迟、全局发送队列、多节点聚合及生产采集/通知验证。
|
||||
3. 已补齐受保护管理环境中的固定凭据操作文件、轮换、撤销、幂等回执和脱敏管理审计；轮换保留授权绑定并要求新令牌重新建立会话，撤销允许在停用范围内执行且不改写历史记录。仍需补齐提交不明故障切点、多节点安全重绑演练、凭据最小权限配置核对和生产密钥托管/审计演练。
|
||||
4. 实现保留/归档与受保护记录核对，再执行备份恢复、兼容升级和六类容量负载。未确认交付、有效幂等身份、当前/历史执行证据和未终结流程不能被普通清理破坏。生产HA及RPO/RTO继续按实际拓扑验证，不缩减为本机多进程检查。
|
||||
|
||||
|
||||
@@ -54,6 +54,8 @@ curl -fsS http://127.0.0.1:9090/metrics
|
||||
| `orbit_weave_workflows_state{state}` | gauge | Weave实例固定状态的有界计数 |
|
||||
| `orbit_weave_workflow_oldest_age_seconds` | gauge | RUNNING/WAITING/CANCELLING/NEEDS_REVIEW实例样本中最早更新时间的年龄 |
|
||||
| `orbit_business_events_recent{event}` | gauge | 最近5分钟内固定事件类别的有界数量，用于观察受理、完成、核查、恢复和流程推进趋势 |
|
||||
| `orbit_pulse_task_terminal_latency_seconds` / `_max_seconds` | gauge | 最近5分钟终态任务从创建到完成的平均/最大耗时样本，单位秒 |
|
||||
| `orbit_weave_workflow_terminal_latency_seconds` / `_max_seconds` | gauge | 最近5分钟终态流程从创建到完成的平均/最大耗时样本，单位秒 |
|
||||
| `orbit_business_snapshot_total{outcome}` | counter | 有界业务快照成功、错误或超时次数 |
|
||||
| `orbit_business_snapshot_duration_seconds` | histogram | 有界业务快照耗时；包含数据库读取 |
|
||||
| `orbit_business_snapshot_last_success_timestamp_seconds` | gauge | 最近一次完整成功快照的Unix时间；失败不会推进 |
|
||||
@@ -101,4 +103,4 @@ promtool check rules deploy/monitoring/orbit.rules.yml
|
||||
promtool test rules deploy/monitoring/orbit.rules.test.yml
|
||||
```
|
||||
|
||||
HTTP失败率和延迟可按route/status_class统计；受理接口响应成功与已完成业务应分别判断。业务状态和事件窗口指标是本节点有限样本，不能相加作为全局精确数量；未知事件类型不会进入标签，应结合 `orbit_business_snapshot_last_success_timestamp_seconds` 和 `orbit_business_snapshot_truncated` 判断新鲜度与完整性。可靠结果量、排队/授权/完成阶段延迟、流程Inbox推进延迟、发送队列、磁盘/复制等仍须补充专门指标；具体当前证据见[进程观测报告](../reports/phase-6-observability.md)和[有界业务采样报告](../reports/phase-6-business-observability.md)。
|
||||
HTTP失败率和延迟可按route/status_class统计；受理接口响应成功与已完成业务应分别判断。业务状态、事件窗口和终结耗时指标是本节点有限样本，不能相加作为全局精确数量；未知事件类型不会进入标签，终结耗时从持久化`created_at`到`completed_at`计算，不包含端到端外部副作用。应结合 `orbit_business_snapshot_last_success_timestamp_seconds` 和 `orbit_business_snapshot_truncated` 判断新鲜度与完整性。可靠结果量、授权阶段延迟、流程Inbox推进延迟、发送队列、磁盘/复制等仍须补充专门指标；具体当前证据见[进程观测报告](../reports/phase-6-observability.md)和[有界业务采样报告](../reports/phase-6-business-observability.md)。
|
||||
|
||||
@@ -6,20 +6,22 @@
|
||||
|
||||
- 迁移 `000026_operational_metrics` 为 `pulse_tasks`、`orbit_deliveries`、`weave_instances` 增加固定前缀索引；不增加模型字段，不引入外键或级联。
|
||||
- 迁移 `000027_operational_event_metrics` 为不可变 `orbit_events` 增加 `(type,occurred_at,id)` 固定事件窗口索引；不增加模型字段，不引入外键或级联。
|
||||
- 迁移 `000028_terminal_latency_metrics` 为任务和流程终态完成时间增加固定索引；采样最近5分钟成功/失败/取消记录，计算从持久化创建到终态的平均/最大耗时，仍不增加模型字段。
|
||||
- [存储采样器](../../internal/storage/mysql/operational_metrics.go)只拼接代码内固定的表、索引、列名、状态和事件集合。每个状态或事件类别使用索引读取最多10001条，再将结果封顶到10000；至少一类封顶时 `orbit_business_snapshot_truncated=1`。
|
||||
- 采样器先读取数据库UTC时间，再读取任务、结果交付和流程实例固定状态计数、最早未完成年龄及最近5分钟受理/完成/核查/恢复/流程推进事件类别。所有调用由独立900ms上下文限制；取消、数据库错误和超时都返回失败，不修改持久化数据。
|
||||
- [业务指标记录器](../../internal/observability/business.go)将成功、错误、超时分别计数并记录耗时。失败样本不覆盖最后一次成功状态，同时保留最后成功时间，方便告警区分“旧值可见”和“本轮采集失败”。标签基数和状态取值均在目录中固定。
|
||||
- 终态耗时只使用`created_at`与`completed_at`，以固定平均/最大指标暴露；它不声称授权耗时、外部副作用耗时或全局分位数。
|
||||
- [进程入口](../../cmd/orbit/main.go)仅在显式启用指标时每5秒后台采样；`GET /metrics`仍只渲染进程内存，不在抓取请求中执行SQL。采样错误进入脱敏结构化日志，不能改变任务、交付或流程事务。
|
||||
|
||||
## 回归证据
|
||||
|
||||
- [业务记录器单测](../../internal/observability/metrics_test.go)验证成功状态、年龄、截断、成功计数和失败后保留最后成功值；超时计数单独增加。
|
||||
- [真实MySQL专项](../../internal/storage/mysql/operational_metrics_integration_test.go)验证两次迁移索引真实存在、数据库外键为0、任务状态和`task.accepted`事件被采样、固定状态集合存在，并验证已取消上下文被拒绝。
|
||||
- `go test ./...`覆盖编译和普通单测；真实MySQL专项由标准`GO=... DOCKER=... sh scripts/test-mysql.sh`执行，未设置`ORBIT_TEST_MYSQL_DSN`时专项会跳过，不能把跳过当通过。最新标准脚本在Go 1.27.1、darwin/arm64、Docker MySQL 8.4.10环境退出码为0；其中存储/迁移/事务组265.925秒，指标开关进程组4.548秒，流程运行器全停恢复48.263秒，SDK与两个独立业务示例均通过。专项日志确认`TestIntegrationOperationalSnapshot`、`TestIntegrationNoForeignKeysUpgrade`、`TestIntegrationCredentialOperations`及`TestIntegrationCredentialCommitFaults`均PASS，迁移账本到000027且dirty=false。
|
||||
- [真实MySQL专项](../../internal/storage/mysql/operational_metrics_integration_test.go)验证三次迁移索引真实存在、数据库外键为0、任务状态、`task.accepted`事件和终态耗时被采样、固定状态集合存在，并验证已取消上下文被拒绝。
|
||||
- `go test ./...`覆盖编译和普通单测；真实MySQL专项由标准`GO=... DOCKER=... sh scripts/test-mysql.sh`执行，未设置`ORBIT_TEST_MYSQL_DSN`时专项会跳过，不能把跳过当通过。最新000028标准脚本在Go 1.27.1、darwin/arm64、Docker MySQL 8.4.10环境退出码为0；存储/迁移/事务组、指标开关进程组、流程运行器全停恢复、SDK与两个独立业务示例均通过。日志确认`TestIntegrationOperationalSnapshot`、`TestIntegrationNoForeignKeysUpgrade`、`TestIntegrationCredentialOperations`、`TestIntegrationCredentialCommitFaults`、`TestIntegrationMetricsProcess`及`TestIntegrationWorkflowRuntimeProcess`均PASS，迁移账本到000028且dirty=false。
|
||||
- 当前固定目录导出的指标夹具为929298字节，包含事件标签回归；`promtool check metrics`成功；`promtool check rules deploy/monitoring/orbit.rules.yml`报告7条规则成功，`promtool test rules deploy/monitoring/orbit.rules.test.yml`成功。标准验证镜像仅用于离线检查，平台运行不依赖Prometheus。
|
||||
|
||||
## 解释和边界
|
||||
|
||||
每个Orbit节点都读取自己的有限样本；多节点指标不能直接相加获得全局精确积压或吞吐。达到10000上限、采样超时、节点重启或节点间时间不同都会影响解释，必须结合截断标记、最后成功时间、数据库权威查询和审计判断。事件窗口按`occurred_at`统计固定类别，不包含未知类型；它是趋势线索，不是端到端受理、授权或完成延迟。
|
||||
|
||||
当前仍未完成端到端阶段延迟、全局吞吐聚合、流程Inbox推进延迟、发送队列全局聚合、生产采集通知演练、锁/磁盘/复制指标和多故障域容量验证。此批实现不能替代保留、备份恢复、HA、RPO/RTO及发布验收。
|
||||
当前仍未完成端到端授权/外部效果阶段延迟、全局吞吐聚合、流程Inbox推进延迟、发送队列全局聚合、生产采集通知演练、锁/磁盘/复制指标和多故障域容量验证。此批实现不能替代保留、备份恢复、HA、RPO/RTO及发布验收。
|
||||
|
||||
@@ -25,6 +25,14 @@ type BusinessSnapshot struct {
|
||||
Truncated bool
|
||||
// RecentEvents 固定事件类别在最近窗口内的有界数量。
|
||||
RecentEvents map[string]uint64
|
||||
// TaskTerminalLatencySeconds 最近窗口终态任务创建到完成的平均耗时样本。
|
||||
TaskTerminalLatencySeconds float64
|
||||
// TaskTerminalLatencyMaxSeconds 最近窗口终态任务样本最大耗时。
|
||||
TaskTerminalLatencyMaxSeconds float64
|
||||
// WorkflowTerminalLatencySeconds 最近窗口终态流程创建到完成的平均耗时样本。
|
||||
WorkflowTerminalLatencySeconds float64
|
||||
// WorkflowTerminalLatencyMaxSeconds 最近窗口终态流程样本最大耗时。
|
||||
WorkflowTerminalLatencyMaxSeconds float64
|
||||
}
|
||||
|
||||
// RecordBusinessSnapshot records one bounded database sample. A failed sample
|
||||
@@ -58,6 +66,10 @@ func (r *Registry) RecordBusinessSnapshot(snapshot BusinessSnapshot, started tim
|
||||
for _, eventType := range eventTypes {
|
||||
r.SetGauge("orbit_business_events_recent", float64(snapshot.RecentEvents[eventType]), Labels{"event": eventType})
|
||||
}
|
||||
r.SetGauge("orbit_pulse_task_terminal_latency_seconds", snapshot.TaskTerminalLatencySeconds, nil)
|
||||
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_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)
|
||||
|
||||
@@ -44,6 +44,10 @@ func catalog() map[string]descriptor {
|
||||
c["orbit_weave_workflows_state"] = descriptor{gauge, "Bounded count of Weave instances by durable state", map[string][]string{"state": workflowStates}}
|
||||
c["orbit_weave_workflow_oldest_age_seconds"] = descriptor{gauge, "Age of the oldest sampled unfinished Weave instance", nil}
|
||||
c["orbit_business_events_recent"] = descriptor{gauge, "Bounded count of fixed event categories in the recent window", map[string][]string{"event": eventTypes}}
|
||||
c["orbit_pulse_task_terminal_latency_seconds"] = descriptor{gauge, "Average sampled Pulse task create-to-terminal latency in seconds", nil}
|
||||
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_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}
|
||||
|
||||
@@ -124,6 +124,8 @@ func TestBusinessSnapshotKeepsLastGoodStateOnFailure(t *testing.T) {
|
||||
WorkflowStates: map[string]uint64{"RUNNING": 1},
|
||||
WorkflowOldestAgeSeconds: 4.75,
|
||||
RecentEvents: map[string]uint64{"task.accepted": 5},
|
||||
TaskTerminalLatencySeconds: 2.5, TaskTerminalLatencyMaxSeconds: 7.5,
|
||||
WorkflowTerminalLatencySeconds: 3.5, WorkflowTerminalLatencyMaxSeconds: 9.5,
|
||||
Truncated: true,
|
||||
}, started, nil)
|
||||
first := r.Render()
|
||||
@@ -132,6 +134,8 @@ func TestBusinessSnapshotKeepsLastGoodStateOnFailure(t *testing.T) {
|
||||
`orbit_result_deliveries_state{state="PENDING"} 2`,
|
||||
`orbit_weave_workflows_state{state="RUNNING"} 1`,
|
||||
`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_tasks_oldest_age_seconds 12.5",
|
||||
"orbit_business_snapshot_truncated 1",
|
||||
`orbit_business_snapshot_total{outcome="success"} 1`,
|
||||
|
||||
@@ -69,6 +69,8 @@ func TestIntegrationApplicationResourcesUpgrade(t *testing.T) {
|
||||
f.exec(`ALTER TABLE orbit_deliveries DROP INDEX ix_delivery_observe_state_available`)
|
||||
f.exec(`ALTER TABLE weave_instances DROP INDEX ix_workflow_observe_state_updated`)
|
||||
f.exec(`ALTER TABLE orbit_events DROP INDEX ix_event_observe_type_occurred`)
|
||||
f.exec(`ALTER TABLE pulse_tasks DROP INDEX ix_task_observe_terminal_completed`)
|
||||
f.exec(`ALTER TABLE weave_instances DROP INDEX ix_workflow_observe_terminal_completed`)
|
||||
f.exec(`DROP TABLE weave_version_scopes`)
|
||||
f.exec(`ALTER TABLE weave_instances DROP INDEX ix_workflow_created,DROP INDEX ix_workflow_state_created,DROP INDEX ix_workflow_business_state_created,DROP INDEX ix_workflow_definition_created,DROP INDEX ix_workflow_definition_state_created,DROP INDEX ix_workflow_definition_business_created,DROP INDEX ix_workflow_definition_business_state_created`)
|
||||
f.exec(`ALTER TABLE weave_signals DROP INDEX ix_signal_history`)
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
-- 为终态任务/流程的最近完成耗时样本提供固定索引。
|
||||
-- 采样只读已持久化时间，不修改状态、不引入外键或级联。
|
||||
ALTER TABLE pulse_tasks
|
||||
ADD KEY ix_task_observe_terminal_completed (state, completed_at, id);
|
||||
|
||||
ALTER TABLE weave_instances
|
||||
ADD KEY ix_workflow_observe_terminal_completed (state, completed_at, id);
|
||||
@@ -89,7 +89,7 @@ func TestIntegrationNoForeignKeysUpgrade(t *testing.T) {
|
||||
indexes := func() []string {
|
||||
t.Helper()
|
||||
// 排除后续新增/替换索引；原有项在此逐项比较，v24/v25新增项由对应Query/Timeline升级测试核对。
|
||||
rows, err := db.QueryContext(ctx, `SELECT CONCAT_WS(':',TABLE_NAME,INDEX_NAME,NON_UNIQUE,SEQ_IN_INDEX,COLUMN_NAME,COALESCE(SUB_PART,0),INDEX_TYPE,IS_VISIBLE) FROM information_schema.STATISTICS WHERE TABLE_SCHEMA=DATABASE() AND TABLE_NAME NOT IN ('orbit_application_resources','orbit_event_streams','orbit_result_events','weave_version_scopes') AND INDEX_NAME NOT IN ('ix_task_priority_dispatch','ix_delivery_subscription_due','ix_delivery_subscription_lease','ix_delivery_history','ix_delivery_state_history','uq_task_retry_parent','fk_pulse_tasks_3','ix_task_queue_business_created','ix_task_queue_business_state_created','uq_weave_task_result','ix_signal_expiry','ix_signal_activation','uq_wait_winner_signal','ix_task_workflow_owner','ix_signal_history','ix_event_workflow_history','ix_workflow_created','ix_workflow_state_created','ix_workflow_business_state_created','ix_workflow_definition_created','ix_workflow_definition_state_created','ix_workflow_definition_business_created','ix_workflow_definition_business_state_created','ix_task_observe_state_available','ix_delivery_observe_state_available','ix_workflow_observe_state_updated','ix_event_observe_type_occurred') ORDER BY TABLE_NAME,INDEX_NAME,SEQ_IN_INDEX`)
|
||||
rows, err := db.QueryContext(ctx, `SELECT CONCAT_WS(':',TABLE_NAME,INDEX_NAME,NON_UNIQUE,SEQ_IN_INDEX,COLUMN_NAME,COALESCE(SUB_PART,0),INDEX_TYPE,IS_VISIBLE) FROM information_schema.STATISTICS WHERE TABLE_SCHEMA=DATABASE() AND TABLE_NAME NOT IN ('orbit_application_resources','orbit_event_streams','orbit_result_events','weave_version_scopes') AND INDEX_NAME NOT IN ('ix_task_priority_dispatch','ix_delivery_subscription_due','ix_delivery_subscription_lease','ix_delivery_history','ix_delivery_state_history','uq_task_retry_parent','fk_pulse_tasks_3','ix_task_queue_business_created','ix_task_queue_business_state_created','uq_weave_task_result','ix_signal_expiry','ix_signal_activation','uq_wait_winner_signal','ix_task_workflow_owner','ix_signal_history','ix_event_workflow_history','ix_workflow_created','ix_workflow_state_created','ix_workflow_business_state_created','ix_workflow_definition_created','ix_workflow_definition_state_created','ix_workflow_definition_business_created','ix_workflow_definition_business_state_created','ix_task_observe_state_available','ix_delivery_observe_state_available','ix_workflow_observe_state_updated','ix_event_observe_type_occurred','ix_task_observe_terminal_completed','ix_workflow_observe_terminal_completed') ORDER BY TABLE_NAME,INDEX_NAME,SEQ_IN_INDEX`)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
@@ -29,6 +29,14 @@ type OperationalSnapshot struct {
|
||||
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
|
||||
// TaskTerminalLatencySeconds 是最近窗口终态任务从创建到完成的平均耗时样本。
|
||||
TaskTerminalLatencySeconds float64
|
||||
// TaskTerminalLatencyMaxSeconds 是最近窗口终态任务样本的最大耗时。
|
||||
TaskTerminalLatencyMaxSeconds float64
|
||||
// WorkflowTerminalLatencySeconds 是最近窗口终态流程从创建到完成的平均耗时样本。
|
||||
WorkflowTerminalLatencySeconds float64
|
||||
// WorkflowTerminalLatencyMaxSeconds 是最近窗口终态流程样本的最大耗时。
|
||||
WorkflowTerminalLatencyMaxSeconds float64
|
||||
}
|
||||
|
||||
var (
|
||||
@@ -76,12 +84,22 @@ func ReadOperationalSnapshot(ctx context.Context, db *sql.DB) (OperationalSnapsh
|
||||
if err != nil {
|
||||
return OperationalSnapshot{}, err
|
||||
}
|
||||
taskLatency, err := sampledTerminalLatency(ctx, db, "pulse_tasks", "ix_task_observe_terminal_completed", []string{"SUCCEEDED", "FAILED", "CANCELLED"}, now.Add(-operationalMetricEventWindow))
|
||||
if err != nil {
|
||||
return OperationalSnapshot{}, err
|
||||
}
|
||||
workflowLatency, err := sampledTerminalLatency(ctx, db, "weave_instances", "ix_workflow_observe_terminal_completed", []string{"SUCCEEDED", "FAILED", "CANCELLED"}, now.Add(-operationalMetricEventWindow))
|
||||
if err != nil {
|
||||
return OperationalSnapshot{}, err
|
||||
}
|
||||
return OperationalSnapshot{
|
||||
TaskStates: tasks, TaskOldestAgeSeconds: taskAge,
|
||||
DeliveryStates: deliveries, DeliveryOldestAgeSeconds: deliveryAge,
|
||||
WorkflowStates: workflows, WorkflowOldestAgeSeconds: workflowAge,
|
||||
RecentEvents: events,
|
||||
Truncated: taskTruncated || deliveryTruncated || workflowTruncated || eventTruncated,
|
||||
TaskTerminalLatencySeconds: taskLatency.average, TaskTerminalLatencyMaxSeconds: taskLatency.maximum,
|
||||
WorkflowTerminalLatencySeconds: workflowLatency.average, WorkflowTerminalLatencyMaxSeconds: workflowLatency.maximum,
|
||||
Truncated: taskTruncated || deliveryTruncated || workflowTruncated || eventTruncated || taskLatency.truncated || workflowLatency.truncated,
|
||||
}, nil
|
||||
}
|
||||
|
||||
@@ -130,6 +148,58 @@ func boundedRecentEventCounts(ctx context.Context, db *sql.DB, now time.Time) (m
|
||||
return counts, truncated, nil
|
||||
}
|
||||
|
||||
type terminalLatencySample struct {
|
||||
average float64
|
||||
maximum float64
|
||||
truncated bool
|
||||
}
|
||||
|
||||
func sampledTerminalLatency(ctx context.Context, db *sql.DB, table, index string, states []string, cutoff time.Time) (terminalLatencySample, error) {
|
||||
placeholders := "?"
|
||||
args := make([]any, 0, len(states)+2)
|
||||
args = append(args, states[0])
|
||||
for _, state := range states[1:] {
|
||||
placeholders += ",?"
|
||||
args = append(args, state)
|
||||
}
|
||||
args = append(args, cutoff, operationalMetricSampleLimit+1)
|
||||
query := "SELECT created_at,completed_at FROM " + table + " FORCE INDEX (" + index + ") WHERE state IN (" + placeholders + ") AND completed_at>=? ORDER BY completed_at,id LIMIT ?"
|
||||
rows, err := db.QueryContext(ctx, query, args...)
|
||||
if err != nil {
|
||||
return terminalLatencySample{}, err
|
||||
}
|
||||
defer rows.Close()
|
||||
var total, maximum float64
|
||||
var read, valid int
|
||||
for rows.Next() {
|
||||
read++
|
||||
if read > operationalMetricSampleLimit {
|
||||
continue
|
||||
}
|
||||
var created, completed time.Time
|
||||
if err := rows.Scan(&created, &completed); err != nil {
|
||||
return terminalLatencySample{}, err
|
||||
}
|
||||
seconds := completed.Sub(created).Seconds()
|
||||
if seconds < 0 {
|
||||
seconds = 0
|
||||
}
|
||||
total += seconds
|
||||
if seconds > maximum {
|
||||
maximum = seconds
|
||||
}
|
||||
valid++
|
||||
}
|
||||
if err := rows.Err(); err != nil {
|
||||
return terminalLatencySample{}, err
|
||||
}
|
||||
result := terminalLatencySample{maximum: maximum, truncated: read > operationalMetricSampleLimit}
|
||||
if valid > 0 {
|
||||
result.average = total / float64(valid)
|
||||
}
|
||||
return result, 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))
|
||||
|
||||
@@ -34,6 +34,9 @@ func TestIntegrationOperationalSnapshot(t *testing.T) {
|
||||
{"pulse_tasks", "ix_task_observe_state_available"},
|
||||
{"orbit_deliveries", "ix_delivery_observe_state_available"},
|
||||
{"weave_instances", "ix_workflow_observe_state_updated"},
|
||||
{"orbit_events", "ix_event_observe_type_occurred"},
|
||||
{"pulse_tasks", "ix_task_observe_terminal_completed"},
|
||||
{"weave_instances", "ix_workflow_observe_terminal_completed"},
|
||||
} {
|
||||
var n int
|
||||
if err := db.QueryRowContext(ctx, `SELECT COUNT(*) FROM information_schema.statistics WHERE table_schema=DATABASE() AND table_name=? AND index_name=?`, want.table, want.index).Scan(&n); err != nil {
|
||||
@@ -52,7 +55,7 @@ func TestIntegrationOperationalSnapshot(t *testing.T) {
|
||||
}
|
||||
|
||||
f := newExecutionFixture(t, ctx, db)
|
||||
f.submit(2)
|
||||
task := f.submit(2)
|
||||
snapshot, err := ReadOperationalSnapshot(ctx, db)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
@@ -77,6 +80,14 @@ func TestIntegrationOperationalSnapshot(t *testing.T) {
|
||||
if _, ok := snapshot.WorkflowStates["RUNNING"]; !ok {
|
||||
t.Fatal("missing running workflow state")
|
||||
}
|
||||
f.exec("UPDATE pulse_tasks SET state='SUCCEEDED', completed_at=UTC_TIMESTAMP(6), updated_at=UTC_TIMESTAMP(6), revision=revision+1 WHERE namespace_id=? AND id=?", f.resources.NamespaceID, task.ID)
|
||||
completed, err := ReadOperationalSnapshot(ctx, db)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if completed.TaskTerminalLatencySeconds < 0 || completed.TaskTerminalLatencyMaxSeconds < 0 {
|
||||
t.Fatalf("negative terminal latency: %#v", completed)
|
||||
}
|
||||
|
||||
cancelled, cancelNow := context.WithCancel(ctx)
|
||||
cancelNow()
|
||||
|
||||
Reference in New Issue
Block a user