feat: measure bounded worker execution with durable verification

This commit is contained in:
2026-09-20 02:28:53 +08:00
parent 3137bce8d5
commit 1dfc7e4234
19 changed files with 1132 additions and 2 deletions

View File

@@ -0,0 +1 @@
{"run_id":"a7b51ef05252222cba0c3a458a2a330c","go_version":"go1.25.14","goos":"linux","goarch":"arm64","started_at":"2026-09-19T18:25:48.034952468Z","admission_finished_at":"2026-09-19T18:25:48.127721385Z","finished_at":"2026-09-19T18:25:50.044512177Z","requests":24,"concurrency":4,"workers":1,"capacity_per_worker":1,"durations_ms":[1000],"run_timeout_ms":2000,"poll_interval_ms":250,"http_timeout_ms":5000,"queue":{"max_unfinished_tasks":100000,"unfinished_tasks":"0","id":"61e5494b4cbf4c7126454a074a56412d","namespace_id":"68983a8088c43ef337aa69bbd349686e","name":"execution","paused":false,"max_concurrency":4,"rate_per_second":10,"revision":"1"},"attempted":24,"not_submitted":0,"accepted":24,"admission_errors":0,"verified_success":0,"unverified":24,"handler_calls":1,"duplicate_invocations":0,"unconfirmed_handler_calls":0,"worker_started":1,"worker_reconnects":0,"worker_renewals_confirmed":6,"admission":{"count":24,"p50_ms":12.970542,"p95_ms":20.052458,"p99_ms":22.639583,"max_ms":22.639583},"queue_wait":{"count":0,"p50_ms":null,"p95_ms":null,"p99_ms":null,"max_ms":null},"authorized_execution":{"count":0,"p50_ms":null,"p95_ms":null,"p99_ms":null,"max_ms":null},"task_completion":{"count":0,"p50_ms":null,"p95_ms":null,"p99_ms":null,"max_ms":null},"errors":{"INVOCATION_MISMATCH":23,"RUN_TIMEOUT":1,"TASK_NEEDS_REVIEW":1,"VERIFY_TIMEOUT":23},"complete":false}

View File

@@ -0,0 +1,55 @@
{
"date_local": "2026-09-20",
"timezone": "Asia/Shanghai",
"test_go": "go1.25.14",
"declared_go": "1.27.1",
"temporary_modfile": true,
"mysql": "8.4.10",
"innodb_flush_log_at_trx_commit": 1,
"sync_binlog": 1,
"mysql_global_transaction_isolation": "REPEATABLE-READ",
"orbit_transaction_isolation": "READ COMMITTED",
"mysql_max_connections": 151,
"innodb_buffer_pool_size_bytes": 134217728,
"orbit_db_max_open": 20,
"orbit_db_max_idle": 5,
"docker_vm_cpus": 12,
"docker_vm_memory_bytes": 12529274880,
"architecture": "arm64",
"orbit_processes": 1,
"mysql_nodes": 1,
"worker_processes": 1,
"worker_connections_normal": 2,
"worker_capacity_each": 4,
"queue_max_concurrency": 4,
"queue_rate_per_second": 10,
"metrics_enabled": false,
"cpu_memory_limits": "No dedicated limits; shared local Docker VM, other workloads possible",
"profiles_in_order": [
"short",
"mixed",
"long",
"deadline"
],
"prior_task_counts": [
0,
96,
192,
198
],
"fresh_disposable_database": true,
"network": "Go runner shares MySQL container network namespace; loopback HTTP/WSS and MySQL",
"schema_verification": {
"schema_version": 28,
"migration_count": 28,
"foreign_key_count": 0,
"required_index_count": 6,
"complete": true
},
"source_sha256": {
"sdk/go/cmd/orbit-exec-load/main.go": "bcaecce6be9fe8aca7a0d93b4671cbc460b1083232a77d13a04642a96ae45d81",
"sdk/go/cmd/orbit-exec-load/measure.go": "ea0a22e6598e12e175f281fd45d511db32e241e532f5bdcf40ca615392fa586e",
"sdk/go/cmd/orbit-exec-load/measure_test.go": "bda2ce1e946745e149c7471462d511ad3bcf66352a8d14fab57b2aa1ef280c3d",
"sdk/go/cmd/orbit-exec-load/report.go": "3d1da9acc1e63142bd3b4b37041d609e61e172eef56ff27467f1803dee857272"
}
}

View File

@@ -0,0 +1 @@
{"run_id":"980e0bccdca1cb9fbb1bdcc78536cc90","go_version":"go1.25.14","goos":"linux","goarch":"arm64","started_at":"2026-09-19T18:24:34.92203642Z","admission_finished_at":"2026-09-19T18:24:34.965149878Z","finished_at":"2026-09-19T18:25:48.023298384Z","requests":6,"concurrency":3,"workers":2,"capacity_per_worker":4,"durations_ms":[35000],"run_timeout_ms":120000,"poll_interval_ms":250,"http_timeout_ms":5000,"queue":{"max_unfinished_tasks":100000,"unfinished_tasks":"0","id":"61e5494b4cbf4c7126454a074a56412d","namespace_id":"68983a8088c43ef337aa69bbd349686e","name":"execution","paused":false,"max_concurrency":4,"rate_per_second":10,"revision":"1"},"attempted":6,"not_submitted":0,"accepted":6,"admission_errors":0,"verified_success":6,"unverified":0,"handler_calls":6,"duplicate_invocations":0,"unconfirmed_handler_calls":0,"worker_started":6,"worker_reconnects":0,"worker_renewals_confirmed":18,"admission":{"count":6,"p50_ms":13.193791,"p95_ms":28.028083,"p99_ms":28.028083,"max_ms":28.028083},"queue_wait":{"count":6,"p50_ms":1058.772,"p95_ms":38015.493,"p99_ms":38015.493,"max_ms":38015.493},"authorized_execution":{"count":6,"p50_ms":35013.932,"p95_ms":35024.585,"p99_ms":35024.585,"max_ms":35024.585},"task_completion":{"count":6,"p50_ms":36067.492,"p95_ms":73040.078,"p99_ms":73040.078,"max_ms":73040.078},"errors":{},"complete":true}

View File

@@ -0,0 +1 @@
{"run_id":"e78c366e6d6acb6cce8159dae900e8ca","go_version":"go1.25.14","goos":"linux","goarch":"arm64","started_at":"2026-09-19T18:23:52.454385095Z","admission_finished_at":"2026-09-19T18:23:52.759812553Z","finished_at":"2026-09-19T18:24:34.90756817Z","requests":96,"concurrency":8,"workers":2,"capacity_per_worker":4,"durations_ms":[0,100,1000],"run_timeout_ms":120000,"poll_interval_ms":250,"http_timeout_ms":5000,"queue":{"max_unfinished_tasks":100000,"unfinished_tasks":"0","id":"61e5494b4cbf4c7126454a074a56412d","namespace_id":"68983a8088c43ef337aa69bbd349686e","name":"execution","paused":false,"max_concurrency":4,"rate_per_second":10,"revision":"1"},"attempted":96,"not_submitted":0,"accepted":96,"admission_errors":0,"verified_success":96,"unverified":0,"handler_calls":96,"duplicate_invocations":0,"unconfirmed_handler_calls":0,"worker_started":96,"worker_reconnects":0,"worker_renewals_confirmed":0,"admission":{"count":96,"p50_ms":23.680834,"p95_ms":36.472167,"p99_ms":40.274167,"max_ms":40.274167},"queue_wait":{"count":96,"p50_ms":20883.756,"p95_ms":38754.793,"p99_ms":41024.973,"max_ms":41024.973},"authorized_execution":{"count":96,"p50_ms":109.912,"p95_ms":1021.918,"p99_ms":1042.773,"max_ms":1042.773},"task_completion":{"count":96,"p50_ms":20898.154,"p95_ms":39775.854,"p99_ms":42047.09,"max_ms":42047.09},"errors":{},"complete":true}

View File

@@ -0,0 +1 @@
{"run_id":"e16f23365b9accaef3ce8b41349d77ea","go_version":"go1.25.14","goos":"linux","goarch":"arm64","started_at":"2026-09-19T18:23:38.326433797Z","admission_finished_at":"2026-09-19T18:23:38.671806422Z","finished_at":"2026-09-19T18:23:52.44758097Z","requests":96,"concurrency":8,"workers":2,"capacity_per_worker":4,"durations_ms":[0],"run_timeout_ms":120000,"poll_interval_ms":250,"http_timeout_ms":5000,"queue":{"max_unfinished_tasks":100000,"unfinished_tasks":"0","id":"61e5494b4cbf4c7126454a074a56412d","namespace_id":"68983a8088c43ef337aa69bbd349686e","name":"execution","paused":false,"max_concurrency":4,"rate_per_second":10,"revision":"1"},"attempted":96,"not_submitted":0,"accepted":96,"admission_errors":0,"verified_success":96,"unverified":0,"handler_calls":96,"duplicate_invocations":0,"unconfirmed_handler_calls":0,"worker_started":96,"worker_reconnects":0,"worker_renewals_confirmed":0,"admission":{"count":96,"p50_ms":26.13175,"p95_ms":38.935083,"p99_ms":54.67775,"max_ms":54.67775},"queue_wait":{"count":96,"p50_ms":5951.689,"p95_ms":12805.411,"p99_ms":13752.092,"max_ms":13752.092},"authorized_execution":{"count":96,"p50_ms":10.405,"p95_ms":23.504,"p99_ms":28.838,"max_ms":28.838},"task_completion":{"count":96,"p50_ms":5959.781,"p95_ms":12813.065,"p99_ms":13768.327,"max_ms":13768.327},"errors":{},"complete":true}

View File

@@ -0,0 +1,71 @@
# P6:真实 Worker 任务执行测量
日期:2026-09-20(Asia/Shanghai,原始报告时间为UTC)。新增独立命令 `sdk/go/cmd/orbit-exec-load`,保留原 `orbit-load` 的纯受理边界。完整参数、权限、错误退出、分母和时钟定义见[执行测量手册](../api/execution-load.md)。本批交付短/混合/中长任务的可运行测量及正确性核验,不代表生产容量验收。
## 实现和核验
负载程序在业务侧独立SDK模块运行,与Orbit服务进程分离,只使用HTTP/WSS公共接口;没有数据库驱动或服务端内部依赖。每次使用独立处理器、固定序号/时长/输入、唯一提交键。HTTP提交不自动重试,任务最多一次尝试,Worker按现有协议心跳、续租、重连和收尾。
成功数量来自持久化任务及尝试历史的读取,逐项核验状态、输入/结果、队列/版本/业务键、单次尝试、授权/结束时间及单次处理器调用。SDK收到控制确认、处理器返回nil和本地事件都不能单独计为成功。截止或任一错配必须以 `complete=false` 和非零退出码结束;没有完成样本时百分位为null。
## 最终环境
原始配置及当前测量源码SHA-256保存在[环境清单](data/phase-6-execution-load/environment.json)。
| 项目 | 实际值 |
| --- | --- |
| 主机/运行环境 | macOS arm64、Docker Linux/arm64;共享VM可见12 CPU、12529274880字节内存,未独占硬件 |
| 工具链 | 实际 `go1.25.14`,仅临时modfile替换Go指令;仓库仍声明Go 1.27.1 |
| 拓扑 | 一次性MySQL 8.4.10,1个Orbit进程,1个负载进程内2条Worker连接,每条capacity=4 |
| 网络 | Go运行容器共享MySQL容器网络命名空间;HTTP/WSS和MySQL均走loopback |
| MySQL | `innodb_flush_log_at_trx_commit=1`、`sync_binlog=1`、buffer pool=128MiB、max_connections=151 |
| 隔离级别 | MySQL全局REPEATABLE-READ;Orbit写事务显式READ COMMITTED |
| Orbit | 数据库连接池max_open=20、max_idle=5;鉴权和持久事件/审计启用;metrics未启用 |
| 队列 | max_concurrency=4、rate_per_second=10、max_unfinished_tasks=100000;工具未更改配置 |
| 核验 | 每个HTTP请求5秒上限、单核验器250ms间隔,核验器最多与提交并发数相同 |
| 数据量 | 空库初始化;short/mixed/long/deadline顺序运行,开始时已有任务数分别0/96/192/198;各运行身份隔离 |
最后 `orbit-admin verify` 返回 schema=28、migration_count=28、foreign_key_count=0、required_index_count=6、complete=true。测试容器退出后销毁一次性数据库和凭据。
## 原始结果
前三组均在2分钟整体预算内完整通过,退出0。三个阶段分布的分母分别为96、96、6;都没有重复处理器调用、无回执调用或Worker重连。
| 样本 | 任务/处理器时长 | 受理p99 ms | 排队p99 ms | 授权执行p99 ms | 任务完成p99 ms | 持久成功/计划数 |
| --- | --- | --- | --- | --- | --- | --- |
| [short原始JSON](data/phase-6-execution-load/short.json) | 96项,0ms | 54.678 | 13752.092 | 28.838 | 13768.327 | 96/96 |
| [mixed原始JSON](data/phase-6-execution-load/mixed.json) | 96项,0/100/1000ms循环,各32项 | 40.274 | 41024.973 | 1042.773 | 42047.090 | 96/96 |
| [long原始JSON](data/phase-6-execution-load/long.json) | 6项,每项35000ms | 28.028 | 38015.493 | 35024.585 | 73040.078 | 6/6 |
长任务总计18次续租确认,最终仍为每项一次尝试、一次调用。该数字验证了此次实际续租路径,不表示节点/网络故障已经发生。
排队分布包含当前4并发/每秒10次开始的队列约束及调度扫描;Worker声明8个槽不会绕过队列限制。这组数字不能视为去掉配额后的最大吞吐。
`authorized_execution` 和 `task_completion` 用持久化数据库时间戳计算;终点是结束事务内部取时点,未包含其后COMMIT及确认延迟。已提交事实由后续读取核验。客户端核验顺序不计入这些分布,但查询负载会影响服务资源消耗。没有收集独占CPU/内存/磁盘/锁等待曲线,也没有多轮稳态和生产指标开启后的对照。
## 失败语义实测
[deadline原始JSON](data/phase-6-execution-load/deadline.json):24项、4并发提交、1个Worker/1个槽、每项1秒、整体预算2秒。命令按预期退出1,`accepted=24`、`verified_success=0`、`unverified=24`、`complete=false`;本地只有1次处理器调用。读取观察到1项NEEDS_REVIEW,23项未能在截止前验证,三种完成阶段的分布均为 `count=0` / 百分位null。
错误计数保留 `RUN_TIMEOUT`、`TASK_NEEDS_REVIEW`、`VERIFY_TIMEOUT` 和 `INVOCATION_MISMATCH`。这些计数含运行级及交叠的核验错误,不能求和当成失败任务总数。工具没有删除、强制成功或重新提交这些任务;未观察到终态不等于数据库确认失败,剩余状态留在原身份下供核查。
## 复现和回归
按[手册](../api/execution-load.md)准备一次性数据库、当前迁移、带Worker权限的凭据及真实Orbit进程,然后在 `sdk/go` 运行:
```sh
go run ./cmd/orbit-exec-load -requests 96 -concurrency 8 -workers 2 -capacity 4 -durations 0ms -run-timeout 2m
go run ./cmd/orbit-exec-load -requests 96 -concurrency 8 -workers 2 -capacity 4 -durations 0ms,100ms,1s -run-timeout 2m
go run ./cmd/orbit-exec-load -requests 6 -concurrency 3 -workers 2 -capacity 4 -durations 35s -run-timeout 2m
# 此项应失败;必须读取JSON确认是预算不足,不应仅判断任意非零退出。
go run ./cmd/orbit-exec-load -requests 24 -concurrency 4 -workers 1 -capacity 1 -durations 1s -run-timeout 2s
```
本轮在上述Docker环境使用临时modfile构建真实Linux二进制,执行了四条等价命令及下列检查:
- SDK全模块 `go test -race ./...`、`go vet ./...`、`go build ./...` 通过;没有设置原SDK集成凭据的普通单测不冒充全量集成。
- 新增单测覆盖:错配/缺失/空字段结果、未知效果、第二次尝试、悬空历史、时间逆序、提交超时/429不重报、整次取消、核查不算成功、读取失败、重复调用、无权限预检及错误脱敏。
- SDK完整依赖图218项中,服务端内部/模型/模块和MySQL驱动依赖均为0。
- `scripts/test-mysql.sh` 已加入6项真实执行命令冒烟,shell语法检查通过。本轮运行的是四个独立真实样本,未重新执行整个 `make integration`。
当前不把临时Go 1.25兼容回归升级为声明Go 1.27.1的正式发布结论。下一批继续定时集中触发、流程推进、长期积压、慢消费者/重连风暴及资源曲线,生产HA、复制切换与RPO/RTO仍需目标拓扑证据。

View File

@@ -17,6 +17,7 @@
| SDK Worker/Event/Workflow 子进程故障 | 同一共享网络命名空间;容器内构建 Orbit 二进制;SDK `TestIntegration(Worker\|Event\|Workflow)Process` | PASS,136.394 秒;派发未送达、租约接管、ACK 提交回执丢失、重试未知结果、计划/优先级/键并发、流程暂停全停接管均通过 |
| SDK 应用配额子进程故障 | 独立双命名空间应用配额凭据;共享网络命名空间;`TestIntegrationWorkerProcessApplicationBackpressure` | PASS,1.069 秒;重启后共享额度、原回执和跨命名空间背压保持 |
| Orbit HTTP/metrics 子进程 | 同一共享网络命名空间;`TestIntegrationMetricsProcess`;metrics 启用/禁用各一组 | PASS,3.081 秒;监听隔离、隐私、后台采样和优雅退出均通过 |
| 真实Worker执行测量 | `orbit-exec-load`;最终短/混合/中长及截止不足四组,环境及原始JSON见[测量报告](phase-6-execution-load.md) | 96+96+6项全部逐项核验,长任务18次续租;24项截止负例按预期非零退出。SDK全模块竞态/vet/build通过,生产容量未验收 |
## 当前环境仍未覆盖