fix(worker): 拆分准入事务并收敛验收失败状态

将批量准入改为每任务独立事务,避免 P24 压测时 48 条任务共享长事务造成 transactionid 锁潮与 Worker 槽位空转。失败验收在保持 validation 的同时清理未提交任务,并记录精确压力门禁原因。统一生产 0+2 Worker 拓扑、运行时 ConfigMap 与发布配置,补充镜像预检诊断和回归测试。\n\n验证:Go 全量测试、go vet、真实 PostgreSQL 48 任务集成测试、迁移安全检查、发布脚本测试、bash -n、ShellCheck、Compose 配置均通过。
This commit is contained in:
2026-08-01 18:23:00 +08:00
parent 215b6b607f
commit edcbbd6a87
11 changed files with 194 additions and 100 deletions
@@ -46,12 +46,12 @@ data:
AI_GATEWAY_ASYNC_WORKER_GLOBAL_HARD_LIMIT: "48"
AI_GATEWAY_ASYNC_WORKER_REFRESH_INTERVAL_SECONDS: "5"
AI_GATEWAY_WORKER_AUTOSCALING_ENABLED: "false"
AI_GATEWAY_WORKER_REPLICAS_NINGBO: "1"
AI_GATEWAY_WORKER_REPLICAS_HONGKONG: "1"
AI_GATEWAY_WORKER_MIN_REPLICAS_NINGBO: "1"
AI_GATEWAY_WORKER_REPLICAS_NINGBO: "0"
AI_GATEWAY_WORKER_REPLICAS_HONGKONG: "2"
AI_GATEWAY_WORKER_MIN_REPLICAS_NINGBO: "0"
AI_GATEWAY_WORKER_MIN_REPLICAS_HONGKONG: "1"
AI_GATEWAY_WORKER_MAX_REPLICAS_NINGBO: "1"
AI_GATEWAY_WORKER_MAX_REPLICAS_HONGKONG: "1"
AI_GATEWAY_WORKER_MAX_REPLICAS_NINGBO: "0"
AI_GATEWAY_WORKER_MAX_REPLICAS_HONGKONG: "2"
AI_GATEWAY_WORKER_TARGET_OUTSTANDING_PER_REPLICA: "48"
AI_GATEWAY_WORKER_SCALE_UP_WINDOW_SECONDS: "20"
AI_GATEWAY_WORKER_SCALE_DOWN_STABILIZATION_SECONDS: "600"
@@ -434,7 +434,7 @@ metadata:
app.kubernetes.io/component: worker
app.kubernetes.io/part-of: easyai-ai-gateway
spec:
replicas: 1
replicas: 0
strategy:
type: RollingUpdate
rollingUpdate:
@@ -607,7 +607,7 @@ metadata:
app.kubernetes.io/component: worker
app.kubernetes.io/part-of: easyai-ai-gateway
spec:
replicas: 1
replicas: 2
strategy:
type: RollingUpdate
rollingUpdate: