Files
easyai-ai-gateway/deploy/kubernetes/easyai-ai-gateway-cluster-release.conf.example
T
wangbo edcbbd6a87 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。
2026-08-01 18:23:00 +08:00

40 lines
1.8 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
RELEASES_DIR=/var/lib/easyai-ai-gateway-cluster-release/releases
NAMESPACE=easyai
PUBLIC_BASE_URL=https://ai.51easyai.com
K3S_BIN=/usr/local/bin/k3s
DESIRED_STATE_DIR=/usr/local/share/easyai-ai-gateway-release/production
# Worker 容量只需修改本发布配置并执行获授权的 `capacity`,不再修改 Go 代码。
# 副本数属于 Deployment 配置,不能由容器内部环境变量改变;发布工具读取这两个变量并写入 replicas。
AI_GATEWAY_WORKER_REPLICAS_NINGBO=0
AI_GATEWAY_WORKER_REPLICAS_HONGKONG=2
AI_GATEWAY_ASYNC_WORKER_INSTANCE_HARD_LIMIT=24
AI_GATEWAY_ASYNC_WORKER_HARD_LIMIT=48
AI_GATEWAY_ASYNC_WORKER_GLOBAL_HARD_LIMIT=48
AI_GATEWAY_WORKER_MEMORY_REQUEST_MIB=1536
AI_GATEWAY_WORKER_CPU_REQUEST_MILLICORES=500
AI_GATEWAY_DATABASE_MAX_CONNS=32
AI_GATEWAY_API_DATABASE_MAX_CONNS=32
AI_GATEWAY_DATABASE_CRITICAL_MAX_CONNS=4
AI_GATEWAY_DATABASE_RIVER_MAX_CONNS=8
AI_GATEWAY_API_DATABASE_RIVER_MAX_CONNS=4
AI_GATEWAY_DATABASE_MIN_IDLE_CONNS=4
AI_GATEWAY_DATABASE_MAX_CONN_IDLE_SECONDS=30
AI_GATEWAY_MEDIA_MATERIALIZATION_CONCURRENCY=24
AI_GATEWAY_MEDIA_REQUEST_CONCURRENCY=24
AI_GATEWAY_WORKER_AUTOSCALING_ENABLED=false
AI_GATEWAY_WORKER_MIN_REPLICAS_NINGBO=0
AI_GATEWAY_WORKER_MIN_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
AI_GATEWAY_WORKER_DRAIN_TIMEOUT_SECONDS=600
AI_GATEWAY_NODE_MEMORY_TARGET_PERCENT=75
AI_GATEWAY_NODE_MEMORY_HARD_PERCENT=85
AI_GATEWAY_NODE_CPU_TARGET_PERCENT=70
AI_GATEWAY_POSTGRES_CONNECTION_BUDGET=150
# 2 个 API 池(2×32)加 2 个 capacity-controller 池(2×4)。
AI_GATEWAY_POSTGRES_NON_WORKER_CONNECTION_BUDGET=72