yeuimu
7c323e9a3f
- 核验日报: 先报订单数量(远程vs本地, verify 修复后重数 verifyReport.post)/商品行数一致性, 再报状态不符单数; SDS 统计口径排除'售后'与本地对称 - OCR: Orders 加 ocrProcessedAt 列(写入自动盖时间戳), 日报报'今日处理 X · 识别失败 Y'(db.count_ocr_today) - 失败任务: check_prefect_failures 补 workflow 名, 日报/设备报列 run 名+状态+时间 - 设备日报: 新增 metrics-agent 侧车(每5分钟采样内存/swap/GPU+每日 du 快照), 报告改 平均/峰值/最低 + 总体/根目录/home 余量 + 增长最快目录 + GPU 温度; 采样缺失降级瞬时值 - Dockerfile 加 tzdata(TZ=Asia/Shanghai); du 用实际占块且容错 rc=1
61 lines
1.6 KiB
YAML
61 lines
1.6 KiB
YAML
services:
|
|
prefect-server:
|
|
image: prefecthq/prefect:3-python3.12
|
|
container_name: prefect-server
|
|
command: prefect server start --host 0.0.0.0
|
|
environment:
|
|
PREFECT_UI_API_URL: http://192.168.124.92:4200/api
|
|
TZ: Asia/Shanghai
|
|
ports:
|
|
- "4200:4200"
|
|
volumes:
|
|
- prefect-data:/root/.prefect
|
|
restart: unless-stopped
|
|
|
|
prefect-worker:
|
|
build: .
|
|
container_name: prefect-worker
|
|
environment:
|
|
PREFECT_API_URL: http://prefect-server:4200/api
|
|
TZ: Asia/Shanghai
|
|
depends_on:
|
|
- prefect-server
|
|
volumes:
|
|
# 设备监控(device-check flow):宿主机磁盘使用率 + Docker 容器状态 + 指标采样
|
|
- /var/run/docker.sock:/var/run/docker.sock
|
|
- /:/host:ro
|
|
- ./data/metrics:/data/metrics:ro
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
# GPU 监控(nvidia-smi);依赖宿主机 nvidia-container-toolkit
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|
|
|
|
# 宿主机指标采样侧车:每 5 分钟写内存/swap/GPU,每日 du 快照(供 device-check 日报)
|
|
metrics-agent:
|
|
build: .
|
|
container_name: metrics-agent
|
|
command: python /opt/metrics_agent.py
|
|
environment:
|
|
TZ: Asia/Shanghai
|
|
METRICS_DIR: /data/metrics
|
|
volumes:
|
|
- /:/host:ro
|
|
- ./data/metrics:/data/metrics
|
|
- ./scripts/metrics_agent.py:/opt/metrics_agent.py:ro
|
|
deploy:
|
|
resources:
|
|
reservations:
|
|
devices:
|
|
- driver: nvidia
|
|
count: all
|
|
capabilities: [gpu]
|
|
restart: unless-stopped
|
|
|
|
volumes:
|
|
prefect-data:
|