From 08db3580a76ca3583ed73da93a79652ad99a4bf1 Mon Sep 17 00:00:00 2001
From: OG T <ogt@WOOOMacMiniM4.local>
Date: Thu, 9 Apr 2026 13:53:13 +0800
Subject: [PATCH] =?UTF-8?q?fix(monitoring):=20=E4=BF=AE=E5=BE=A9=20110=20?=
 =?UTF-8?q?=E4=B8=BB=E6=A9=9F=20CPU=20=E9=AB=98=E8=B2=A0=E8=BC=89?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

根因 1: cadvisor 持續掃描 overlay2 磁碟用量 (每次 1-4s × N 容器)
  → 加 --disable_metrics=disk,diskIO,tcp,udp,percpu,sched,process
  → --housekeeping_interval=30s --docker_only=true
  → CPU 從 239% 降到 <1%

根因 2: node_exporter scrape_timeout 預設 10s，高 load 下超時→broken pipe→瘋狂重試
  → 加 scrape_interval: 30s / scrape_timeout: 25s
  → CPU 從 48% 降到 0%

整體 load average: 20 → 9

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 k8s/monitoring/docker-compose-110.yml | 138 ++++++++++++++++++++++++++
 k8s/monitoring/prometheus.yml         |   2 +
 2 files changed, 140 insertions(+)
 create mode 100644 k8s/monitoring/docker-compose-110.yml

diff --git a/k8s/monitoring/docker-compose-110.yml b/k8s/monitoring/docker-compose-110.yml
new file mode 100644
index 00000000..3116b227
--- /dev/null
+++ b/k8s/monitoring/docker-compose-110.yml
@@ -0,0 +1,138 @@
+version: '3.8'
+
+services:
+  cadvisor:
+    image: gcr.io/cadvisor/cadvisor:latest
+    container_name: cadvisor
+    restart: unless-stopped
+    command:
+      - --logtostderr
+      - --disable_metrics=disk,diskIO,tcp,udp,percpu,sched,process
+      - --housekeeping_interval=30s
+      - --max_housekeeping_interval=60s
+      - --docker_only=true
+    ports:
+      - "9180:8080"
+    volumes:
+      - /:/rootfs:ro
+      - /var/run:/var/run:ro
+      - /sys:/sys:ro
+      - /var/lib/docker/:/var/lib/docker:ro
+      - /dev/disk/:/dev/disk:ro
+      - /etc/localtime:/etc/localtime:ro
+    environment:
+      - TZ=Asia/Taipei
+    privileged: true
+    devices:
+      - /dev/kmsg
+    networks:
+      - monitoring
+
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: prometheus
+    restart: unless-stopped
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
+      - ./alerts.yml:/etc/prometheus/alerts.yml:ro
+      - prometheus_data:/prometheus
+      - /etc/localtime:/etc/localtime:ro
+    environment:
+      - TZ=Asia/Taipei
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=30d'
+      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
+      - '--web.console.templates=/usr/share/prometheus/consoles'
+      - '--web.enable-lifecycle'
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    networks:
+      - monitoring
+
+  grafana:
+    image: grafana/grafana:latest
+    container_name: grafana
+    restart: unless-stopped
+    ports:
+      - "3002:3000"
+    environment:
+      - GF_SECURITY_ADMIN_USER=admin
+      - GF_SECURITY_ADMIN_PASSWORD=WoooTech2026
+      - GF_SERVER_ROOT_URL=http://192.168.0.110:3002
+      - TZ=Asia/Taipei
+    volumes:
+      - grafana_data:/var/lib/grafana
+      - /etc/localtime:/etc/localtime:ro
+    networks:
+      - monitoring
+    depends_on:
+      - prometheus
+
+  blackbox-exporter:
+    image: prom/blackbox-exporter:latest
+    container_name: blackbox-exporter
+    restart: unless-stopped
+    ports:
+      - "9115:9115"
+    volumes:
+      - ./blackbox.yml:/etc/blackbox_exporter/config.yml:ro
+      - /etc/localtime:/etc/localtime:ro
+    environment:
+      - TZ=Asia/Taipei
+    command:
+      - '--config.file=/etc/blackbox_exporter/config.yml'
+    networks:
+      - monitoring
+
+  alertmanager:
+    image: prom/alertmanager:latest
+    container_name: alertmanager
+    restart: unless-stopped
+    ports:
+      - "9093:9093"
+    volumes:
+      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
+      - alertmanager_data:/alertmanager
+      - /etc/localtime:/etc/localtime:ro
+    environment:
+      - TZ=Asia/Taipei
+    command:
+      - '--config.file=/etc/alertmanager/alertmanager.yml'
+      - '--storage.path=/alertmanager'
+    networks:
+      - monitoring
+
+  # === Phase 5: GitHub Exporter (OPS.176) ===
+  github-exporter:
+    image: promhippie/github-exporter:latest
+    container_name: github-exporter
+    restart: unless-stopped
+    ports:
+      - '9504:9504'
+    environment:
+      - GITHUB_EXPORTER_TOKEN=${GITHUB_TOKEN}
+      - GITHUB_EXPORTER_REPOS=owenhytsai/wooo-aiops,owenhytsai/clawbot-v5
+      - GITHUB_EXPORTER_LOG_LEVEL=info
+    networks:
+      - monitoring
+    labels:
+      - 'com.wooo.service=github-exporter'
+      - 'com.wooo.phase=phase-5'
+    logging:
+      driver: json-file
+      options:
+        max-size: '10m'
+        max-file: '3'
+
+networks:
+  monitoring:
+    driver: bridge
+
+volumes:
+  prometheus_data:
+  grafana_data:
+  alertmanager_data:
diff --git a/k8s/monitoring/prometheus.yml b/k8s/monitoring/prometheus.yml
index cffef73a..5f716740 100644
--- a/k8s/monitoring/prometheus.yml
+++ b/k8s/monitoring/prometheus.yml
@@ -22,6 +22,8 @@ scrape_configs:
 
   # === Node Exporters (5 台主機) ===
   - job_name: "node-exporter-110"
+    scrape_interval: 30s
+    scrape_timeout: 25s
     static_configs:
       - targets: ["192.168.0.110:9100"]
         labels: