fix(monitoring): classify host memory pressure accurately

This commit is contained in:
ogt
2026-07-15 06:15:13 +08:00
parent 89595a7d8d
commit 5c0c5f6da2
11 changed files with 76 additions and 25 deletions

View File

@@ -104,18 +104,18 @@ PLAYBOOK_TEMPLATES = [
"severity_range": ["P2", "P3"],
},
{
"name": "節點記憶體不足清理 Cache",
"alert_type": "HostOutOfMemory",
"description": "主機記憶體不足,清理 Page Cache 釋放空間",
"name": "節點記憶體壓力唯讀診斷",
"alert_type": "HostMemoryUsageHigh",
"description": "主機 MemAvailable 偏低;先驗證 OOM、swap、程序與服務狀態不做破壞性快取清理",
"category": "infrastructure",
"repair_steps": [
{"command": "ssh {target} 'free -h'", "purpose": "確認記憶體狀況"},
{"command": "ssh {target} 'sudo sync && sudo sysctl vm.drop_caches=3'", "purpose": "清理 Page Cache"},
{"command": "ssh {target} 'free -h'", "purpose": "確認記憶體已釋放"},
{"command": "ssh {target} 'free -h'", "purpose": "讀取 MemAvailable 與 swap 狀況"},
{"command": "ssh {target} \"awk '$1 == \\\"oom_kill\\\" { print }' /proc/vmstat\"", "purpose": "確認 kernel OOM kill 累計值"},
{"command": "ssh {target} 'ps aux --sort=-%mem | head -20'", "purpose": "讀取主要記憶體程序"},
],
"estimated_minutes": 5,
"symptom_alertnames": ["HostOutOfMemory", "NodeMemoryPressure"],
"severity_range": ["P1", "P2"],
"symptom_alertnames": ["HostMemoryUsageHigh", "HostOutOfMemory", "NodeMemoryPressure"],
"severity_range": ["P2", "P3"],
},
{
"name": "磁碟使用率過高 — 清理舊日誌",