way/pigway-raspberry-pi-agent
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 10 Wiki Activity

fix: validate atomic configuration updates and expire stale monitoring snapshots

Browse Source
This commit is contained in:
way
2026-10-18 18:15:22 +08:00
parent c82d9ab3c2
commit 9b83937d60
10 changed files with 244 additions and 85 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/pigway_pi_control.py
+7 -6
View File
@@ -1,7 +1,7 @@
#!/usr/bin/env python3
import time,socket,subprocess,configparser,signal,re,argparse,json,os,platform
from pathlib import Path
APP_VERSION="3.11.2"
APP_VERSION="3.11.3"
import sys
sys.path.append("/usr/local/share/pigway-pi-control")
from plugin_api import Publisher,registered,discover
@@ -185,7 +185,7 @@ def internet():
except: return False
def load_cfg():
c=configparser.ConfigParser(); c.read(CFG)
c=configparser.ConfigParser(interpolation=None); c.read(CFG)
watches=[]
if c.has_section("services"):
for label,target in c["services"].items():
@@ -331,10 +331,10 @@ def update_active_alerts(cpu,temp,mem,disk,sample_elapsed=0.0):
else: alert_manager.clear("MEMORY_HIGH")
if disk is not None:
if disk>=DISK_CRIT:
alert_manager.request("DISK_CRITICAL",2,"DISK CRITICAL",f"USED {disk:.1f}%","FREE < 5%","CHECK STORAGE")
alert_manager.request("DISK_CRITICAL",2,"DISK CRITICAL",f"USED {disk:.1f}%",f"USED >= {DISK_CRIT:g}%","CHECK STORAGE")
alert_manager.clear("DISK_HIGH")
elif disk>=DISK_HIGH:
alert_manager.request("DISK_HIGH",1,"DISK SPACE LOW",f"USED {disk:.1f}%","FREE < 10%","CHECK STORAGE")
alert_manager.request("DISK_HIGH",1,"DISK SPACE LOW",f"USED {disk:.1f}%",f"USED >= {DISK_HIGH:g}%","CHECK STORAGE")
alert_manager.clear("DISK_CRITICAL")
else:
alert_manager.clear("DISK_HIGH"); alert_manager.clear("DISK_CRITICAL")
@@ -408,13 +408,14 @@ class AlertManager:
"first_seen":old["first_seen"] if old else now,"metadata":metadata or {}}
value["last_changed"]=old["last_changed"] if old and all(old[k]==v for k,v in value.items()) else now
self.requests[request_id]=value
if old is None:log("WARN","ALERT_ACTIVE",alert=request_id,severity=severity,detail=l2)
if old is None or old["severity"]!=severity:
log({1:"WARN",2:"CRITICAL",3:"EMERGENCY"}[severity],"ALERT_ACTIVE" if old is None else "ALERT_CHANGED",alert=request_id,severity=severity,detail=l2)
def clear(self,request_id):
if self.requests.pop(request_id,None) is not None:log("INFO","ALERT_RECOVERED",alert=request_id)
def status_snapshot(self):
values=sorted(self.requests.values(),key=lambda a:(-a["priority"],a["first_seen"],a["id"]))
values=sorted(self.requests.values(),key=lambda a:(-a["severity"],-a["priority"],a["first_seen"],a["id"]))
return {"owner":values[0]["id"] if values else "NORMAL_HOME","alerts":values}