LotusGuild/hwmonDaemon
2
0
Fork 0
Code Issues 3 Pull Requests Actions Packages Projects Releases Wiki Activity

Adjusted network logic, made map of both subnet ip

Browse Source
This commit is contained in:
Jared Vititoe
2024-12-04 21:14:47 -05:00
parent 8e5cda287d
commit 0b26b67019
2 changed files with 43 additions and 33 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
hwmonDaemon.py
View File

@ -5,6 +5,8 @@ import json
import datetime
import requests
import psutil
import socket
import subprocess
from typing import Dict, Any, List
class SystemHealthMonitor:
@ -62,7 +64,7 @@ class SystemHealthMonitor:
priority = "P4" # Default to low priority
categories = set() # To accumulate unique categories
issue_types = set() # To accumulate unique issue types
hostname = "medium1" # Replace with actual logic to determine the hostname
hostname = socket.gethostname()
action_type = "[auto]"
scope = "[cluster-wide]"
environment = "[production]"
@ -246,7 +248,7 @@ class SystemHealthMonitor:
def _check_drive_smart_status(self) -> List[Dict[str, Any]]:
"""
Check SMART status of drives
Check SMART status of drives using smartctl.
:return: List of SMART status for drives
"""
@ -254,38 +256,27 @@ class SystemHealthMonitor:
try:
for disk in psutil.disk_partitions():
drive = disk.device
# Example placeholder: SMART status retrieval would need smartmontools
drives.append({'drive': drive, 'status': 'HEALTHY'})
return drives
try:
# Use smartctl to check the drive's SMART status
result = subprocess.run(
['smartctl', '-H', drive],
stdout=subprocess.PIPE,
stderr=subprocess.PIPE,
text=True
)
output = result.stdout + result.stderr
status = 'HEALTHY' if 'PASSED' in output else 'UNHEALTHY'
drives.append({'drive': drive, 'status': status})
except Exception as e:
drives.append({'drive': drive, 'status': 'ERROR', 'error': str(e)})
except Exception as e:
print(f"SMART status check failed: {e}")
return [{'error': str(e)}]
def _check_system_temperatures(self) -> Dict[str, Any]:
"""
Check system temperatures and return health metrics
:return: System temperature metrics
"""
try:
temperatures = psutil.sensors_temperatures()
if not temperatures:
return {'error': 'No temperature data available'}
temp_metrics = {}
for name, entries in temperatures.items():
temp_metrics[name] = [
{'label': entry.label, 'current': entry.current, 'high': entry.high, 'critical': entry.critical}
for entry in entries
]
return temp_metrics
except Exception as e:
print(f"Temperature health check failed: {e}")
return {'error': str(e)}
return drives
def _check_network_status(self) -> Dict[str, Any]:
"""
Check network connectivity between nodes
Check network connectivity between nodes and include detailed identifiers.
:return: Network health report
"""
@ -294,8 +285,21 @@ class SystemHealthMonitor:
'ceph_network': {'status': 'UNKNOWN', 'issues': []}
}
management_ips = ['10.10.10.2', '10.10.10.10', '10.10.10.4', '10.10.10.8', '10.10.10.9']
ceph_ips = ['10.10.90.10', '10.10.90.4', '10.10.90.3', '10.10.90.2', '10.10.90.6']
# IP-to-hostname mapping
management_mapping = {
'10.10.10.2': 'large1',
'10.10.10.10': 'medium1',
'10.10.10.4': 'medium2',
'10.10.10.8': 'micro1',
'10.10.10.9': 'micro2'
}
ceph_mapping = {
'10.10.90.10': 'large1',
'10.10.90.4': 'medium1',
'10.10.90.3': 'medium2',
'10.10.90.2': 'micro1',
'10.10.90.6': 'micro2'
}
def _ping_device(ip: str) -> bool:
try:
@ -306,17 +310,23 @@ class SystemHealthMonitor:
return False
# Check management network
management_ips = list(management_mapping.keys())
for source_ip in management_ips:
for target_ip in management_ips:
if source_ip != target_ip and not _ping_device(target_ip):
issue = f"{source_ip} cannot reach {target_ip} in Management Network"
source_host = management_mapping[source_ip]
target_host = management_mapping[target_ip]
issue = f"{source_host} ({source_ip}) cannot reach {target_host} ({target_ip}) in Management Network"
network_health['management_network']['issues'].append(issue)
# Check Ceph network
ceph_ips = list(ceph_mapping.keys())
for source_ip in ceph_ips:
for target_ip in ceph_ips:
if source_ip != target_ip and not _ping_device(target_ip):
issue = f"{source_ip} cannot reach {target_ip} in Ceph Network"
source_host = ceph_mapping[source_ip]
target_host = ceph_mapping[target_ip]
issue = f"{source_host} ({source_ip}) cannot reach {target_host} ({target_ip}) in Ceph Network"
network_health['ceph_network']['issues'].append(issue)
# Update statuses