nexus/ProxMenux
2
0
Fork 0
mirror of https://github.com/MacRimi/ProxMenux.git synced 2026-04-18 01:52:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update health_monitor.py

Browse Source
This commit is contained in:
MacRimi
2026-02-27 20:07:01 +01:00
parent 9841e92634
commit 828c0f66a6
1 changed files with 29 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
AppImage/scripts/health_monitor.py
View File

@@ -1712,21 +1712,22 @@ class HealthMonitor:
display = f"VM {vmid} ({vm_name})" if vm_name else f"VM {vmid}"
error_key = f'vm_{vmid}'
if error_key not in vm_details:
health_persistence.record_error(
rec_result = health_persistence.record_error(
error_key=error_key,
category='vms',
severity='WARNING',
reason=f'{display}: QMP command failed or timed out.\n{line.strip()[:200]}',
details={'id': vmid, 'vmname': vm_name, 'type': 'VM'}
)
issues.append(f'{display}: QMP communication issue')
vm_details[error_key] = {
'status': 'WARNING',
'reason': f'{display}: QMP command failed or timed out',
'id': vmid,
'vmname': vm_name,
'type': 'VM'
}
if not rec_result or rec_result.get('type') != 'skipped_acknowledged':
issues.append(f'{display}: QMP communication issue')
vm_details[error_key] = {
'status': 'WARNING',
'reason': f'{display}: QMP command failed or timed out',
'id': vmid,
'vmname': vm_name,
'type': 'VM'
}
continue
# Container errors (including startup issues via vzstart)
@@ -1746,20 +1747,21 @@ class HealthMonitor:
reason = 'Startup error'
# Record persistent error
health_persistence.record_error(
rec_result = health_persistence.record_error(
error_key=error_key,
category='vms',
severity='WARNING',
reason=reason,
details={'id': ctid, 'type': 'CT'}
)
issues.append(f'CT {ctid}: {reason}')
vm_details[error_key] = {
'status': 'WARNING',
'reason': reason,
'id': ctid,
'type': 'CT'
}
if not rec_result or rec_result.get('type') != 'skipped_acknowledged':
issues.append(f'CT {ctid}: {reason}')
vm_details[error_key] = {
'status': 'WARNING',
'reason': reason,
'id': ctid,
'type': 'CT'
}
# Generic failed to start for VMs and CTs
if any(keyword in line_lower for keyword in ['failed to start', 'cannot start', 'activation failed', 'start error']):
@@ -1790,21 +1792,22 @@ class HealthMonitor:
display = f"{vm_type} {vmid_ctid} ({vm_name})"
reason = f'{display}: Failed to start\n{line.strip()[:200]}'
# Record persistent error
health_persistence.record_error(
rec_result = health_persistence.record_error(
error_key=error_key,
category='vms',
severity='CRITICAL',
reason=reason,
details={'id': vmid_ctid, 'vmname': vm_name, 'type': vm_type}
)
issues.append(f'{display}: Failed to start')
vm_details[error_key] = {
'status': 'CRITICAL',
'reason': reason,
'id': vmid_ctid,
'vmname': vm_name,
'type': vm_type
}
if not rec_result or rec_result.get('type') != 'skipped_acknowledged':
issues.append(f'{display}: Failed to start')
vm_details[error_key] = {
'status': 'CRITICAL',
'reason': reason,
'id': vmid_ctid,
'vmname': vm_name,
'type': vm_type
}
# Build checks dict from vm_details
checks = {}