andreas/heartbeat
Public Access
1
0
Fork 1
Code Issues Pull Requests Actions Packages Projects Releases 44 Wiki Activity

fix: agree: zpool ONLINE=OK, DEGRADED=WARNING, all else is CRITICAL

Browse Source
This commit is contained in:
Andreas Wrede
2026-05-08 17:18:41 -04:00
parent 12f7eb722b
commit b95f1a5bb7
4 changed files with 8 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/THRESHOLD_ALERTING.md
+2 -1
View File
@@ -269,7 +269,8 @@ zfs_monitor:
pools: pools:
'*': '*':
status: status:
critical: 1 warning: 1
critical: 2
operator: ">" operator: ">"
hysteresis: 0.0 hysteresis: 0.0
display: "ZFS pool {pool_name} is {health}" display: "ZFS pool {pool_name} is {health}"
hbd/config_thresholds_example.yaml
+2 -1
View File
@@ -144,7 +144,8 @@ thresholds:
pools: pools:
'*': '*':
status: status:
critical: 0 # Alert CRITICAL when pool is not ONLINE warning: 1 # Alert WARNING when pool is DEGRADED
critical: 2 # Alert CRITICAL when pool is SUSPENDED/FAULTED/UNAVAIL
operator: ">" operator: ">"
hysteresis: 0.0 # No hysteresis — a degraded pool is always critical hysteresis: 0.0 # No hysteresis — a degraded pool is always critical
display: "ZFS pool {pool_name} is {health}" display: "ZFS pool {pool_name} is {health}"
hbd/server/config.py
+2 -1
View File
@@ -109,7 +109,8 @@ THRESHOLD_DEFAULTS = {
'pools': { 'pools': {
'*': { '*': {
'status': { 'status': {
'critical': 1, # Alert if pool health is not ONLINE 'warning': 1,
'critical': 2,
'operator': '>', 'operator': '>',
'hysteresis': 0.0, 'hysteresis': 0.0,
'display': 'ZFS pool {pool_name} is {health}' 'display': 'ZFS pool {pool_name} is {health}'
hbd/server/threshold.py
+2 -1
View File
@@ -681,7 +681,8 @@ class ThresholdChecker:
pools: pools:
'*': '*':
status: status:
critical: 0 warning: 1
critical: 2
operator: '>' operator: '>'
tank: tank:
capacity: capacity: