health: enable go.d data collection job status alert (#18989)
Ilya Mashchenko committed
Nov 11, 2024 at 21:58 UTC
85988eb177209756125b44726eb761841e2944ca
1 file changed
+9
-11
src/health/health.d/go.d.plugin.conf
+9
-11
@@ -1,17 +1,15 @@
1
# make sure go.d.plugin data collection job is running
2
3
- template: go.d_job_last_collected_secs
4
- on: netdata.go_plugin_execution_time
3
+ template: plugin_data_collection_status
4
+ on: netdata.plugin_data_collection_status
5
class: Errors
6
type: Netdata
7
component: go.d.plugin
8
-host labels: _hostname=!*
9
- calc: $now - $last_collected_t
10
- units: seconds ago
8
+ lookup: average -30s unaligned of failed
9
+ units: status
10
every: 10s
12
- warn: $this > (($status >= $WARNING) ? ($update_every) : ( 5 * $update_every))
13
- crit: $this > (($status == $CRITICAL) ? ($update_every) : (60 * $update_every))
14
- delay: down 5m multiplier 1.5 max 1h
15
- summary: Go.d plugin last collection
16
- info: Number of seconds since the last successful data collection
17
- to: webmaster
11
+ warn: $this == 1
12
+ delay: down 1m
13
+ summary: Data collection failure (${label:_collect_plugin}/${label:_collect_module}/${label:_collect_job})
14
+ info: Data collection failure (${label:_collect_plugin}/${label:_collect_module}/${label:_collect_job})
15
+ to: silent