my shitty notes I've asked AI to clean up and reorder so that they are readable
It is just work in progress so I don't really car
This commit is contained in:
51
exporters/examples/alerts.yml
Normal file
51
exporters/examples/alerts.yml
Normal file
@@ -0,0 +1,51 @@
|
||||
groups:
|
||||
- name: ptp
|
||||
rules:
|
||||
- alert: PTPExporterDown
|
||||
expr: up{job=~"ptp-linux|ptp-nexus"} == 0
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "PTP exporter is unreachable on {{ $labels.instance }}"
|
||||
|
||||
- alert: LinuxPTPScrapeFailed
|
||||
expr: ptp_exporter_scrape_success{stage!="ok"} == 0
|
||||
for: 2m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "linuxptp PMC scrape failed on {{ $labels.instance }}"
|
||||
|
||||
- alert: PTPGrandmasterMissing
|
||||
expr: ptp_gm_present == 0
|
||||
for: 30s
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "PTP grandmaster is not present on {{ $labels.instance }}"
|
||||
|
||||
- alert: NexusPTPUnlocked
|
||||
expr: ptp_nexus_clock_locked == 0
|
||||
for: 30s
|
||||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: "Nexus PTP clock is not locked"
|
||||
|
||||
# Start conservatively and tighten this after observing normal behavior.
|
||||
- alert: PTPMasterOffsetHigh
|
||||
expr: abs(ptp_master_offset_nanoseconds) > 1000
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "PTP offset exceeds 1 us on {{ $labels.instance }}"
|
||||
|
||||
- alert: NexusPTPMasterOffsetHigh
|
||||
expr: abs(ptp_nexus_offset_from_master_nanoseconds) > 1000
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: "Nexus PTP offset exceeds 1 us"
|
||||
Reference in New Issue
Block a user