VictoriaMetrics/deployment/docker/rules/alerts-vlogs.yml

44 lines
1.8 KiB
YAML
Raw Normal View History

# File contains default list of alerts for VictoriaLogs single server.
# The alerts below are just recommendations and may require some updates
# and threshold calibration according to every specific setup.
groups:
- name: vlogs
interval: 30s
concurrency: 2
rules:
- alert: DiskRunsOutOfSpace
expr: |
sum(vl_data_size_bytes) by(job, instance) /
(
sum(vl_free_disk_space_bytes) by(job, instance) +
sum(vl_data_size_bytes) by(job, instance)
) > 0.8
for: 30m
labels:
severity: critical
annotations:
summary: "Instance {{ $labels.instance }} (job={{ $labels.job }}) will run out of disk space soon"
description: "Disk utilisation on instance {{ $labels.instance }} is more than 80%.\n
Having less than 20% of free disk space could cripple merge processes and overall performance.
Consider to limit the ingestion rate, decrease retention or scale the disk space if possible."
- alert: RequestErrorsToAPI
expr: increase(vl_http_errors_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "Too many errors served for path {{ $labels.path }} (instance {{ $labels.instance }})"
description: "Requests to path {{ $labels.path }} are receiving errors.
Please verify if clients are sending correct requests."
- alert: RowsRejectedOnIngestion
expr: rate(vl_rows_dropped_total[5m]) > 0
for: 15m
labels:
severity: warning
annotations:
summary: "Some rows are rejected on \"{{ $labels.instance }}\" on ingestion attempt"
description: "VictoriaLogs is rejecting to ingest rows on \"{{ $labels.instance }}\" due to the
following reason: \"{{ $labels.reason }}\""