128 lines
6.0 KiB
YAML
128 lines
6.0 KiB
YAML
# 告警规则从已退役的 Compose 栈迁入，原始版本保留在 Git 历史。
|
|
apiVersion: operator.victoriametrics.com/v1beta1
|
|
kind: VMRule
|
|
metadata:
|
|
name: vmsingle
|
|
namespace: monitoring
|
|
labels:
|
|
app.kubernetes.io/part-of: victoria-metrics
|
|
spec:
|
|
groups:
|
|
- name: vmsingle
|
|
interval: 30s
|
|
concurrency: 2
|
|
rules:
|
|
- alert: DiskRunsOutOfSpaceIn3Days
|
|
expr: |
|
|
sum(vm_free_disk_space_bytes) without(path) /
|
|
(
|
|
(rate(vm_rows_added_to_storage_total[1d]) - sum(rate(vm_deduplicated_samples_total[1d])) without(type)) * (
|
|
sum(vm_data_size_bytes{type!~"indexdb.*"}) without(type) /
|
|
sum(vm_rows{type!~"indexdb.*"}) without(type)
|
|
)
|
|
+
|
|
rate(vm_new_timeseries_created_total[1d]) * (
|
|
sum(vm_data_size_bytes{type="indexdb/file"}) without(type)/
|
|
sum(vm_rows{type="indexdb/file"}) without(type)
|
|
)
|
|
) < 3 * 24 * 3600 > 0
|
|
for: 30m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Instance {{ $labels.instance }} will run out of disk space soon"
|
|
description: "Taking into account current ingestion rate, free disk space will be enough only
|
|
for {{ $value | humanizeDuration }} on instance {{ $labels.instance }}.\n
|
|
Consider to limit the ingestion rate, decrease retention or scale the disk space if possible."
|
|
- alert: NodeBecomesReadonlyIn3Days
|
|
expr: |
|
|
sum(vm_free_disk_space_bytes - vm_free_disk_space_limit_bytes) without(path) /
|
|
(
|
|
(rate(vm_rows_added_to_storage_total[1d]) - sum(rate(vm_deduplicated_samples_total[1d])) without(type)) * (
|
|
sum(vm_data_size_bytes{type!~"indexdb.*"}) without(type) /
|
|
sum(vm_rows{type!~"indexdb.*"}) without(type)
|
|
)
|
|
+
|
|
rate(vm_new_timeseries_created_total[1d]) * (
|
|
sum(vm_data_size_bytes{type="indexdb/file"}) without(type) /
|
|
sum(vm_rows{type="indexdb/file"}) without(type)
|
|
)
|
|
) < 3 * 24 * 3600 > 0
|
|
for: 30m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Instance {{ $labels.instance }} will become read-only in 3 days"
|
|
description: "Taking into account current ingestion rate and free disk space
|
|
instance {{ $labels.instance }} is writable for {{ $value | humanizeDuration }}.\n
|
|
Consider to limit the ingestion rate, decrease retention or scale the disk space up if possible."
|
|
- alert: DiskRunsOutOfSpace
|
|
expr: |
|
|
sum(vm_data_size_bytes) by(job, instance) /
|
|
(
|
|
sum(vm_free_disk_space_bytes) by(job, instance) +
|
|
sum(vm_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(vm_http_request_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: TooHighChurnRate
|
|
expr: |
|
|
(
|
|
sum(rate(vm_new_timeseries_created_total[5m])) by(instance)
|
|
/
|
|
sum(rate(vm_rows_inserted_total[5m])) by(instance)
|
|
) > 0.1
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Churn rate is more than 10% on \"{{ $labels.instance }}\" for the last 15m"
|
|
description: "VM constantly creates new time series on \"{{ $labels.instance }}\".\n
|
|
This effect is known as Churn Rate.\n
|
|
High Churn Rate is tightly connected with database performance and may
|
|
result in unexpected OOM's or slow queries."
|
|
- alert: TooHighChurnRate24h
|
|
expr: |
|
|
sum(increase(vm_new_timeseries_created_total[24h])) by(instance)
|
|
>
|
|
(sum(vm_cache_entries{type="storage/hour_metric_ids"}) by(instance) * 3)
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Too high number of new series on \"{{ $labels.instance }}\" created over last 24h"
|
|
description: "The number of created new time series over last 24h is 3x times higher than
|
|
current number of active series on \"{{ $labels.instance }}\".\n
|
|
This effect is known as Churn Rate.\n
|
|
High Churn Rate is tightly connected with database performance and may
|
|
result in unexpected OOM's or slow queries."
|
|
- alert: TooHighSlowInsertsRate
|
|
expr: |
|
|
(
|
|
sum(rate(vm_slow_row_inserts_total[5m])) by(instance)
|
|
/
|
|
sum(rate(vm_rows_inserted_total[5m])) by(instance)
|
|
) > 0.05
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Percentage of slow inserts is more than 5% on \"{{ $labels.instance }}\" for the last 15m"
|
|
description: "High rate of slow inserts on \"{{ $labels.instance }}\" may be a sign of resource exhaustion
|
|
for the current load. It is likely more RAM is needed for optimal handling of the current number of active time series."
|