mirror of
https://github.com/VictoriaMetrics/VictoriaMetrics.git
synced 2024-11-21 14:44:00 +00:00
003ef3a518
Using `min_over_time` should reduce the amount of false positives when component is running in near-the-threshold state. Now it should trigger only if all collected samples were above the threshold on 10m interval. Signed-off-by: hagen1778 <roman@victoriametrics.com>
89 lines
4.8 KiB
YAML
89 lines
4.8 KiB
YAML
# File contains default list of alerts for various VM components.
|
|
# The following alerts are recommended for use for any VM installation.
|
|
# The alerts below are just recommendations and may require some updates
|
|
# and threshold calibration according to every specific setup.
|
|
groups:
|
|
- name: vm-health
|
|
# note the `job` filter and update accordingly to your setup
|
|
rules:
|
|
- alert: TooManyRestarts
|
|
expr: changes(process_start_time_seconds{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"}[15m]) > 2
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "{{ $labels.job }} too many restarts (instance {{ $labels.instance }})"
|
|
description: "Job {{ $labels.job }} (instance {{ $labels.instance }}) has restarted more than twice in the last 15 minutes.
|
|
It might be crashlooping."
|
|
|
|
- alert: ServiceDown
|
|
expr: up{job=~".*(victoriametrics|vmselect|vminsert|vmstorage|vmagent|vmalert|vmsingle|vmalertmanager|vmauth).*"} == 0
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Service {{ $labels.job }} is down on {{ $labels.instance }}"
|
|
description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes."
|
|
|
|
- alert: ProcessNearFDLimits
|
|
expr: (process_max_fds - process_open_fds) < 100
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Number of free file descriptors is less than 100 for \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") for the last 5m"
|
|
description: "Exhausting OS file descriptors limit can cause severe degradation of the process.
|
|
Consider to increase the limit as fast as possible."
|
|
|
|
- alert: TooHighMemoryUsage
|
|
expr: (min_over_time(process_resident_memory_anon_bytes[10m]) / vm_available_memory_bytes) > 0.8
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "It is more than 80% of memory used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") during the last 5m"
|
|
description: "Too high memory usage may result into multiple issues such as OOMs or degraded performance.
|
|
Consider to either increase available memory or decrease the load on the process."
|
|
|
|
- alert: TooHighCPUUsage
|
|
expr: rate(process_cpu_seconds_total[5m]) / process_cpu_cores_available > 0.9
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "More than 90% of CPU is used by \"{{ $labels.job }}\"(\"{{ $labels.instance }}\") during the last 5m"
|
|
description: "Too high CPU usage may be a sign of insufficient resources and make process unstable.
|
|
Consider to either increase available CPU resources or decrease the load on the process."
|
|
|
|
- alert: TooManyLogs
|
|
expr: sum(increase(vm_log_messages_total{level="error"}[5m])) by (job, instance) > 0
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "Too many logs printed for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
|
|
description: "Logging rate for job \"{{ $labels.job }}\" ({{ $labels.instance }}) is {{ $value }} for last 15m.\n
|
|
Worth to check logs for specific error messages."
|
|
|
|
- alert: TooManyTSIDMisses
|
|
expr: sum(rate(vm_missing_tsids_for_metric_id_total[5m])) by (job, instance) > 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Too many TSID misses for job \"{{ $labels.job }}\" ({{ $labels.instance }})"
|
|
description: "The rate of TSID misses during query lookups is too high for \"{{ $labels.job }}\" ({{ $labels.instance }}).\n
|
|
Make sure you're running VictoriaMetrics of v1.85.3 or higher.\n
|
|
Related issue https://github.com/VictoriaMetrics/VictoriaMetrics/issues/3502"
|
|
|
|
- alert: ConcurrentInsertsHitTheLimit
|
|
expr: avg_over_time(vm_concurrent_insert_current[1m]) >= vm_concurrent_insert_capacity
|
|
for: 15m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: "{{ $labels.job }} on instance {{ $labels.instance }} is constantly hitting concurrent inserts limit"
|
|
description: "The limit of concurrent inserts on instance {{ $labels.instance }} depends on the number of CPUs.\n
|
|
Usually, when component constantly hits the limit it is likely the component is overloaded and requires more CPU.
|
|
In some cases for components like vmagent or vminsert the alert might trigger if there are too many clients
|
|
making write attempts. If vmagent's or vminsert's CPU usage and network saturation are at normal level, then
|
|
it might be worth adjusting `-maxConcurrentInserts` cmd-line flag."
|