# File contains default list of alerts for vmagent service.
# The alerts below are just recommendations and may require some updates
# and threshold calibration according to every specific setup.
groups:
  # Alerts group for vmagent assumes that Grafana dashboard
  # https://grafana.com/grafana/dashboards/12683/ is installed.
  # Pls update the `dashboard` annotation according to your setup.
  - name: vmagent
    interval: 30s
    concurrency: 2
    rules:
      - alert: PersistentQueueIsDroppingData
        expr: sum(increase(vm_persistentqueue_bytes_dropped_total[5m])) without (path) > 0
        for: 10m
        labels:
          severity: critical
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=49&var-instance={{ $labels.instance }}"
          summary: "Instance {{ $labels.instance }} is dropping data from persistent queue"
          description: "Vmagent dropped {{ $value | humanize1024 }} from persistent queue
              on instance {{ $labels.instance }} for the last 10m."

      - alert: RejectedRemoteWriteDataBlocksAreDropped
        expr: sum(increase(vmagent_remotewrite_packets_dropped_total[5m])) without (url) > 0
        for: 15m
        labels:
          severity: warning
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=79&var-instance={{ $labels.instance }}"
          summary: "Vmagent is dropping data blocks that are rejected by remote storage"
          description: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} drops the rejected by 
            remote-write server data blocks. Check the logs to find the reason for rejects."

      - alert: TooManyScrapeErrors
        expr: increase(vm_promscrape_scrapes_failed_total[5m]) > 0
        for: 15m
        labels:
          severity: warning
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=31&var-instance={{ $labels.instance }}"
          summary: "Vmagent fails to scrape one or more targets"
          description: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} fails to scrape targets for last 15m"

      - alert: TooManyWriteErrors
        expr: |
          (sum(increase(vm_ingestserver_request_errors_total[5m])) without (name,net,type)
          +
          sum(increase(vmagent_http_request_errors_total[5m])) without (path,protocol)) > 0
        for: 15m
        labels:
          severity: warning
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=77&var-instance={{ $labels.instance }}"
          summary: "Vmagent responds with too many errors on data ingestion protocols"
          description: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} responds with errors to write requests for last 15m."

      - alert: TooManyRemoteWriteErrors
        expr: rate(vmagent_remotewrite_retries_count_total[5m]) > 0
        for: 15m
        labels:
          severity: warning
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=61&var-instance={{ $labels.instance }}"
          summary: "Job \"{{ $labels.job }}\" on instance {{ $labels.instance }} fails to push to remote storage"
          description: "Vmagent fails to push data via remote write protocol to destination \"{{ $labels.url }}\"\n
            Ensure that destination is up and reachable."

      - alert: RemoteWriteConnectionIsSaturated
        expr: |
          (
           rate(vmagent_remotewrite_send_duration_seconds_total[5m])
           / 
           vmagent_remotewrite_queues
          ) > 0.9
        for: 15m
        labels:
          severity: warning
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=84&var-instance={{ $labels.instance }}"
          summary: "Remote write connection from \"{{ $labels.job }}\" (instance {{ $labels.instance }}) to {{ $labels.url }} is saturated"
          description: "The remote write connection between vmagent \"{{ $labels.job }}\" (instance {{ $labels.instance }}) and destination \"{{ $labels.url }}\"
            is saturated by more than 90% and vmagent won't be able to keep up.\n
            This usually means that `-remoteWrite.queues` command-line flag must be increased in order to increase
            the number of connections per each remote storage."

      - alert: PersistentQueueForWritesIsSaturated
        expr: rate(vm_persistentqueue_write_duration_seconds_total[5m]) > 0.9
        for: 15m
        labels:
          severity: warning
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=98&var-instance={{ $labels.instance }}"
          summary: "Persistent queue writes for instance {{ $labels.instance }} are saturated"
          description: "Persistent queue writes for vmagent \"{{ $labels.job }}\" (instance {{ $labels.instance }})
            are saturated by more than 90% and vmagent won't be able to keep up with flushing data on disk. 
            In this case, consider to decrease load on the vmagent or improve the disk throughput."

      - alert: PersistentQueueForReadsIsSaturated
        expr: rate(vm_persistentqueue_read_duration_seconds_total[5m]) > 0.9
        for: 15m
        labels:
          severity: warning
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=99&var-instance={{ $labels.instance }}"
          summary: "Persistent queue reads for instance {{ $labels.instance }} are saturated"
          description: "Persistent queue reads for vmagent \"{{ $labels.job }}\" (instance {{ $labels.instance }})
            are saturated by more than 90% and vmagent won't be able to keep up with reading data from the disk. 
            In this case, consider to decrease load on the vmagent or improve the disk throughput."

      - alert: SeriesLimitHourReached
        expr: (vmagent_hourly_series_limit_current_series / vmagent_hourly_series_limit_max_series) > 0.9
        labels:
          severity: critical
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=88&var-instance={{ $labels.instance }}"
          summary: "Instance {{ $labels.instance }} reached 90% of the limit"
          description: "Max series limit set via -remoteWrite.maxHourlySeries flag is close to reaching the max value. 
            Then samples for new time series will be dropped instead of sending them to remote storage systems."

      - alert: SeriesLimitDayReached
        expr: (vmagent_daily_series_limit_current_series / vmagent_daily_series_limit_max_series) > 0.9
        labels:
          severity: critical
        annotations:
          dashboard: "http://localhost:3000/d/G7Z9GzMGz?viewPanel=90&var-instance={{ $labels.instance }}"
          summary: "Instance {{ $labels.instance }} reached 90% of the limit"
          description: "Max series limit set via -remoteWrite.maxDailySeries flag is close to reaching the max value. 
            Then samples for new time series will be dropped instead of sending them to remote storage systems."

      - alert: ConfigurationReloadFailure
        expr: |
          vm_promscrape_config_last_reload_successful != 1
          or
          vmagent_relabel_config_last_reload_successful != 1
        labels:
          severity: warning
        annotations:
          summary: "Configuration reload failed for vmagent instance {{ $labels.instance }}"
          description: "Configuration hot-reload failed for vmagent on instance {{ $labels.instance }}.
          Check vmagent's logs for detailed error message."

      - alert: StreamAggrFlushTimeout
        expr: |
          increase(vm_streamaggr_flush_timeouts_total[5m]) > 0
        labels:
          severity: warning
        annotations:
          summary: "Streaming aggregation at \"{{ $labels.job }}\" (instance {{ $labels.instance }}) can't be finished within the configured aggregation interval."
          description: "Stream aggregation process can't keep up with the load and might produce incorrect aggregation results. Check logs for more details.
            Possible solutions: increase aggregation interval; aggregate smaller number of series; reduce samples' ingestion rate to stream aggregation."

      - alert: StreamAggrDedupFlushTimeout
        expr: |
          increase(vm_streamaggr_dedup_flush_timeouts_total[5m]) > 0
        labels:
          severity: warning
        annotations:
          summary: "Deduplication \"{{ $labels.job }}\" (instance {{ $labels.instance }}) can't be finished within configured deduplication interval."
          description: "Deduplication process can't keep up with the load and might produce incorrect results. Check docs https://docs.victoriametrics.com/stream-aggregation/#deduplication and logs for more details.
            Possible solutions: increase deduplication interval; deduplicate smaller number of series; reduce samples' ingestion rate."