nightingale/integrations/Linux/alerts/linux_by_exporter.json

[
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "A certain disk is unable to read/write normally",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 1,
    "severities": [
      1
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "(node_filesystem_device_error{instance=\"$node\",mountpoint!~\"/var/lib/.*\",mountpoint!~\"/run.*\"}) > 0",
          "severity": 1
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Disk needs to be cleaned - utilization has reached 92% - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 1,
    "severities": [
      1
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "(100 - ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes) ) > 92 ",
          "severity": 1
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [
      "dingtalk"
    ],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Insufficient computational resources - average load per core of the machine is greater than 10 - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "avg (node_load1) by (instance)/count(count(node_cpu_seconds_total) by (cpu,instance)) by (instance) >10",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Insufficient file handles - usage exceeds 90% - node exporter",
    "note": "You can increase the file handle limit or expand the capacity",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "(node_filefd_allocated{instance=\"$node\"}/node_filefd_maximum{instance=\"$node\"}*100) > 90",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Insufficient inode resources - usage exceeds 90% - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "(100 - ((node_filesystem_files_free * 100) / node_filesystem_files))>90",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Insufficient memory resources - utilization is greater than 75% - node exporter",
    "note": "Expansion or upgrading of configuration is required",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "(node_memory_MemTotal_bytes - node_memory_MemFree_bytes - (node_memory_Cached_bytes + node_memory_Buffers_bytes))/node_memory_MemTotal_bytes*100 > 75",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [
      "dingtalk"
    ],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Insufficient memory resources - utilization is greater than 95% - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 1,
    "severities": [
      1
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "(node_memory_MemTotal_bytes - node_memory_MemFree_bytes - (node_memory_Cached_bytes + node_memory_Buffers_bytes))/node_memory_MemTotal_bytes*100 > 95",
          "severity": 1
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [
      "dingtalk"
    ],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Packet loss in the inbound direction of the network card - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "rate(node_network_receive_drop_total{device=~\"e.*\"}[1m]) > 3",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Packet loss in the outbound direction of the network card - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "rate(node_network_transmit_drop_total{device=~\"e.*\"}[1m]) > 3",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "System conntrack needs to be adjusted - usage exceeds 80% - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "node_nf_conntrack_entries / node_nf_conntrack_entries_limit*100 > 80",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "System experiences OOM - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "increase(node_vmstat_oom_kill[1m]) > 0",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  },
  {
    "cate": "prometheus",
    "datasource_ids": [
      0
    ],
    "name": "Too many running processes - exceeding 3000 - node exporter",
    "note": "",
    "prod": "metric",
    "algorithm": "",
    "algo_params": null,
    "delay": 0,
    "severity": 2,
    "severities": [
      2
    ],
    "disabled": 1,
    "prom_for_duration": 60,
    "prom_ql": "",
    "rule_config": {
      "algo_params": null,
      "inhibit": false,
      "prom_ql": "",
      "queries": [
        {
          "prom_ql": "node_procs_running > 3000",
          "severity": 2
        }
      ],
      "severity": 0
    },
    "prom_eval_interval": 15,
    "enable_stime": "00:00",
    "enable_stimes": [
      "00:00"
    ],
    "enable_etime": "23:59",
    "enable_etimes": [
      "23:59"
    ],
    "enable_days_of_week": [
      "1",
      "2",
      "3",
      "4",
      "5",
      "6",
      "0"
    ],
    "enable_days_of_weeks": [
      [
        "1",
        "2",
        "3",
        "4",
        "5",
        "6",
        "0"
      ]
    ],
    "enable_in_bg": 0,
    "notify_recovered": 1,
    "notify_channels": [],
    "notify_repeat_step": 60,
    "notify_max_number": 0,
    "recover_duration": 0,
    "callbacks": [],
    "runbook_url": "",
    "append_tags": [],
    "annotations": null,
    "extra_config": null
  }
]