提交 be1c3b17 编写于 作者: N ning

doc: add node_exporter kafka_exporter zk_exporter's dashboard and alert template

上级 a6735663
[
{
"name": "数据有丢失风险-同步副本数小于3",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "sum(kafka_topic_partition_in_sync_replica) by (topic) < 3",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "消费能力不足-积压消息数超过50条",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "sum(kafka_topic_partition_current_offset{instance=\"$instance\"}) by (topic) - sum(kafka_consumergroup_current_offset{instance=\"$instance\"}) by (topic) ",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]
\ No newline at end of file
[
{
"name": "inode资源不足-使用率超过90",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "(100 - ((node_filesystem_files_free * 100) / node_filesystem_files))>90",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "内存资源不足-利用率大于75%",
"note": "需要扩容或者升级配置了",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "(node_memory_MemTotal_bytes - node_memory_MemFree_bytes - (node_memory_Cached_bytes + node_memory_Buffers_bytes))/node_memory_MemTotal_bytes*100 > 75",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "文件句柄不足-使用率超过90%",
"note": "可以将文件句柄limit调大,或者扩容",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "(node_filefd_allocated{instance=\"$node\"}/node_filefd_maximum{instance=\"$node\"}*100) > 90",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "某磁盘无法正常读写",
"note": "",
"severity": 1,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "(node_filesystem_device_error{instance=\"$node\",mountpoint!~\"/var/lib/.*\",mountpoint!~\"/run.*\"}) > 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "磁盘需要清理了-利用率达到92%",
"note": "",
"severity": 1,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "(100 - ((node_filesystem_avail_bytes * 100) / node_filesystem_size_bytes) ) > 92 ",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "系统conntrack需要调整-使用率超过80%",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "node_nf_conntrack_entries / node_nf_conntrack_entries_limit*100 > 80",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "系统出现oom",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "increase(node_vmstat_oom_kill[1m]) > 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "网卡入方向丢包",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "rate(node_network_receive_drop_total{device=~\"e.*\"}[1m]) > 3",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "网卡出方向丢包",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "rate(node_network_transmit_drop_total{device=~\"e.*\"}[1m]) > 3",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "计算资源不足-机器loadavg1大于15",
"note": "需要扩容或者升级配置了",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "node_load1>15",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "运行进程数过多-超过3000",
"note": "建议扩容",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "node_procs_running > 3000",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]
\ No newline at end of file
[
{
"name": "Zookeeper leader 个数大于1",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "sum(zk_server_leader) > 1",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "Zookeeper 实例运行异常",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "zk_ruok == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "Zookeeper 没有 leader 了",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "sum(zk_server_leader) == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
},
{
"name": "Zookeeper 挂掉了",
"note": "",
"severity": 2,
"disabled": 0,
"prom_for_duration": 60,
"prom_ql": "zk_up == 0",
"prom_eval_interval": 15,
"enable_stime": "00:00",
"enable_etime": "23:59",
"enable_days_of_week": [
"1",
"2",
"3",
"4",
"5",
"6",
"0"
],
"enable_in_bg": 0,
"notify_recovered": 1,
"notify_channels": [],
"notify_repeat_step": 60,
"recover_duration": 0,
"callbacks": [],
"runbook_url": "",
"append_tags": []
}
]
\ No newline at end of file
[
{
"name": "Kafka - 模板",
"tags": "Kafka Prometheus ",
"configs": "{\"var\":[{\"name\":\"instance\",\"definition\":\"label_values(kafka_brokers, instance)\"},{\"name\":\"job\",\"definition\":\"label_values(kafka_brokers, job)\"}]}",
"chart_groups": [
{
"name": "overview",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"count(count by (topic) (kafka_topic_partitions))\"}],\"name\":\"topics\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":8,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_brokers\"}],\"name\":\"brokers\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":0,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"sum(kafka_topic_partitions)\"}],\"name\":\"partitions\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":8,\"x\":16,\"y\":0,\"i\":\"2\"}}",
"weight": 0
}
]
},
{
"name": "throughput",
"weight": 1,
"charts": [
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(kafka_topic_partition_current_offset{instance=\\\"$instance\\\"}[1m])) by (topic)\"}],\"name\":\"Message in per second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(kafka_consumer_lag_millis{instance=\\\"$instance\\\"}) by (consumergroup, topic) \",\"legend\":\"{{consumergroup}} (topic: {{topic}})\"}],\"name\":\"Latency by Consumer Group\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"humantimeMilliseconds\"},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":2,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(rate(kafka_consumergroup_current_offset{instance=\\\"$instance\\\"}[1m])) by (topic)\"}],\"name\":\"Message consume per second\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"expr\":\"sum(kafka_topic_partition_current_offset{instance=\\\"$instance\\\"}) by (topic) - sum(kafka_consumergroup_current_offset{instance=\\\"$instance\\\"}) by (topic) \",\"legend\":\"{{consumergroup}} (topic: {{topic}})\"}],\"name\":\"Lag by Consumer Group\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":2,\"i\":\"3\"}}",
"weight": 0
}
]
},
{
"name": "patition/replicate",
"weight": 2,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_topic_partitions{instance=\\\"$instance\\\"}\",\"legend\":\"{{topic}}\"}],\"name\":\"Partitions per Topic\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"seriesToRows\"},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"kafka_topic_partition_under_replicated_partition\",\"legend\":\"{{topic}}-{{partition}}\"}],\"name\":\"Under Replicated\",\"description\":\"副本不同步预案\\n1. Restart the Zookeeper leader.\\n2. Restart the broker\\\\brokers that are not replicating some of the partitions.\",\"custom\":{\"showHeader\":true,\"calc\":\"lastNotNull\",\"displayMode\":\"seriesToRows\"},\"options\":{\"standardOptions\":{}},\"overrides\":[{}],\"version\":\"2.0.0\",\"type\":\"table\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":0,\"i\":\"1\"}}",
"weight": 0
}
]
}
]
}
]
\ No newline at end of file
此差异已折叠。
[
{
"name": "Zookeeper - 模板",
"tags": "",
"configs": "{\"var\":[{\"name\":\"job\",\"definition\":\"label_values(zk_up,job)\"},{\"definition\":\"label_values(zk_up,instance)\",\"name\":\"instance\"}]}",
"chart_groups": [
{
"name": "overview",
"weight": 0,
"charts": [
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_up{job=\\\"$job\\\", instance=\\\"$instance\\\"}\",\"legend\":\"up\"}],\"name\":\"up\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":40}},\"options\":{\"valueMappings\":[{\"type\":\"special\",\"match\":{\"special\":1},\"result\":{\"color\":\"#3d950e\",\"text\":\"UP\"}},{\"type\":\"special\",\"match\":{\"special\":0},\"result\":{\"color\":\"#f01414\",\"text\":\"DOWN\"}}],\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_znode_count{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"{{instance}}\"}],\"name\":\"zk_znode_count\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":6,\"y\":0,\"i\":\"1\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_watch_count{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"{{instance}}\"}],\"name\":\"zk_watch_count\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":12,\"y\":0,\"i\":\"2\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_ephemerals_count{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"zk_ephemerals_count\"}],\"name\":\"zk_ephemerals_count\",\"custom\":{\"textMode\":\"value\",\"colorMode\":\"value\",\"calc\":\"lastNotNull\",\"colSpan\":1,\"textSize\":{\"value\":50}},\"options\":{\"standardOptions\":{}},\"version\":\"2.0.0\",\"type\":\"stat\",\"layout\":{\"h\":1,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(zk_packets_sent{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}[5m])\",\"legend\":\"{{instance}}-sent\"},{\"expr\":\"rate(zk_packets_received{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}[5m])\",\"refId\":\"B\",\"legend\":\"{{instance}}-received\"}],\"name\":\"Pakages\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":1,\"i\":\"4\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_num_alive_connections{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"{{instance}}\"}],\"name\":\"alive_connections\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":6,\"y\":3,\"i\":\"5\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_open_file_descriptor_count{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"{{instance}}-open\"},{\"expr\":\"zk_max_file_descriptor_count{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"{{instance}}-max\"}],\"name\":\"file_descriptor\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":3,\"i\":\"6\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_avg_latency{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"{{instance}}-avg\"},{\"expr\":\"zk_min_latency{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"{{instance}}-min\"},{\"expr\":\"zk_max_latency{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"{{instance}}-max\"}],\"name\":\"latency(ms)\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":3,\"i\":\"7\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_outstanding_requests{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"{{instance}}\"}],\"name\":\"outstanding_requests\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":0,\"y\":3,\"i\":\"8\"}}",
"weight": 0
},
{
"configs": "{\"targets\":[{\"refId\":\"A\",\"expr\":\"zk_approximate_data_size{job=~\\\"$job\\\", instance=~\\\"$instance\\\"}\",\"legend\":\"{{instance}}\"}],\"name\":\"approximate_data_size\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":12,\"y\":1,\"i\":\"9\"}}",
"weight": 0
}
]
}
]
}
]
\ No newline at end of file
......@@ -350,3 +350,145 @@ windows_system_system_calls_total: Total number of system calls (WMI source is P
windows_system_system_up_time: System boot time (WMI source is PerfOS_System.SystemUpTime)(gauge)
windows_system_threads: Current number of threads (WMI source is PerfOS_System.Threads)(gauge)
# [node_exporter]
# SYSTEM
# CPU context switch 次数
node_context_switches_total: context_switches
# Interrupts 次数
node_intr_total: Interrupts
# 运行的进程数
node_procs_running: Processes in runnable state
# 熵池大小
node_entropy_available_bits: Entropy available to random number generators
node_time_seconds: System time in seconds since epoch (1970)
node_boot_time_seconds: Node boot time, in unixtime
# CPU
node_cpu_seconds_total: Seconds the CPUs spent in each mode
node_load1: cpu load 1m
node_load5: cpu load 5m
node_load15: cpu load 15m
# MEM
# 内核态
# 用户追踪已从交换区获取但尚未修改的页面的内存
node_memory_SwapCached_bytes: Memory that keeps track of pages that have been fetched from swap but not yet been modified
# 内核用于缓存数据结构供自己使用的内存
node_memory_Slab_bytes: Memory used by the kernel to cache data structures for its own use
# slab中可回收的部分
node_memory_SReclaimable_bytes: SReclaimable - Part of Slab, that might be reclaimed, such as caches
# slab中不可回收的部分
node_memory_SUnreclaim_bytes: Part of Slab, that cannot be reclaimed on memory pressure
# Vmalloc内存区的大小
node_memory_VmallocTotal_bytes: Total size of vmalloc memory area
# vmalloc已分配的内存,虚拟地址空间上的连续的内存
node_memory_VmallocUsed_bytes: Amount of vmalloc area which is used
# vmalloc区可用的连续最大快的大小,通过此指标可以知道vmalloc可分配连续内存的最大值
node_memory_VmallocChunk_bytes: Largest contigious block of vmalloc area which is free
# 内存的硬件故障删除掉的内存页的总大小
node_memory_HardwareCorrupted_bytes: Amount of RAM that the kernel identified as corrupted / not working
# 用于在虚拟和物理内存地址之间映射的内存
node_memory_PageTables_bytes: Memory used to map between virtual and physical memory addresses (gauge)
# 内核栈内存,常驻内存,不可回收
node_memory_KernelStack_bytes: Kernel memory stack. This is not reclaimable
# 用来访问高端内存,复制高端内存的临时buffer,称为“bounce buffering”,会降低I/O 性能
node_memory_Bounce_bytes: Memory used for block device bounce buffers
#用户态
# 单个巨页大小
node_memory_Hugepagesize_bytes: Huge Page size
# 系统分配的常驻巨页数
node_memory_HugePages_Total: Total size of the pool of huge pages
# 系统空闲的巨页数
node_memory_HugePages_Free: Huge pages in the pool that are not yet allocated
# 进程已申请但未使用的巨页数
node_memory_HugePages_Rsvd: Huge pages for which a commitment to allocate from the pool has been made, but no allocation
# 超过系统设定的常驻HugePages数量的个数
node_memory_HugePages_Surp: Huge pages in the pool above the value in /proc/sys/vm/nr_hugepages
# 透明巨页 Transparent HugePages (THP)
node_memory_AnonHugePages_bytes: Memory in anonymous huge pages
# inactivelist中的File-backed内存
node_memory_Inactive_file_bytes: File-backed memory on inactive LRU list
# inactivelist中的Anonymous内存
node_memory_Inactive_anon_bytes: Anonymous and swap cache on inactive LRU list, including tmpfs (shmem)
# activelist中的File-backed内存
node_memory_Active_file_bytes: File-backed memory on active LRU list
# activelist中的Anonymous内存
node_memory_Active_anon_bytes: Anonymous and swap cache on active least-recently-used (LRU) list, including tmpfs
# 禁止换出的页,对应 Unevictable 链表
node_memory_Unevictable_bytes: Amount of unevictable memory that can't be swapped out for a variety of reasons
# 共享内存
node_memory_Shmem_bytes: Used shared memory (shared between several processes, thus including RAM disks)
# 匿名页内存大小
node_memory_AnonPages_bytes: Memory in user pages not backed by files
# 被关联的内存页大小
node_memory_Mapped_bytes: Used memory in mapped pages files which have been mmaped, such as libraries
# file-backed内存页缓存大小
node_memory_Cached_bytes: Parked file data (file content) cache
# 系统中有多少匿名页曾经被swap-out、现在又被swap-in并且swap-in之后页面中的内容一直没发生变化
node_memory_SwapCached_bytes: Memory that keeps track of pages that have been fetched from swap but not yet been modified
# 被mlock()系统调用锁定的内存大小
node_memory_Mlocked_bytes: Size of pages locked to memory using the mlock() system call
# 块设备(block device)所占用的缓存页
node_memory_Buffers_bytes: Block device (e.g. harddisk) cache
node_memory_SwapTotal_bytes: Memory information field SwapTotal_bytes
node_memory_SwapFree_bytes: Memory information field SwapFree_bytes
# DISK
node_filesystem_files_free: Filesystem space available to non-root users in byte
node_filesystem_free_bytes: Filesystem free space in bytes
node_filesystem_size_bytes: Filesystem size in bytes
node_filesystem_files_free: Filesystem total free file nodes
node_filesystem_files: Filesystem total free file nodes
node_filefd_maximum: Max open files
node_filefd_allocated: Open files
node_filesystem_readonly: Filesystem read-only status
node_filesystem_device_error: Whether an error occurred while getting statistics for the given device
node_disk_reads_completed_total: The total number of reads completed successfully
node_disk_writes_completed_total: The total number of writes completed successfully
node_disk_reads_merged_total: The number of reads merged
node_disk_writes_merged_total: The number of writes merged
node_disk_read_bytes_total: The total number of bytes read successfully
node_disk_written_bytes_total: The total number of bytes written successfully
node_disk_io_time_seconds_total: Total seconds spent doing I/Os
node_disk_read_time_seconds_total: The total number of seconds spent by all reads
node_disk_write_time_seconds_total: The total number of seconds spent by all writes
node_disk_io_time_weighted_seconds_total: The weighted of seconds spent doing I/Os
# NET
node_network_receive_bytes_total: Network device statistic receive_bytes (counter)
node_network_transmit_bytes_total: Network device statistic transmit_bytes (counter)
node_network_receive_packets_total: Network device statistic receive_bytes
node_network_transmit_packets_total: Network device statistic transmit_bytes
node_network_receive_errs_total: Network device statistic receive_errs
node_network_transmit_errs_total: Network device statistic transmit_errs
node_network_receive_drop_total: Network device statistic receive_drop
node_network_transmit_drop_total: Network device statistic transmit_drop
node_nf_conntrack_entries: Number of currently allocated flow entries for connection tracking
node_sockstat_TCP_alloc: Number of TCP sockets in state alloc
node_sockstat_TCP_inuse: Number of TCP sockets in state inuse
node_sockstat_TCP_orphan: Number of TCP sockets in state orphan
node_sockstat_TCP_tw: Number of TCP sockets in state tw
node_netstat_Tcp_CurrEstab: Statistic TcpCurrEstab
node_sockstat_sockets_used: Number of IPv4 sockets in use
# [kafka_exporter]
kafka_brokers: count of kafka_brokers (gauge)
kafka_topic_partitions: Number of partitions for this Topic (gauge)
kafka_topic_partition_current_offset: Current Offset of a Broker at Topic/Partition (gauge)
kafka_consumergroup_current_offset: Current Offset of a ConsumerGroup at Topic/Partition (gauge)
kafka_consumer_lag_millis: Current approximation of consumer lag for a ConsumerGroup at Topic/Partition (gauge)
kafka_topic_partition_under_replicated_partition: 1 if Topic/Partition is under Replicated
# [zookeeper_exporter]
zk_znode_count: The total count of znodes stored
zk_ephemerals_count: The number of Ephemerals nodes
zk_watch_count: The number of watchers setup over Zookeeper nodes.
zk_approximate_data_size: Size of data in bytes that a zookeeper server has in its data tree
zk_outstanding_requests: Number of currently executing requests
zk_packets_sent: Count of the number of zookeeper packets sent from a server
zk_packets_received: Count of the number of zookeeper packets received by a server
zk_num_alive_connections: Number of active clients connected to a zookeeper server
zk_open_file_descriptor_count: Number of file descriptors that a zookeeper server has open
zk_max_file_descriptor_count: Maximum number of file descriptors that a zookeeper server can open
zk_avg_latency: Average time in milliseconds for requests to be processed
zk_min_latency: Maximum time in milliseconds for a request to be processed
zk_max_latency: Minimum time in milliseconds for a request to be processed
\ No newline at end of file
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册