"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) ",
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"jvm_memory_pool_bytes_max{pool=\\\"G1 Eden Space\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"legend\":\"Max\"},{\"expr\":\"jvm_memory_pool_bytes_used{pool=\\\"G1 Eden Space\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"Used\"},{\"expr\":\"jvm_memory_pool_bytes_committed{pool=\\\"G1 Eden Space\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"Committed\"}],\"name\":\"G1 Eden Space\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"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\":0,\"i\":\"3\"}}",
"weight":0
},
{
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"jvm_memory_pool_bytes_max{pool=\\\"Compressed Class Space\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"legend\":\"Max\"},{\"expr\":\"jvm_memory_pool_bytes_used{pool=\\\"Compressed Class Space\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"Used\"},{\"expr\":\"jvm_memory_pool_bytes_committed{pool=\\\"Compressed Class Space\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"Committed\"}],\"name\":\"Compressed Class Space\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"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\":2,\"i\":\"4\"}}",
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"jvm_memory_pool_bytes_max{pool=\\\"G1 Old Gen\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"legend\":\"Max\"},{\"expr\":\"jvm_memory_pool_bytes_used{pool=\\\"G1 Old Gen\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"refId\":\"B\",\"legend\":\"Used\"},{\"expr\":\"jvm_memory_pool_bytes_committed{pool=\\\"G1 Old Gen\\\", job=\\\"$job\\\",instance=\\\"$instance\\\"}\",\"refId\":\"C\",\"legend\":\"Committed\"}],\"name\":\"G1 Old Gen\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"bytesIEC\",\"decimals\":1},\"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\":2,\"i\":\"6\"}}",
"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\"}}",
"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\"}}",
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(mongodb_extra_info_page_faults_total{instance=\\\"$instance\\\"}[5m])\",\"legend\":\"{{type}}\"}],\"name\":\"Page Faults\",\"description\":\"页缺失中断次数 Page faults indicate that requests are processed from disk either because an index is missing or there is not enough memory for the data set. Consider increasing memory or sharding out.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"none\",\"decimals\":null},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":18,\"y\":0,\"i\":\"3\"}}",
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"mongodb_connections{instance=\\\"$instance\\\", state=\\\"current\\\"}\",\"legend\":\"Connections\"}],\"name\":\"Connections\",\"description\":\"连接数 Keep in mind the hard limit on the maximum number of connections set by your distribution.\",\"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\":2,\"i\":\"5\"}}",
"weight":0
},
{
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(mongodb_asserts_total{instance=\\\"$instance\\\"}[5m])\",\"legend\":\"{{type}}\"}],\"name\":\"Assert Events\",\"description\":\"断言错误次数 Asserts are not important by themselves, but you can correlate spikes with other graphs.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":6,\"x\":12,\"y\":2,\"i\":\"6\"}}",
"weight":0
},
{
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"mongodb_mongod_global_lock_current_queue{instance=\\\"$instance\\\"}\",\"legend\":\"{{type}}\"}],\"name\":\"Lock Queue\",\"description\":\"等待获取锁操作数量 Any number of queued operations for long periods of time is an indication of possible issues. Find the cause and fix it before requests get stuck in the queue.\",\"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\":2,\"i\":\"7\"}}",
"weight":0
}
]
},
{
"name":"Operation Info",
"weight":1,
"charts":[
{
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(mongodb_op_counters_total{instance=\\\"$instance\\\", type!=\\\"command\\\"}[5m])\",\"legend\":\"{{type}}\"},{\"expr\":\"rate(mongodb_mongod_op_counters_repl_total{instance=\\\"$instance\\\", type!~\\\"(command|query|getmore)\\\"}[5m]) or \\nrate(mongodb_mongos_op_counters_repl_total{instance=\\\"$instance\\\", type!~\\\"(command|query|getmore)\\\"}[5m])\",\"refId\":\"B\",\"legend\":\"repl_{{type}}\"},{\"expr\":\"rate(mongodb_mongod_metrics_ttl_deleted_documents_total{instance=\\\"$instance\\\"}[5m]) or \\nrate(mongodb_mongos_metrics_ttl_deleted_documents_total{instance=\\\"$instance\\\"}[5m])\",\"refId\":\"C\",\"legend\":\"ttl_delete\"}],\"name\":\"Command Operations\",\"description\":\"接收请求数 Shows how many times a command is executed per second on average during the selected interval.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"desc\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":12,\"x\":0,\"y\":0,\"i\":\"0\"}}",
"weight":0
},
{
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"rate(mongodb_mongod_metrics_document_total{instance=\\\"$instance\\\"}[5m])\",\"legend\":\"{{state}}\"}],\"name\":\"Document Operations\",\"description\":\"文档操作数 When used in combination with 'Command Operations', this graph can help identify write amplification. For example, when one insert or update command actually inserts or updates hundreds, thousands, or even millions of documents.\",\"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\":\"1\"}}",
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"mongodb_mongod_metrics_cursor_open{instance=\\\"$instance\\\"}\",\"legend\":\"{{state}}\"}],\"name\":\"Cursors\",\"description\":\"游标数量 Helps identify why connections are increasing. Shows active cursors compared to cursors being automatically killed after 10 minutes due to an application not closing the connection.\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{},\"thresholds\":{}},\"custom\":{\"drawStyle\":\"lines\",\"lineInterpolation\":\"smooth\",\"fillOpacity\":0.5,\"stack\":\"off\"},\"version\":\"2.0.0\",\"type\":\"timeseries\",\"layout\":{\"h\":2,\"w\":8,\"x\":16,\"y\":2,\"i\":\"4\"}}",
"configs":"{\"targets\":[{\"refId\":\"A\",\"expr\":\"mongodb_mongod_replset_member_replication_lag{instance=\\\"$instance\\\"}\",\"legend\":\"lag\"}],\"name\":\"Replset Lag Seconds\",\"description\":\"副本集成员主从同步延迟\",\"options\":{\"tooltip\":{\"mode\":\"all\",\"sort\":\"none\"},\"legend\":{\"displayMode\":\"hidden\"},\"standardOptions\":{\"util\":\"seconds\"},\"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\":\"1\"}}",
