prometheus监控系统的的报警规则是在prometheus这个组件完成配置的。 prometheus支持2种类型的规则,记录规则和报警规则, 记录规则主要是为了简写报警规则和提高规则复用的, 报警规则才是真正去判定是否需要报警的规则。 报警规则中是可以使用记录规则的。
提供下我整理的node-exporter的记录规则和报警规则。
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 |
groups: - name: node-exporter-record rules: - expr: up{job=~"node-exporter"} record: node_exporter:up labels: desc: "节点是否在线, 在线1,不在线0" unit: " " job: "node-exporter" - expr: time() - node_boot_time_seconds{} record: node_exporter:node_uptime labels: desc: "节点的运行时间" unit: "s" job: "node-exporter" ############################################################################################## # cpu # - expr: (1 - avg by (environment,instance) (irate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[5m]))) * 100 record: node_exporter:cpu:total:percent labels: desc: "节点的cpu总消耗百分比" unit: "%" job: "node-exporter" - expr: (avg by (environment,instance) (irate(node_cpu_seconds_total{job="node-exporter",mode="idle"}[5m]))) * 100 record: node_exporter:cpu:idle:percent labels: desc: "节点的cpu idle百分比" unit: "%" job: "node-exporter" - expr: (avg by (environment,instance) (irate(node_cpu_seconds_total{job="node-exporter",mode="iowait"}[5m]))) * 100 record: node_exporter:cpu:iowait:percent labels: desc: "节点的cpu iowait百分比" unit: "%" job: "node-exporter" - expr: (avg by (environment,instance) (irate(node_cpu_seconds_total{job="node-exporter",mode="system"}[5m]))) * 100 record: node_exporter:cpu:system:percent labels: desc: "节点的cpu system百分比" unit: "%" job: "node-exporter" - expr: (avg by (environment,instance) (irate(node_cpu_seconds_total{job="node-exporter",mode="user"}[5m]))) * 100 record: node_exporter:cpu:user:percent labels: desc: "节点的cpu user百分比" unit: "%" job: "node-exporter" - expr: (avg by (environment,instance) (irate(node_cpu_seconds_total{job="node-exporter",mode=~"softirq|nice|irq|steal"}[5m]))) * 100 record: node_exporter:cpu:other:percent labels: desc: "节点的cpu 其他的百分比" unit: "%" job: "node-exporter" ############################################################################################## ############################################################################################## # memory # - expr: node_memory_MemTotal_bytes{job="node-exporter"} record: node_exporter:memory:total labels: desc: "节点的内存总量" unit: byte job: "node-exporter" - expr: node_memory_MemFree_bytes{job="node-exporter"} record: node_exporter:memory:free labels: desc: "节点的剩余内存量" unit: byte job: "node-exporter" - expr: node_memory_MemTotal_bytes{job="node-exporter"} - node_memory_MemFree_bytes{job="node-exporter"} record: node_exporter:memory:used labels: desc: "节点的已使用内存量" unit: byte job: "node-exporter" - expr: node_memory_MemTotal_bytes{job="node-exporter"} - node_memory_MemAvailable_bytes{job="node-exporter"} record: node_exporter:memory:actualused labels: desc: "节点用户实际使用的内存量" unit: byte job: "node-exporter" - expr: (1-(node_memory_MemAvailable_bytes{job="node-exporter"} / (node_memory_MemTotal_bytes{job="node-exporter"})))* 100 record: node_exporter:memory:used:percent labels: desc: "节点的内存使用百分比" unit: "%" job: "node-exporter" - expr: ((node_memory_MemAvailable_bytes{job="node-exporter"} / (node_memory_MemTotal_bytes{job="node-exporter"})))* 100 record: node_exporter:memory:free:percent labels: desc: "节点的内存剩余百分比" unit: "%" job: "node-exporter" ############################################################################################## # load # - expr: sum by (instance) (node_load1{job="node-exporter"}) record: node_exporter:load:load1 labels: desc: "系统1分钟负载" unit: " " job: "node-exporter" - expr: sum by (instance) (node_load5{job="node-exporter"}) record: node_exporter:load:load5 labels: desc: "系统5分钟负载" unit: " " job: "node-exporter" - expr: sum by (instance) (node_load15{job="node-exporter"}) record: node_exporter:load:load15 labels: desc: "系统15分钟负载" unit: " " job: "node-exporter" ############################################################################################## # disk # - expr: node_filesystem_size_bytes{job="node-exporter" ,fstype=~"ext4|xfs"} record: node_exporter:disk:usage:total labels: desc: "节点的磁盘总量" unit: byte job: "node-exporter" - expr: node_filesystem_avail_bytes{job="node-exporter",fstype=~"ext4|xfs"} record: node_exporter:disk:usage:free labels: desc: "节点的磁盘剩余空间" unit: byte job: "node-exporter" - expr: node_filesystem_size_bytes{job="node-exporter",fstype=~"ext4|xfs"} - node_filesystem_avail_bytes{job="node-exporter",fstype=~"ext4|xfs"} record: node_exporter:disk:usage:used labels: desc: "节点的磁盘使用的空间" unit: byte job: "node-exporter" - expr: (1 - node_filesystem_avail_bytes{job="node-exporter",fstype=~"ext4|xfs"} / node_filesystem_size_bytes{job="node-exporter",fstype=~"ext4|xfs"}) * 100 record: node_exporter:disk:used:percent labels: desc: "节点的磁盘的使用百分比" unit: "%" job: "node-exporter" - expr: irate(node_disk_reads_completed_total{job="node-exporter"}[1m]) record: node_exporter:disk:read:count:rate labels: desc: "节点的磁盘读取速率" unit: "次/秒" job: "node-exporter" - expr: irate(node_disk_writes_completed_total{job="node-exporter"}[1m]) record: node_exporter:disk:write:count:rate labels: desc: "节点的磁盘写入速率" unit: "次/秒" job: "node-exporter" - expr: (irate(node_disk_written_bytes_total{job="node-exporter"}[1m]))/1024/1024 record: node_exporter:disk:read:mb:rate labels: desc: "节点的设备读取MB速率" unit: "MB/s" job: "node-exporter" - expr: (irate(node_disk_read_bytes_total{job="node-exporter"}[1m]))/1024/1024 record: node_exporter:disk:write:mb:rate labels: desc: "节点的设备写入MB速率" unit: "MB/s" job: "node-exporter" ############################################################################################## # filesystem # - expr: (1 -node_filesystem_files_free{job="node-exporter",fstype=~"ext4|xfs"} / node_filesystem_files{job="node-exporter",fstype=~"ext4|xfs"}) * 100 record: node_exporter:filesystem:used:percent labels: desc: "节点的inode的剩余可用的百分比" unit: "%" job: "node-exporter" ############################################################################################# # filefd # - expr: node_filefd_allocated{job="node-exporter"} record: node_exporter:filefd_allocated:count labels: desc: "节点的文件描述符打开个数" unit: "%" job: "node-exporter" - expr: node_filefd_allocated{job="node-exporter"}/node_filefd_maximum{job="node-exporter"} * 100 record: node_exporter:filefd_allocated:percent labels: desc: "节点的文件描述符打开百分比" unit: "%" job: "node-exporter" ############################################################################################# # network # - expr: avg by (environment,instance,device) (irate(node_network_receive_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m])) record: node_exporter:network:netin:bit:rate labels: desc: "节点网卡eth0每秒接收的比特数" unit: "bit/s" job: "node-exporter" - expr: avg by (environment,instance,device) (irate(node_network_transmit_bytes_total{device=~"eth0|eth1|ens33|ens37"}[1m])) record: node_exporter:network:netout:bit:rate labels: desc: "节点网卡eth0每秒发送的比特数" unit: "bit/s" job: "node-exporter" - expr: avg by (environment,instance,device) (irate(node_network_receive_packets_total{device=~"eth0|eth1|ens33|ens37"}[1m])) record: node_exporter:network:netin:packet:rate labels: desc: "节点网卡每秒接收的数据包个数" unit: "个/秒" job: "node-exporter" - expr: avg by (environment,instance,device) (irate(node_network_transmit_packets_total{device=~"eth0|eth1|ens33|ens37"}[1m])) record: node_exporter:network:netout:packet:rate labels: desc: "节点网卡发送的数据包个数" unit: "个/秒" job: "node-exporter" - expr: avg by (environment,instance,device) (irate(node_network_receive_errs_total{device=~"eth0|eth1|ens33|ens37"}[1m])) record: node_exporter:network:netin:error:rate labels: desc: "节点设备驱动器检测到的接收错误包的数量" unit: "个/秒" job: "node-exporter" - expr: avg by (environment,instance,device) (irate(node_network_transmit_errs_total{device=~"eth0|eth1|ens33|ens37"}[1m])) record: node_exporter:network:netout:error:rate labels: desc: "节点设备驱动器检测到的发送错误包的数量" unit: "个/秒" job: "node-exporter" - expr: node_tcp_connection_states{job="node-exporter", state="established"} record: node_exporter:network:tcp:established:count labels: desc: "节点当前established的个数" unit: "个" job: "node-exporter" - expr: node_tcp_connection_states{job="node-exporter", state="time_wait"} record: node_exporter:network:tcp:timewait:count labels: desc: "节点timewait的连接数" unit: "个" job: "node-exporter" - expr: sum by (environment,instance) (node_tcp_connection_states{job="node-exporter"}) record: node_exporter:network:tcp:total:count labels: desc: "节点tcp连接总数" unit: "个" job: "node-exporter" ############################################################################################# # process # - expr: node_processes_state{state="Z"} record: node_exporter:process:zoom:total:count labels: desc: "节点当前状态为zoom的个数" unit: "个" job: "node-exporter" ############################################################################################# # other # - expr: abs(node_timex_offset_seconds{job="node-exporter"}) record: node_exporter:time:offset labels: desc: "节点的时间偏差" unit: "s" job: "node-exporter" ############################################################################################# - expr: count by (instance) ( count by (instance,cpu) (node_cpu_seconds_total{ mode='system'}) ) record: node_exporter:cpu:count # |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
node-exporter-alert-rules.yml groups: - name: node-exporter-alert rules: - alert: node-exporter-down expr: node_exporter:up == 0 for: 1m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 宕机了" description: "instance: {{ $labels.instance }} \n- job: {{ $labels.job }} 关机了, 时间已经1分钟了。" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-cpu-high expr: node_exporter:cpu:total:percent > 80 for: 3m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} cpu 使用率高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-cpu-iowait-high expr: node_exporter:cpu:iowait:percent >= 12 for: 3m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} cpu iowait 使用率高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-load-load1-high expr: (node_exporter:load:load1) > (node_exporter:cpu:count) * 1.2 for: 3m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} load1 使用率高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-memory-high expr: node_exporter:memory:used:percent > 85 for: 3m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} memory 使用率高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-disk-high expr: node_exporter:disk:used:percent > 88 for: 10m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} disk 使用率高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-disk-read:count-high expr: node_exporter:disk:read:count:rate > 3000 for: 2m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} iops read 使用率高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-disk-write-count-high expr: node_exporter:disk:write:count:rate > 3000 for: 2m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} iops write 使用率高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-disk-read-mb-high expr: node_exporter:disk:read:mb:rate > 60 for: 2m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 读取字节数 高于 {{ $value }}" description: "" instance: "{{ $labels.instance }}" value: "{{ $value }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-disk-write-mb-high expr: node_exporter:disk:write:mb:rate > 60 for: 2m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 写入字节数 高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-filefd-allocated-percent-high expr: node_exporter:filefd_allocated:percent > 80 for: 10m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 打开文件描述符 高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-network-netin-error-rate-high expr: node_exporter:network:netin:error:rate > 4 for: 1m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 包进入的错误速率 高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-network-netin-packet-rate-high expr: node_exporter:network:netin:packet:rate > 35000 for: 1m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 包进入速率 高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-network-netout-packet-rate-high expr: node_exporter:network:netout:packet:rate > 35000 for: 1m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 包流出速率 高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-network-tcp-total-count-high expr: node_exporter:network:tcp:total:count > 40000 for: 1m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} tcp连接数量 高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-process-zoom-total-count-high expr: node_exporter:process:zoom:total:count > 10 for: 10m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} 僵死进程数量 高于 {{ $value }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" - alert: node-exporter-time-offset-high expr: node_exporter:time:offset > 0.03 for: 2m labels: severity: info annotations: summary: "instance: {{ $labels.instance }} {{ $labels.desc }} {{ $value }} {{ $labels.unit }}" description: "" value: "{{ $value }}" instance: "{{ $labels.instance }}" grafana: "http://xxxxxxxx.com/d/node-exporter/node-exporter?orgId=1&var-instance={{ $labels.instance }} " console: "https://ecs.console.aliyun.com/#/server/{{ $labels.instanceid }}/detail?regionId=cn-beijing" cloudmonitor: "https://cloudmonitor.console.aliyun.com/#/hostDetail/chart/instanceId={{ $labels.instanceid }}&system=&region=cn-beijing&aliyunhost=true" id: "{{ $labels.instanceid }}" type: "aliyun_meta_ecs_info" |