2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								{
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								  prometheusRules+:: {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    groups+: [
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								      {
							 | 
						
					
						
							
								
									
										
										
										
											2018-08-06 01:46:28 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								        name: 'node-exporter.rules',
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        rules: [
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            // This rule gives the number of CPUs per node.
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_num_cpu:sum',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2021-09-03 03:13:35 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              count without (cpu, mode) (
							 | 
						
					
						
							
								
									
										
										
										
											2021-09-02 06:06:50 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                node_cpu_seconds_total{%(nodeExporterSelector)s,mode="idle"}
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2021-11-04 03:03:27 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            // CPU utilisation is % CPU without {idle,iowait,steal}.
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_cpu_utilisation:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2021-11-04 03:03:27 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              1 - avg without (cpu) (
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                sum without (mode) (rate(node_cpu_seconds_total{%(nodeExporterSelector)s, mode=~"idle|iowait|steal"}[%(rateInterval)s]))
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-12 13:58:43 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            // This is CPU saturation: 1min avg run queue length / number of CPUs.
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-17 14:54:31 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            // Can go over 1.
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            // TODO: There are situation where a run queue >1/core is just normal and fine.
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-22 05:06:27 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            //       We need to clarify how to read this metric and if its usage is helpful at all.
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-12 13:58:43 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_load1_per_cpu:ratio',
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-10 11:07:20 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              (
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-12 13:58:43 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                node_load1{%(nodeExporterSelector)s}
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              /
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-12 13:58:43 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                instance:node_num_cpu:sum{%(nodeExporterSelector)s}
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-22 05:06:27 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            // Memory utilisation (ratio of used memory per instance).
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_memory_utilisation:ratio',
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-10 02:35:48 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              1 - (
							 | 
						
					
						
							
								
									
										
										
										
											2021-09-28 01:22:06 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                (
							 | 
						
					
						
							
								
									
										
										
										
											2021-10-21 03:07:38 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                  node_memory_MemAvailable_bytes{%(nodeExporterSelector)s}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                  or
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                  (
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                    node_memory_Buffers_bytes{%(nodeExporterSelector)s}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                    +
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                    node_memory_Cached_bytes{%(nodeExporterSelector)s}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                    +
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                    node_memory_MemFree_bytes{%(nodeExporterSelector)s}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                    +
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                    node_memory_Slab_bytes{%(nodeExporterSelector)s}
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                  )
							 | 
						
					
						
							
								
									
										
										
										
											2021-09-28 01:22:06 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                )
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-10 11:07:20 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              /
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								                node_memory_MemTotal_bytes{%(nodeExporterSelector)s}
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-10 02:35:48 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							
								
									
										
										
										
											2018-07-13 06:01:01 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_vmstat_pgmajfault:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              rate(node_vmstat_pgmajfault{%(nodeExporterSelector)s}[%(rateInterval)s])
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-22 05:06:27 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            // Disk utilisation (seconds spent, 1 second rate).
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance_device:node_disk_io_time_seconds:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              rate(node_disk_io_time_seconds_total{%(nodeExporterSelector)s, %(diskDeviceSelector)s}[%(rateInterval)s])
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-22 05:06:27 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            // Disk saturation (weighted seconds spent, 1 second rate).
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance_device:node_disk_io_time_weighted_seconds:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              rate(node_disk_io_time_weighted_seconds_total{%(nodeExporterSelector)s, %(diskDeviceSelector)s}[%(rateInterval)s])
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_network_receive_bytes_excluding_lo:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-12 13:58:43 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              sum without (device) (
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                rate(node_network_receive_bytes_total{%(nodeExporterSelector)s, device!="lo"}[%(rateInterval)s])
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_network_transmit_bytes_excluding_lo:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-12 13:58:43 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              sum without (device) (
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                rate(node_network_transmit_bytes_total{%(nodeExporterSelector)s, device!="lo"}[%(rateInterval)s])
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-16 12:18:17 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-17 14:54:31 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								          // TODO: Find out if those drops ever happen on modern switched networks.
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-16 12:18:17 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_network_receive_drop_excluding_lo:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-16 12:18:17 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              sum without (device) (
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                rate(node_network_receive_drop_total{%(nodeExporterSelector)s, device!="lo"}[%(rateInterval)s])
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-16 12:18:17 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          {
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            record: 'instance:node_network_transmit_drop_excluding_lo:rate%(rateInterval)s' % $._config,
							 | 
						
					
						
							
								
									
										
										
										
											2019-07-16 12:18:17 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								            expr: |||
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              sum without (device) (
							 | 
						
					
						
							
								
									
										
										
										
											2021-04-03 03:40:22 -07:00
										 
									 
								 
							 | 
							
								
									
										
									
								
							 | 
							
								
							 | 
							
							
								                rate(node_network_transmit_drop_total{%(nodeExporterSelector)s, device!="lo"}[%(rateInterval)s])
							 | 
						
					
						
							
								
									
										
										
										
											2018-05-08 03:10:29 -07:00
										 
									 
								 
							 | 
							
								
							 | 
							
								
							 | 
							
							
								              )
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								            ||| % $._config,
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								          },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								        ],
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								      },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								    ],
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								  },
							 | 
						
					
						
							| 
								
							 | 
							
								
							 | 
							
								
							 | 
							
							
								}
							 |