2025-11-17 14:22:46 -03:00
{
"uid" : "atlas-overview" ,
"title" : "Atlas Overview" ,
2025-11-17 16:27:38 -03:00
"folderUid" : "atlas-overview" ,
"editable" : false ,
2025-11-17 14:22:46 -03:00
"annotations" : {
2025-11-17 16:27:38 -03:00
"list" : [ ]
2025-11-17 14:22:46 -03:00
} ,
"panels" : [
{
"id" : 1 ,
"type" : "stat" ,
2025-11-17 19:49:50 -03:00
"title" : "Workers ready" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 4 ,
"x" : 0 ,
"y" : 0
} ,
"targets" : [
{
2025-11-17 19:49:50 -03:00
"expr" : "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\",node=~\"titan-04|titan-05|titan-06|titan-07|titan-08|titan-09|titan-10|titan-11|titan-12|titan-13|titan-14|titan-15|titan-16|titan-17|titan-18|titan-19|titan-22|titan-24\"})" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
2025-11-17 19:49:50 -03:00
"color" : "red" ,
2025-11-17 14:22:46 -03:00
"value" : null
} ,
2025-11-17 19:49:50 -03:00
{
"color" : "orange" ,
"value" : 16
} ,
{
"color" : "yellow" ,
"value" : 17
} ,
2025-11-17 14:22:46 -03:00
{
"color" : "green" ,
2025-11-17 19:49:50 -03:00
"value" : 18
2025-11-17 14:22:46 -03:00
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "none" ,
"custom" : {
2025-11-17 19:49:50 -03:00
"displayMode" : "auto" ,
"valueSuffix" : "/18"
2025-11-17 16:27:38 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
}
} ,
{
"id" : 2 ,
"type" : "stat" ,
2025-11-17 19:49:50 -03:00
"title" : "Control plane ready" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 4 ,
"x" : 4 ,
"y" : 0
} ,
"targets" : [
{
2025-11-17 19:49:50 -03:00
"expr" : "sum(kube_node_status_condition{condition=\"Ready\",status=\"true\",node=~\"titan-0a|titan-0b|titan-0c\"})" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
2025-11-17 16:27:38 -03:00
"color" : "red" ,
2025-11-17 14:22:46 -03:00
"value" : null
} ,
{
"color" : "green" ,
2025-11-17 19:49:50 -03:00
"value" : 3
2025-11-17 14:22:46 -03:00
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "none" ,
"custom" : {
"displayMode" : "auto" ,
2025-11-17 19:49:50 -03:00
"valueSuffix" : "/3"
2025-11-17 16:27:38 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
}
} ,
{
"id" : 3 ,
"type" : "stat" ,
2025-11-17 19:49:50 -03:00
"title" : "Control plane workloads" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 4 ,
"x" : 8 ,
"y" : 0
} ,
"targets" : [
{
2025-11-17 19:49:50 -03:00
"expr" : "sum(kube_pod_info{node=~\"titan-0a|titan-0b|titan-0c\",namespace!~\"kube-system|kube-public|kube-node-lease|longhorn-system|monitoring\"})" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
2025-11-17 19:49:50 -03:00
"color" : "green" ,
2025-11-17 14:22:46 -03:00
"value" : null
} ,
{
2025-11-17 19:49:50 -03:00
"color" : "yellow" ,
"value" : 1
} ,
{
"color" : "orange" ,
"value" : 2
} ,
{
"color" : "red" ,
2025-11-17 16:27:38 -03:00
"value" : 3
2025-11-17 14:22:46 -03:00
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "none" ,
"custom" : {
2025-11-17 19:49:50 -03:00
"displayMode" : "auto"
2025-11-17 16:27:38 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
2025-11-17 19:49:50 -03:00
} ,
"links" : [
{
"title" : "Open atlas-pods dashboard" ,
"url" : "/d/atlas-pods" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
"id" : 4 ,
"type" : "stat" ,
2025-11-17 19:49:50 -03:00
"title" : "Problem pods" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 4 ,
"x" : 12 ,
"y" : 0
} ,
"targets" : [
{
2025-11-17 19:49:50 -03:00
"expr" : "sum(max by (namespace,pod) (kube_pod_status_phase{phase!~\"Running|Succeeded\"}))" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
2025-11-17 16:27:38 -03:00
"color" : "green" ,
2025-11-17 14:22:46 -03:00
"value" : null
} ,
{
2025-11-17 19:24:03 -03:00
"color" : "yellow" ,
2025-11-17 14:22:46 -03:00
"value" : 1
2025-11-17 19:24:03 -03:00
} ,
{
"color" : "orange" ,
"value" : 2
} ,
{
"color" : "red" ,
"value" : 3
2025-11-17 14:22:46 -03:00
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "none" ,
"custom" : {
"displayMode" : "auto"
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-pods dashboard" ,
"url" : "/d/atlas-pods" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
"id" : 5 ,
"type" : "stat" ,
2025-11-17 19:49:50 -03:00
"title" : "Stuck terminating" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 4 ,
"x" : 16 ,
"y" : 0
} ,
"targets" : [
{
2025-11-17 19:49:50 -03:00
"expr" : "sum(max by (namespace,pod) (((time() - kube_pod_deletion_timestamp{pod!=\"\"}) > bool 600) and on(namespace,pod) (kube_pod_deletion_timestamp{pod!=\"\"} > bool 0)))" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
2025-11-17 16:27:38 -03:00
"color" : "green" ,
2025-11-17 14:22:46 -03:00
"value" : null
} ,
{
2025-11-17 19:24:03 -03:00
"color" : "yellow" ,
2025-11-17 14:22:46 -03:00
"value" : 1
2025-11-17 19:24:03 -03:00
} ,
{
"color" : "orange" ,
"value" : 2
} ,
{
"color" : "red" ,
"value" : 3
2025-11-17 14:22:46 -03:00
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "none" ,
"custom" : {
"displayMode" : "auto"
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-pods dashboard" ,
"url" : "/d/atlas-pods" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
"id" : 6 ,
"type" : "stat" ,
2025-11-17 19:49:50 -03:00
"title" : "Running pods" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 4 ,
"x" : 20 ,
"y" : 0
} ,
"targets" : [
{
2025-11-17 19:49:50 -03:00
"expr" : "sum(kube_pod_status_phase{phase=\"Running\"})" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
2025-11-17 19:49:50 -03:00
"color" : "rgba(115, 115, 115, 1)" ,
2025-11-17 14:22:46 -03:00
"value" : null
} ,
{
2025-11-17 19:49:50 -03:00
"color" : "green" ,
2025-11-17 14:22:46 -03:00
"value" : 1
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "none" ,
"custom" : {
"displayMode" : "auto"
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
2025-11-17 19:49:50 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
{
"id" : 7 ,
"type" : "stat" ,
"title" : "Hottest node: CPU" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
2025-11-17 16:27:38 -03:00
"w" : 6 ,
"x" : 0 ,
"y" : 5
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 20:00:40 -03:00
"expr" : "topk(1, avg by (node) (((1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))) * 100) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\")))" ,
2025-11-17 19:24:03 -03:00
"refId" : "A" ,
2025-11-17 20:04:50 -03:00
"legendFormat" : "{{node}}\\n" ,
2025-11-17 19:38:40 -03:00
"instant" : true
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "percentage" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "yellow" ,
"value" : 70
} ,
{
"color" : "red" ,
"value" : 85
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "percent" ,
"custom" : {
"displayMode" : "auto"
2025-11-17 19:56:57 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
2025-11-17 19:49:50 -03:00
"textMode" : "name_and_value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-nodes dashboard" ,
"url" : "/d/atlas-nodes" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
"id" : 8 ,
"type" : "stat" ,
"title" : "Hottest node: RAM" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
2025-11-17 16:27:38 -03:00
"w" : 6 ,
"x" : 6 ,
"y" : 5
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 20:00:40 -03:00
"expr" : "topk(1, avg by (node) ((avg by (instance) ((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100)) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\")))" ,
2025-11-17 19:24:03 -03:00
"refId" : "A" ,
2025-11-17 20:04:50 -03:00
"legendFormat" : "{{node}}\\n" ,
2025-11-17 19:38:40 -03:00
"instant" : true
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "percentage" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "yellow" ,
"value" : 70
} ,
{
"color" : "red" ,
"value" : 85
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "percent" ,
"custom" : {
"displayMode" : "auto"
2025-11-17 19:56:57 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
2025-11-17 19:49:50 -03:00
"textMode" : "name_and_value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-nodes dashboard" ,
"url" : "/d/atlas-nodes" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
"id" : 9 ,
2025-11-17 16:27:38 -03:00
"type" : "stat" ,
2025-11-17 20:00:40 -03:00
"title" : "Hottest node: NET (rx+tx)" ,
2025-11-17 16:27:38 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 6 ,
"x" : 12 ,
"y" : 5
} ,
"targets" : [
{
2025-11-17 20:00:40 -03:00
"expr" : "topk(1, avg by (node) (rate(container_network_receive_bytes_total{namespace!=\"\" ,pod!=\"\"}[5m]) + rate(container_network_transmit_bytes_total{namespace!=\"\" ,pod!=\"\"}[5m])))" ,
2025-11-17 19:24:03 -03:00
"refId" : "A" ,
2025-11-17 20:04:50 -03:00
"legendFormat" : "{{node}}\\n" ,
2025-11-17 19:38:40 -03:00
"instant" : true
2025-11-17 16:27:38 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "rgba(115, 115, 115, 1)" ,
"value" : null
} ,
{
"color" : "green" ,
"value" : 1
}
]
} ,
2025-11-17 18:55:11 -03:00
"unit" : "Bps" ,
2025-11-17 16:27:38 -03:00
"custom" : {
"displayMode" : "auto"
2025-11-17 19:56:57 -03:00
}
2025-11-17 16:27:38 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
2025-11-17 19:49:50 -03:00
"textMode" : "name_and_value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-nodes dashboard" ,
"url" : "/d/atlas-nodes" ,
"targetBlank" : true
}
]
} ,
{
"id" : 10 ,
"type" : "stat" ,
2025-11-17 20:00:40 -03:00
"title" : "Hottest node: I/O (r+w)" ,
2025-11-17 16:27:38 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 5 ,
"w" : 6 ,
"x" : 18 ,
"y" : 5
} ,
"targets" : [
{
2025-11-17 20:00:40 -03:00
"expr" : "topk(1, avg by (node) (rate(node_disk_read_bytes_total[5m]) + rate(node_disk_written_bytes_total[5m])))" ,
2025-11-17 19:24:03 -03:00
"refId" : "A" ,
2025-11-17 20:04:50 -03:00
"legendFormat" : "{{node}}\\n" ,
2025-11-17 19:38:40 -03:00
"instant" : true
2025-11-17 16:27:38 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "rgba(115, 115, 115, 1)" ,
"value" : null
} ,
{
"color" : "green" ,
"value" : 1
}
]
} ,
2025-11-17 18:55:11 -03:00
"unit" : "Bps" ,
2025-11-17 16:27:38 -03:00
"custom" : {
"displayMode" : "auto"
2025-11-17 19:56:57 -03:00
}
2025-11-17 16:27:38 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
2025-11-17 19:49:50 -03:00
"textMode" : "name_and_value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-nodes dashboard" ,
"url" : "/d/atlas-nodes" ,
"targetBlank" : true
}
]
} ,
{
"id" : 11 ,
2025-11-17 14:22:46 -03:00
"type" : "piechart" ,
"title" : "Namespace CPU share" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 9 ,
"w" : 12 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 10
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "topk(10, sum(rate(container_cpu_usage_seconds_total{namespace!=\"\",pod!=\"\"}[5m])) by (namespace))" ,
2025-11-17 19:38:40 -03:00
"refId" : "A" ,
"legendFormat" : "{{namespace}}"
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
2025-11-17 19:38:40 -03:00
"unit" : "percent"
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
"displayMode" : "list" ,
"placement" : "right"
} ,
"pieType" : "pie" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
}
}
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 12 ,
2025-11-17 14:22:46 -03:00
"type" : "piechart" ,
"title" : "Namespace RAM share" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 9 ,
"w" : 12 ,
"x" : 12 ,
2025-11-17 16:27:38 -03:00
"y" : 10
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "topk(10, sum(container_memory_working_set_bytes{namespace!=\"\",pod!=\"\"}) by (namespace))" ,
2025-11-17 19:38:40 -03:00
"refId" : "A" ,
"legendFormat" : "{{namespace}}"
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
2025-11-17 19:38:40 -03:00
"unit" : "percent"
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
"displayMode" : "list" ,
"placement" : "right"
} ,
"pieType" : "pie" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
}
}
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 13 ,
2025-11-17 14:22:46 -03:00
"type" : "timeseries" ,
"title" : "Cluster node CPU" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 19
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "avg by (node) (((1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))) * 100) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\"))" ,
2025-11-17 14:22:46 -03:00
"refId" : "A" ,
"legendFormat" : "{{node}}"
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "percent"
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
"displayMode" : "table" ,
"placement" : "right" ,
"calcs" : [
"last"
]
} ,
"tooltip" : {
"mode" : "multi"
}
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-nodes dashboard" ,
"url" : "/d/atlas-nodes" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 14 ,
2025-11-17 14:22:46 -03:00
"type" : "timeseries" ,
"title" : "Cluster node RAM" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
2025-11-17 16:27:38 -03:00
"y" : 19
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "avg by (node) ((avg by (instance) ((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100)) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\"))" ,
2025-11-17 14:22:46 -03:00
"refId" : "A" ,
"legendFormat" : "{{node}}"
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "percent"
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
"displayMode" : "table" ,
"placement" : "right" ,
"calcs" : [
"last"
]
} ,
"tooltip" : {
"mode" : "multi"
}
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-nodes dashboard" ,
"url" : "/d/atlas-nodes" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 15 ,
"type" : "timeseries" ,
"title" : "Control plane CPU (incl. titan-db)" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
2025-11-17 16:27:38 -03:00
"h" : 7 ,
2025-11-17 14:22:46 -03:00
"w" : 12 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 27
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "(avg by (node) (((1 - avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m]))) * 100) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\"))) * on(node) group_left() label_replace(node_uname_info{nodename=~\"titan-0a|titan-0b|titan-0c|titan-db\"}, \"node\", \"$1\", \"nodename\", \"(.*)\")" ,
"refId" : "A" ,
"legendFormat" : "{{node}}"
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
2025-11-17 16:27:38 -03:00
"unit" : "percent"
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
2025-11-17 16:27:38 -03:00
"legend" : {
"displayMode" : "table" ,
"placement" : "right"
} ,
"tooltip" : {
"mode" : "multi"
2025-11-17 14:22:46 -03:00
}
2025-11-17 16:27:38 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 16 ,
"type" : "timeseries" ,
"title" : "Control plane RAM (incl. titan-db)" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
2025-11-17 16:27:38 -03:00
"h" : 7 ,
2025-11-17 14:22:46 -03:00
"w" : 12 ,
"x" : 12 ,
2025-11-17 16:27:38 -03:00
"y" : 27
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "(avg by (node) ((avg by (instance) ((node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100)) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\"))) * on(node) group_left() label_replace(node_uname_info{nodename=~\"titan-0a|titan-0b|titan-0c|titan-db\"}, \"node\", \"$1\", \"nodename\", \"(.*)\")" ,
"refId" : "A" ,
"legendFormat" : "{{node}}"
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
2025-11-17 16:27:38 -03:00
"unit" : "percent"
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
2025-11-17 16:27:38 -03:00
"legend" : {
"displayMode" : "table" ,
"placement" : "right"
2025-11-17 14:22:46 -03:00
} ,
2025-11-17 16:27:38 -03:00
"tooltip" : {
"mode" : "multi"
2025-11-17 14:22:46 -03:00
}
2025-11-17 16:27:38 -03:00
}
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 17 ,
2025-11-17 14:22:46 -03:00
"type" : "timeseries" ,
2025-11-17 16:27:38 -03:00
"title" : "Cluster ingress throughput" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 7 ,
"w" : 12 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 34
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "sum(rate(container_network_receive_bytes_total{namespace!=\"\" ,pod!=\"\"}[5m])) or on() vector(0)" ,
"refId" : "A"
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
2025-11-17 18:55:11 -03:00
"unit" : "Bps"
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
2025-11-17 16:27:38 -03:00
"displayMode" : "list" ,
2025-11-17 14:22:46 -03:00
"placement" : "bottom"
} ,
"tooltip" : {
"mode" : "multi"
}
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-network dashboard" ,
"url" : "/d/atlas-network" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 18 ,
2025-11-17 14:22:46 -03:00
"type" : "timeseries" ,
2025-11-17 16:27:38 -03:00
"title" : "Cluster egress throughput" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 7 ,
"w" : 12 ,
"x" : 12 ,
2025-11-17 16:27:38 -03:00
"y" : 34
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "sum(rate(container_network_transmit_bytes_total{namespace!=\"\" ,pod!=\"\"}[5m])) or on() vector(0)" ,
"refId" : "A"
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
2025-11-17 18:55:11 -03:00
"unit" : "Bps"
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
2025-11-17 16:27:38 -03:00
"displayMode" : "list" ,
2025-11-17 14:22:46 -03:00
"placement" : "bottom"
} ,
"tooltip" : {
"mode" : "multi"
}
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-network dashboard" ,
"url" : "/d/atlas-network" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 19 ,
2025-11-17 14:22:46 -03:00
"type" : "timeseries" ,
"title" : "Root filesystem usage" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 41
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "avg by (node) ((avg by (instance) ((1 - (node_filesystem_avail_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"} / node_filesystem_size_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"})) * 100)) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\"))" ,
2025-11-17 14:22:46 -03:00
"refId" : "A" ,
"legendFormat" : "{{node}}"
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "percent"
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
"displayMode" : "table" ,
"placement" : "right" ,
"calcs" : [
"last"
]
} ,
"tooltip" : {
"mode" : "multi"
}
} ,
2025-11-17 16:27:38 -03:00
"timeFrom" : "30d" ,
"links" : [
{
"title" : "Open atlas-storage dashboard" ,
"url" : "/d/atlas-storage" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 20 ,
2025-11-17 14:22:46 -03:00
"type" : "bargauge" ,
"title" : "Nodes closest to full root disks" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
2025-11-17 16:27:38 -03:00
"y" : 41
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "topk(8, avg by (node) ((avg by (instance) ((1 - (node_filesystem_avail_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"} / node_filesystem_size_bytes{mountpoint=\"/\",fstype!~\"tmpfs|overlay\"})) * 100)) * on(instance) group_left(node) label_replace(node_uname_info{nodename!=\"\"}, \"node\", \"$1\", \"nodename\", \"(.*)\")))" ,
"refId" : "A"
2025-11-17 14:22:46 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "percent" ,
"min" : 0 ,
"max" : 100 ,
"thresholds" : {
2025-11-17 16:27:38 -03:00
"mode" : "absolute" ,
2025-11-17 14:22:46 -03:00
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "yellow" ,
"value" : 50
} ,
{
"color" : "orange" ,
"value" : 70
} ,
{
"color" : "red" ,
"value" : 85
}
]
2025-11-17 16:27:38 -03:00
} ,
"displayName" : "{{node}}"
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"displayMode" : "gradient" ,
"orientation" : "horizontal" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
}
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-storage dashboard" ,
"url" : "/d/atlas-storage" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 21 ,
2025-11-17 14:22:46 -03:00
"type" : "stat" ,
"title" : "Astreae usage" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 6 ,
"w" : 6 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 49
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
"expr" : "100 - (sum(node_filesystem_avail_bytes{mountpoint=\"/mnt/astreae\",fstype!~\"tmpfs|overlay\"}) / sum(node_filesystem_size_bytes{mountpoint=\"/mnt/astreae\",fstype!~\"tmpfs|overlay\"}) * 100)" ,
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "percentage" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "yellow" ,
"value" : 70
} ,
{
"color" : "red" ,
"value" : 85
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "percent" ,
"custom" : {
"displayMode" : "auto"
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-storage dashboard" ,
"url" : "/d/atlas-storage" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 22 ,
2025-11-17 14:22:46 -03:00
"type" : "stat" ,
"title" : "Asteria usage" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 6 ,
"w" : 6 ,
"x" : 6 ,
2025-11-17 16:27:38 -03:00
"y" : 49
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
"expr" : "100 - (sum(node_filesystem_avail_bytes{mountpoint=\"/mnt/asteria\",fstype!~\"tmpfs|overlay\"}) / sum(node_filesystem_size_bytes{mountpoint=\"/mnt/asteria\",fstype!~\"tmpfs|overlay\"}) * 100)" ,
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "percentage" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "yellow" ,
"value" : 70
} ,
{
"color" : "red" ,
"value" : 85
}
]
} ,
2025-11-17 16:27:38 -03:00
"unit" : "percent" ,
"custom" : {
"displayMode" : "auto"
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-storage dashboard" ,
"url" : "/d/atlas-storage" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 23 ,
2025-11-17 14:22:46 -03:00
"type" : "stat" ,
"title" : "Astreae free" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 6 ,
"w" : 6 ,
"x" : 12 ,
2025-11-17 16:27:38 -03:00
"y" : 49
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
"expr" : "sum(node_filesystem_avail_bytes{mountpoint=\"/mnt/astreae\",fstype!~\"tmpfs|overlay\"})" ,
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "rgba(115, 115, 115, 1)" ,
"value" : null
} ,
{
"color" : "green" ,
"value" : 1
}
]
} ,
2025-11-17 18:55:11 -03:00
"unit" : "decbytes" ,
2025-11-17 16:27:38 -03:00
"custom" : {
"displayMode" : "auto"
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Open atlas-storage dashboard" ,
"url" : "/d/atlas-storage" ,
"targetBlank" : true
}
]
2025-11-17 14:22:46 -03:00
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 24 ,
2025-11-17 14:22:46 -03:00
"type" : "stat" ,
"title" : "Asteria free" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 6 ,
"w" : 6 ,
"x" : 18 ,
2025-11-17 16:27:38 -03:00
"y" : 49
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
"expr" : "sum(node_filesystem_avail_bytes{mountpoint=\"/mnt/asteria\",fstype!~\"tmpfs|overlay\"})" ,
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
"mode" : "palette-classic"
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "rgba(115, 115, 115, 1)" ,
"value" : null
} ,
{
"color" : "green" ,
"value" : 1
}
]
} ,
2025-11-17 18:55:11 -03:00
"unit" : "decbytes" ,
2025-11-17 16:27:38 -03:00
"custom" : {
"displayMode" : "auto"
}
2025-11-17 14:22:46 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
} ,
2025-11-17 16:27:38 -03:00
"links" : [
2025-11-17 14:22:46 -03:00
{
2025-11-17 16:27:38 -03:00
"title" : "Open atlas-storage dashboard" ,
"url" : "/d/atlas-storage" ,
"targetBlank" : true
2025-11-17 14:22:46 -03:00
}
]
} ,
{
"id" : 25 ,
"type" : "text" ,
"title" : "About this dashboard" ,
"gridPos" : {
"h" : 5 ,
"w" : 24 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 55
2025-11-17 14:22:46 -03:00
} ,
"datasource" : null ,
"options" : {
"mode" : "markdown" ,
2025-11-17 16:27:38 -03:00
"content" : "### Atlas Overview\n- Anonymous users land here; follow the panel links for pod/node/storage/network drill-downs.\n- Control plane workload count flags any non-system pods that slipped onto the HA nodes.\n- Problem and stuck pods use kube-state-metrics so counts and detail tables match exactly."
2025-11-17 14:22:46 -03:00
}
}
] ,
"schemaVersion" : 39 ,
"style" : "dark" ,
"tags" : [
"atlas" ,
"overview"
] ,
"templating" : {
"list" : [ ]
} ,
"time" : {
"from" : "now-12h" ,
"to" : "now"
2025-11-17 16:27:38 -03:00
} ,
"links" : [
{
"title" : "Atlas Pods" ,
"type" : "dashboard" ,
"dashboardUid" : "atlas-pods" ,
"keepTime" : false
} ,
{
"title" : "Atlas Nodes" ,
"type" : "dashboard" ,
"dashboardUid" : "atlas-nodes" ,
"keepTime" : false
} ,
{
"title" : "Atlas Storage" ,
"type" : "dashboard" ,
"dashboardUid" : "atlas-storage" ,
"keepTime" : false
} ,
{
"title" : "Atlas Network" ,
"type" : "dashboard" ,
"dashboardUid" : "atlas-network" ,
"keepTime" : false
}
]
2025-11-17 14:22:46 -03:00
}