2025-11-17 14:22:46 -03:00
{
"uid" : "atlas-pods" ,
"title" : "Atlas Pods" ,
2025-11-17 16:27:38 -03:00
"folderUid" : "atlas-internal" ,
2025-11-17 14:22:46 -03:00
"editable" : true ,
"panels" : [
{
"id" : 1 ,
2025-11-17 16:27:38 -03:00
"type" : "stat" ,
2025-12-02 14:41:39 -03:00
"title" : "Problem Pods" ,
2025-11-17 16:27:38 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 4 ,
"w" : 6 ,
"x" : 0 ,
"y" : 0
} ,
"targets" : [
{
2025-12-12 20:30:00 -03:00
"expr" : "sum(max by (namespace,pod) (kube_pod_status_phase{phase!~\"Running|Succeeded\"})) or on() vector(0)" ,
2025-11-17 16:27:38 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
2025-12-12 20:44:20 -03:00
"mode" : "thresholds"
2025-11-17 16:27:38 -03:00
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 1
}
]
} ,
"unit" : "none" ,
"custom" : {
"displayMode" : "auto"
}
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
}
} ,
{
"id" : 2 ,
"type" : "stat" ,
"title" : "CrashLoop / ImagePull" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 4 ,
"w" : 6 ,
"x" : 6 ,
"y" : 0
} ,
"targets" : [
{
2025-12-12 20:30:00 -03:00
"expr" : "sum(max by (namespace,pod) (kube_pod_container_status_waiting_reason{reason=~\"CrashLoopBackOff|ImagePullBackOff\"})) or on() vector(0)" ,
2025-11-17 16:27:38 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
2025-12-12 20:44:20 -03:00
"mode" : "thresholds"
2025-11-17 16:27:38 -03:00
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 1
}
]
} ,
"unit" : "none" ,
"custom" : {
"displayMode" : "auto"
}
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
}
} ,
{
"id" : 3 ,
"type" : "stat" ,
2025-12-02 14:41:39 -03:00
"title" : "Stuck Terminating (>10m)" ,
2025-11-17 16:27:38 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 4 ,
"w" : 6 ,
"x" : 12 ,
"y" : 0
} ,
"targets" : [
{
2025-12-12 20:30:00 -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))) or on() vector(0)" ,
2025-11-17 16:27:38 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
2025-12-12 20:44:20 -03:00
"mode" : "thresholds"
2025-11-17 16:27:38 -03:00
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 1
}
]
} ,
"unit" : "none" ,
"custom" : {
"displayMode" : "auto"
}
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
}
} ,
{
"id" : 4 ,
"type" : "stat" ,
2025-12-02 14:41:39 -03:00
"title" : "Control Plane Workloads" ,
2025-11-17 16:27:38 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 4 ,
"w" : 6 ,
"x" : 18 ,
"y" : 0
} ,
"targets" : [
{
2025-11-18 16:18:52 -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|flux-system\"})" ,
2025-11-17 16:27:38 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"color" : {
2025-12-12 20:44:20 -03:00
"mode" : "thresholds"
2025-11-17 16:27:38 -03:00
} ,
"mappings" : [ ] ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "red" ,
"value" : 1
}
]
} ,
"unit" : "none" ,
"custom" : {
"displayMode" : "auto"
}
} ,
"overrides" : [ ]
} ,
"options" : {
"colorMode" : "value" ,
"graphMode" : "area" ,
"justifyMode" : "center" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
} ,
"textMode" : "value"
}
} ,
{
"id" : 5 ,
2025-11-17 14:22:46 -03:00
"type" : "table" ,
2025-12-02 14:41:39 -03:00
"title" : "Pods Not Running" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 10 ,
"w" : 24 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 4
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "(time() - kube_pod_created{pod!=\"\"}) * on(namespace,pod) group_left(node) kube_pod_info * on(namespace,pod) group_left(phase) max by (namespace,pod,phase) (kube_pod_status_phase{phase!~\"Running|Succeeded\"})" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "s"
} ,
"overrides" : [ ]
} ,
"options" : {
"showHeader" : true
} ,
"transformations" : [
{
"id" : "labelsToFields" ,
"options" : { }
}
]
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 6 ,
2025-11-17 14:22:46 -03:00
"type" : "table" ,
"title" : "CrashLoop / ImagePull" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 10 ,
"w" : 24 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 14
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 16:27:38 -03:00
"expr" : "(time() - kube_pod_created{pod!=\"\"}) * on(namespace,pod) group_left(node) kube_pod_info * on(namespace,pod,container) group_left(reason) max by (namespace,pod,container,reason) (kube_pod_container_status_waiting_reason{reason=~\"CrashLoopBackOff|ImagePullBackOff\"})" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "s"
} ,
"overrides" : [ ]
} ,
"options" : {
"showHeader" : true
} ,
"transformations" : [
{
"id" : "labelsToFields" ,
"options" : { }
}
]
} ,
{
2025-11-17 16:27:38 -03:00
"id" : 7 ,
2025-11-17 14:22:46 -03:00
"type" : "table" ,
2025-11-17 16:27:38 -03:00
"title" : "Terminating >10m" ,
2025-11-17 14:22:46 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 10 ,
"w" : 24 ,
"x" : 0 ,
2025-11-17 16:27:38 -03:00
"y" : 24
2025-11-17 14:22:46 -03:00
} ,
"targets" : [
{
2025-11-17 18:55:11 -03:00
"expr" : "(((time() - kube_pod_deletion_timestamp{pod!=\"\"}) and on(namespace,pod) (kube_pod_deletion_timestamp{pod!=\"\"} > bool 0)) * on(namespace,pod) group_left(node) kube_pod_info)" ,
2025-11-17 14:22:46 -03:00
"refId" : "A"
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "s"
} ,
"overrides" : [ ]
} ,
"options" : {
"showHeader" : true
} ,
"transformations" : [
{
"id" : "labelsToFields" ,
"options" : { }
} ,
{
"id" : "filterByValue" ,
"options" : {
"match" : "Value" ,
"operator" : "gt" ,
"value" : 600
}
}
]
2025-12-12 18:32:45 -03:00
} ,
{
"id" : 8 ,
"type" : "piechart" ,
2025-12-12 20:30:00 -03:00
"title" : "Node Pod Share" ,
2025-12-12 18:32:45 -03:00
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 12 ,
"y" : 34
} ,
"targets" : [
{
2025-12-12 20:40:32 -03:00
"expr" : "(sum(kube_pod_info{pod!=\"\" , node!=\"\"}) by (node) / clamp_min(sum(kube_pod_info{pod!=\"\" , node!=\"\"}), 1)) * 100" ,
2025-12-12 18:32:45 -03:00
"refId" : "A" ,
"legendFormat" : "{{namespace}}"
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "percent" ,
"color" : {
"mode" : "palette-classic"
}
} ,
"overrides" : [ ]
} ,
"options" : {
"legend" : {
"displayMode" : "list" ,
"placement" : "right"
} ,
"pieType" : "pie" ,
2025-12-12 20:40:32 -03:00
"displayLabels" : [ ] ,
2025-12-12 18:32:45 -03:00
"tooltip" : {
"mode" : "single"
} ,
"colorScheme" : "interpolateSpectral" ,
"colorBy" : "value" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
}
}
2025-12-12 18:45:29 -03:00
} ,
{
"id" : 9 ,
"type" : "bargauge" ,
"title" : "Top Nodes by Pod Count" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 8 ,
"w" : 12 ,
"x" : 0 ,
"y" : 34
} ,
"targets" : [
{
2025-12-12 19:09:51 -03:00
"expr" : "topk(12, sum(kube_pod_info{pod!=\"\" , node!=\"\"}) by (node))" ,
2025-12-12 18:45:29 -03:00
"refId" : "A" ,
2025-12-12 20:30:00 -03:00
"legendFormat" : "{{node}}" ,
"instant" : true
2025-12-12 18:45:29 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "none" ,
"min" : 0 ,
"max" : null ,
"thresholds" : {
"mode" : "absolute" ,
"steps" : [
{
"color" : "green" ,
"value" : null
} ,
{
"color" : "yellow" ,
"value" : 50
} ,
{
"color" : "orange" ,
2025-12-12 20:20:13 -03:00
"value" : 75
2025-12-12 18:45:29 -03:00
} ,
{
"color" : "red" ,
2025-12-12 20:20:13 -03:00
"value" : 100
2025-12-12 18:45:29 -03:00
}
]
2025-12-12 20:20:13 -03:00
} ,
"decimals" : 0
2025-12-12 18:45:29 -03:00
} ,
"overrides" : [ ]
} ,
"options" : {
"displayMode" : "gradient" ,
"orientation" : "horizontal" ,
"reduceOptions" : {
"calcs" : [
"lastNotNull"
] ,
"fields" : "" ,
"values" : false
}
2025-12-12 18:51:43 -03:00
} ,
"transformations" : [
{
"id" : "sortBy" ,
"options" : {
"fields" : [
"Value"
] ,
"order" : "desc"
}
2025-12-12 18:56:13 -03:00
} ,
{
"id" : "limit" ,
"options" : {
"limit" : 12
}
2025-12-12 18:51:43 -03:00
}
]
2025-12-13 03:57:20 -03:00
} ,
{
"id" : 10 ,
"type" : "table" ,
"title" : "Namespace Plurality by Node" ,
"datasource" : {
"type" : "prometheus" ,
"uid" : "atlas-vm"
} ,
"gridPos" : {
"h" : 8 ,
"w" : 24 ,
"x" : 0 ,
"y" : 42
} ,
"targets" : [
{
2025-12-13 11:48:44 -03:00
"expr" : "( sum by (namespace,node) (kube_pod_info{pod!=\"\"}) / sum by (namespace) (kube_pod_info{pod!=\"\"}))* on(namespace) group_left(node)( (sum by (namespace,node) (kube_pod_info{pod!=\"\"}) / sum by (namespace) (kube_pod_info{pod!=\"\"})) >= on(namespace) group_left() (max by (namespace) (sum by (namespace,node) (kube_pod_info{pod!=\"\"}) / sum by (namespace) (kube_pod_info{pod!=\"\"})) - 1e-9))" ,
2025-12-13 04:00:57 -03:00
"refId" : "A" ,
"instant" : true
2025-12-13 03:57:20 -03:00
}
] ,
"fieldConfig" : {
"defaults" : {
"unit" : "percent"
} ,
"overrides" : [ ]
} ,
"options" : {
"showHeader" : true
} ,
"transformations" : [
{
"id" : "labelsToFields" ,
"options" : { }
} ,
{
"id" : "sortBy" ,
"options" : {
"fields" : [
2025-12-13 04:10:10 -03:00
"node" ,
2025-12-13 03:57:20 -03:00
"Value"
] ,
2025-12-13 04:10:10 -03:00
"order" : "asc"
2025-12-13 03:57:20 -03:00
}
}
]
2025-11-17 14:22:46 -03:00
}
] ,
"time" : {
"from" : "now-12h" ,
"to" : "now"
} ,
"annotations" : {
"list" : [ ]
} ,
"schemaVersion" : 39 ,
"style" : "dark" ,
"tags" : [
"atlas" ,
"pods"
]
}