A cada cluster disponibilizado, possuimos um endpoint para realizar a Observabilidade/Monitoramento dos ambientes. Para tal, utilizamos o Grafana como dashboard das informações integrado com o prometheus.
Para acessar:
Utilizar o usuário e senha de rede da TOTVS com o GOOGLE |
Os dashs disponibilizados pelo time de TKS nos auxiliam na analise e saúde da infra-estrutura, assim como o uso do ambiente por parte dos clientes. Além destes, customizamos um dashboard para o time de SRE avaliar em tempo real o uso dos recursos dos Namespaces e alguns pontos de falha que podemos detectar:
Em caso de novos clusters, basta importar o json:
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"id": 17,
"links": [],
"panels": [
{
"datasource": null,
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {},
"decimals": 0,
"mappings": [],
"max": 60,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 2,
"x": 0,
"y": 0
},
"id": 14,
"options": {
"displayMode": "lcd",
"orientation": "vertical",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"showUnfilled": true
},
"pluginVersion": "7.0.5",
"targets": [
{
"expr": "sum by (value) (count by (namespace)(kube_pod_info{pod=~\"protheus-dbaccess.*\",namespace!~\".*development\",namespace!~\".*release\"}) >= 1)",
"format": "table",
"instant": true,
"interval": "",
"legendFormat": "{{development}}",
"refId": "A"
}
],
"timeFrom": null,
"timeShift": null,
"title": "Production",
"type": "bargauge"
},
{
"datasource": null,
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {},
"decimals": 0,
"mappings": [],
"max": 60,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 2,
"x": 2,
"y": 0
},
"id": 21,
"options": {
"displayMode": "lcd",
"orientation": "vertical",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"showUnfilled": true
},
"pluginVersion": "7.0.5",
"targets": [
{
"expr": "sum by (value) (count by (namespace)(kube_pod_info{pod=~\"protheus-dbaccess.*\",namespace=~\".*development\"}) >= 1)",
"format": "table",
"instant": true,
"legendFormat": "{{development}}",
"refId": "A"
}
],
"timeFrom": null,
"timeShift": null,
"title": "Development",
"type": "bargauge"
},
{
"datasource": null,
"description": "",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {},
"decimals": 0,
"mappings": [],
"max": 60,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 4,
"w": 2,
"x": 4,
"y": 0
},
"id": 22,
"options": {
"displayMode": "lcd",
"orientation": "vertical",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"showUnfilled": true
},
"pluginVersion": "7.0.5",
"targets": [
{
"expr": "sum by (value) (count by (namespace)(kube_pod_info{pod=~\"protheus-dbaccess.*\",namespace=~\".*release\"}) >= 1)",
"format": "table",
"instant": true,
"interval": "",
"legendFormat": "{{development}}",
"refId": "A"
}
],
"timeFrom": null,
"timeShift": null,
"title": "Release",
"type": "bargauge"
},
{
"columns": [],
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fontSize": "100%",
"gridPos": {
"h": 21,
"w": 8,
"x": 6,
"y": 0
},
"id": 7,
"pageSize": null,
"showHeader": true,
"sort": {
"col": 3,
"desc": true
},
"styles": [
{
"alias": "",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"mappingType": 1,
"pattern": "Time",
"thresholds": [],
"type": "hidden",
"unit": "short"
},
{
"alias": "appserver",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"mappingType": 1,
"pattern": "Value #A",
"thresholds": [],
"type": "number",
"unit": "short"
},
{
"alias": "pods",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"mappingType": 1,
"pattern": "Value #B",
"thresholds": [],
"type": "number",
"unit": "short"
},
{
"alias": "config",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"mappingType": 1,
"pattern": "Value #C",
"thresholds": [],
"type": "number",
"unit": "short"
},
{
"alias": "rest",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"mappingType": 1,
"pattern": "Value #D",
"thresholds": [],
"type": "number",
"unit": "short"
}
],
"targets": [
{
"expr": "sort (count by (namespace)(kube_pod_info{pod=~\"protheus-appserver-.*\"}) >= 1)",
"format": "table",
"instant": true,
"legendFormat": "{{namespace}}",
"refId": "A"
},
{
"expr": "sort (count by (namespace)(kube_pod_info{pod=~\"protheus-config-.*\"}) >= 1)",
"format": "table",
"instant": true,
"legendFormat": "{{namespace}}",
"refId": "C"
},
{
"expr": "sort (count by (namespace)(kube_pod_info{pod=~\"protheus-rest-.*\"}) >= 1)",
"format": "table",
"instant": true,
"legendFormat": "{{namespace}}",
"refId": "D"
},
{
"expr": "(count by (namespace)(kube_pod_info{pod=~\"protheus-sleeper.*\"}) >= 1) * (count by (namespace)(kube_pod_status_phase{phase=\"Running\"} >= 1) > 1)",
"format": "table",
"instant": true,
"legendFormat": "{{namespace}}",
"refId": "B"
}
],
"timeFrom": null,
"timeShift": null,
"title": "Online users",
"transform": "table",
"type": "table-old"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 8,
"w": 10,
"x": 14,
"y": 0
},
"hiddenSeries": false,
"id": 17,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "(kube_pod_container_status_restarts_total{container=~\"protheus.*\"}) > 0",
"legendFormat": "{{namespace}}:{{pod}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Restarts Components",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 2,
"x": 0,
"y": 4
},
"id": 4,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false,
"ymax": null,
"ymin": null
},
"tableColumn": "",
"targets": [
{
"expr": "count(kube_pod_info{pod=~\"protheus-appserver-.*\"})",
"instant": true,
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Appservers",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "avg"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 2,
"x": 2,
"y": 4
},
"id": 10,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"pluginVersion": "6.4.4",
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false,
"ymax": null,
"ymin": null
},
"tableColumn": "",
"targets": [
{
"expr": "count(kube_pod_info{pod=~\"protheus-config.*\"})",
"instant": true,
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Configs",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "avg"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 3,
"w": 2,
"x": 4,
"y": 4
},
"id": 20,
"interval": null,
"links": [],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"pluginVersion": "6.4.4",
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false,
"ymax": null,
"ymin": null
},
"tableColumn": "",
"targets": [
{
"expr": "count(kube_pod_info{pod=~\"protheus-rest.*\"})",
"instant": true,
"interval": "",
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Rest",
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "avg"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 7
},
"hiddenSeries": false,
"id": 5,
"interval": "",
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "count by (namespace)(kube_pod_info{pod=~\"protheus-appserver-.*\"}) >= 1",
"interval": "",
"legendFormat": "{{namespace}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Online Protheus Appserver Users by topology",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"decimals": null,
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "2",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"cacheTimeout": null,
"datasource": null,
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"custom": {},
"mappings": [
{
"id": 0,
"op": "=",
"text": "N/A",
"type": 1,
"value": "null"
}
],
"max": 60,
"min": 0,
"nullValueMode": "connected",
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "#EAB839",
"value": 50
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 14,
"y": 8
},
"id": 12,
"links": [],
"options": {
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"showThresholdLabels": false,
"showThresholdMarkers": true
},
"pluginVersion": "7.0.5",
"targets": [
{
"expr": "count (kube_node_labels{label_node_pool=~\"worker-base|worker-base-d|worker-sleeper|worker-tools|worker-jobs|worker-apps\"})",
"instant": true,
"refId": "A"
}
],
"timeFrom": null,
"timeShift": null,
"title": "Running Nodes",
"type": "gauge"
},
{
"columns": [],
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fontSize": "100%",
"gridPos": {
"h": 6,
"w": 4,
"x": 20,
"y": 8
},
"id": 9,
"pageSize": null,
"pluginVersion": "6.4.4",
"showHeader": true,
"sort": {
"col": 0,
"desc": true
},
"styles": [
{
"alias": "",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"mappingType": 1,
"pattern": "Time",
"thresholds": [],
"type": "hidden",
"unit": "short"
},
{
"alias": "node-pool",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"mappingType": 1,
"pattern": "label_node_pool",
"thresholds": [],
"type": "string",
"unit": "short"
},
{
"alias": "count",
"align": "auto",
"colorMode": null,
"colors": [
"rgba(245, 54, 54, 0.9)",
"rgba(237, 129, 40, 0.89)",
"rgba(50, 172, 45, 0.97)"
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"mappingType": 1,
"pattern": "Value",
"thresholds": [],
"type": "number",
"unit": "short"
}
],
"targets": [
{
"expr": "sort (count by (label_node_pool)(kube_node_labels{label_node_pool=~\"worker-base.*|worker-sleeper|worker-tools|worker-jobs|worker-apps\"}))",
"format": "table",
"instant": true,
"legendFormat": "{{label_node_pool}}",
"refId": "A"
}
],
"timeFrom": null,
"timeShift": null,
"title": "Node Pools",
"transform": "table",
"type": "table-old"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 14
},
"hiddenSeries": false,
"id": 2,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "count(kube_pod_info{pod=~\"protheus-appserver-.*\"})",
"instant": false,
"legendFormat": "Online Users",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Total Online Protheus Appserver Users",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": null,
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 10,
"x": 14,
"y": 14
},
"hiddenSeries": false,
"id": 19,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 2,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum (kube_node_labels{label_node_pool=~\"worker-base|worker-base-d|worker-sleeper|worker-tools|worker-jobs|worker-apps\"}) by (label_node_pool)",
"instant": false,
"legendFormat": "{{label_node_pool}}",
"refId": "A"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Running Nodes",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
}
],
"refresh": "5s",
"schemaVersion": 25,
"style": "dark",
"tags": [],
"templating": {
"list": []
},
"time": {
"from": "now-3h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
]
},
"timezone": "",
"title": "Online Users",
"uid": "ODts8PbWz",
"version": 15
} |
Desta forma, as informações deste dash serãoexibidos com os novos dados do cluster.