mirror of
https://github.com/ryan4yin/nix-config.git
synced 2026-05-25 00:50:01 +02:00
feat: Grafana Dashboards & VMAlert (#224)
* chore: grafana - remove useless dashboards * fix: alertmanager - metrics * fix: victoria-metrics - job filter * feat: add recoding rules * fix: grafana - add or update uid for all dashboards * fix: vmalert - remoteWrite
This commit is contained in:
Ryan Yin
@@ -73,11 +73,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": true,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"#7eb26d",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "#7eb26d", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
@@ -156,11 +152,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"description": "start time of the process",
|
||||
"format": "dateTimeFromNow",
|
||||
@@ -239,11 +231,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"rgba(245, 54, 54, 0.9)",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"rgba(50, 172, 45, 0.97)"
|
||||
],
|
||||
"colors": ["rgba(245, 54, 54, 0.9)", "rgba(237, 129, 40, 0.89)", "rgba(50, 172, 45, 0.97)"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "decbytes",
|
||||
"gauge": {
|
||||
@@ -322,11 +310,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"rgba(245, 54, 54, 0.9)",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"rgba(50, 172, 45, 0.97)"
|
||||
],
|
||||
"colors": ["rgba(245, 54, 54, 0.9)", "rgba(237, 129, 40, 0.89)", "rgba(50, 172, 45, 0.97)"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "decbytes",
|
||||
"gauge": {
|
||||
@@ -405,11 +389,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"rgba(245, 54, 54, 0.9)",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"rgba(50, 172, 45, 0.97)"
|
||||
],
|
||||
"colors": ["rgba(245, 54, 54, 0.9)", "rgba(237, 129, 40, 0.89)", "rgba(50, 172, 45, 0.97)"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "decbytes",
|
||||
"gauge": {
|
||||
@@ -488,11 +468,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
@@ -864,11 +840,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "bytes",
|
||||
"gauge": {
|
||||
@@ -945,11 +917,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "bytes",
|
||||
"gauge": {
|
||||
@@ -1026,11 +994,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "bytes",
|
||||
"gauge": {
|
||||
@@ -1107,11 +1071,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "bytes",
|
||||
"gauge": {
|
||||
@@ -1189,11 +1149,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"decimals": 1,
|
||||
"format": "bytes",
|
||||
@@ -1271,11 +1227,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
@@ -1352,11 +1304,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
@@ -1433,11 +1381,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
@@ -1514,11 +1458,7 @@
|
||||
"cacheTimeout": null,
|
||||
"colorBackground": false,
|
||||
"colorValue": false,
|
||||
"colors": [
|
||||
"#299c46",
|
||||
"rgba(237, 129, 40, 0.89)",
|
||||
"#d44a3a"
|
||||
],
|
||||
"colors": ["#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a"],
|
||||
"datasource": "${DS_PROMETHEUS}",
|
||||
"format": "none",
|
||||
"gauge": {
|
||||
@@ -2944,11 +2884,7 @@
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 19,
|
||||
"style": "dark",
|
||||
"tags": [
|
||||
"postgres",
|
||||
"db",
|
||||
"stats"
|
||||
],
|
||||
"tags": ["postgres", "db", "stats"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
@@ -3136,32 +3072,11 @@
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"5s",
|
||||
"10s",
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
"refresh_intervals": ["5s", "10s", "30s", "1m", "5m", "15m", "30m", "1h", "2h", "1d"],
|
||||
"time_options": ["5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d"]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "PostgreSQL Database",
|
||||
"uid": "000000039",
|
||||
"uid": "postgresql-database",
|
||||
"version": 1
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11139,6 +11139,6 @@
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Alertmanager",
|
||||
"uid": "eea-9_sik",
|
||||
"uid": "alertmanager",
|
||||
"version": 27
|
||||
}
|
||||
|
||||
+1
-1
@@ -23262,7 +23262,7 @@
|
||||
},
|
||||
"timezone": "browser",
|
||||
"title": "Node Exporter Full",
|
||||
"uid": "rYdddlPWk",
|
||||
"uid": "node-exporter-full",
|
||||
"version": 87,
|
||||
"weekStart": ""
|
||||
}
|
||||
|
||||
@@ -853,19 +853,11 @@
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
]
|
||||
"refresh_intervals": ["30s", "1m", "5m", "15m", "30m", "1h", "2h", "1d"]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Istio Wasm Extension Dashboard",
|
||||
"uid": "istio-wasm-extension",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
|
||||
@@ -114,9 +114,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -196,9 +194,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -275,9 +271,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -354,9 +348,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -433,9 +425,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -511,9 +501,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -589,9 +577,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -667,9 +653,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -745,9 +729,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -823,9 +805,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -901,9 +881,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -979,9 +957,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -1329,9 +1305,7 @@
|
||||
"footer": {
|
||||
"countRows": false,
|
||||
"fields": "",
|
||||
"reducer": [
|
||||
"sum"
|
||||
],
|
||||
"reducer": ["sum"],
|
||||
"show": false
|
||||
},
|
||||
"showHeader": true
|
||||
@@ -1466,9 +1440,7 @@
|
||||
"cellHeight": "sm",
|
||||
"footer": {
|
||||
"show": false,
|
||||
"reducer": [
|
||||
"sum"
|
||||
],
|
||||
"reducer": ["sum"],
|
||||
"countRows": false,
|
||||
"fields": ""
|
||||
}
|
||||
@@ -1832,30 +1804,12 @@
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
"refresh_intervals": ["30s", "1m", "5m", "15m", "30m", "1h", "2h", "1d"],
|
||||
"time_options": ["5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d"]
|
||||
},
|
||||
"timezone": "browser",
|
||||
"title": "Istio Mesh Dashboard",
|
||||
"uid": "istio-mesh",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1574,30 +1574,12 @@
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
"refresh_intervals": ["30s", "1m", "5m", "15m", "30m", "1h", "2h", "1d"],
|
||||
"time_options": ["5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d"]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Istio Performance Dashboard",
|
||||
"uid": "istio-performance",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
|
||||
@@ -123,9 +123,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -197,9 +195,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -398,9 +394,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -478,9 +472,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -552,9 +544,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -753,9 +743,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -3368,28 +3356,12 @@
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
"refresh_intervals": ["5m", "15m", "30m", "1h", "2h", "1d"],
|
||||
"time_options": ["5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d"]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Istio Service Dashboard",
|
||||
"uid": "istio-service",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
|
||||
@@ -123,9 +123,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"lastNotNull"
|
||||
],
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -206,9 +204,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -405,9 +401,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -485,9 +479,7 @@
|
||||
"justifyMode": "auto",
|
||||
"orientation": "horizontal",
|
||||
"reduceOptions": {
|
||||
"calcs": [
|
||||
"mean"
|
||||
],
|
||||
"calcs": ["mean"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
@@ -3040,28 +3032,12 @@
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
"refresh_intervals": ["5m", "15m", "30m", "1h", "2h", "1d"],
|
||||
"time_options": ["5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d"]
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "Istio Workload Dashboard",
|
||||
"uid": "istio-workload",
|
||||
"version": 1,
|
||||
"weekStart": ""
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,458 +1,434 @@
|
||||
{
|
||||
"graphTooltip": 1,
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"panels": [ ],
|
||||
"title": "Process",
|
||||
"type": "row"
|
||||
"graphTooltip": 1,
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Version number of each running instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 0,
|
||||
"y": 1
|
||||
},
|
||||
"id": 2,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum(istio_build{component=\"ztunnel\"}) by (tag)",
|
||||
"legendFormat": "Version ({{tag}})"
|
||||
}
|
||||
],
|
||||
"title": "Ztunnel Versions",
|
||||
"type": "timeseries"
|
||||
"id": 1,
|
||||
"panels": [],
|
||||
"title": "Process",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Memory usage of each running instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "bytes"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 8,
|
||||
"y": 1
|
||||
},
|
||||
"id": 3,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n container_memory_working_set_bytes{container=\"istio-proxy\", pod=~\"ztunnel-.*\"}\n)",
|
||||
"legendFormat": "Container ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage",
|
||||
"type": "timeseries"
|
||||
"description": "Version number of each running instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "CPU usage of each running instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 16,
|
||||
"y": 1
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n irate(\n container_cpu_usage_seconds_total{container=\"istio-proxy\", pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Container ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "CPU Usage",
|
||||
"type": "timeseries"
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 0,
|
||||
"y": 1
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 9
|
||||
},
|
||||
"id": 5,
|
||||
"panels": [ ],
|
||||
"title": "Network",
|
||||
"type": "row"
|
||||
"id": 2,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Connections opened and closed per instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "cps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 0,
|
||||
"y": 10
|
||||
},
|
||||
"id": 6,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_tcp_connections_opened_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Opened ({{pod}})"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "-sum by (pod) (\n rate(\n istio_tcp_connections_closed_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Closed ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Connections",
|
||||
"type": "timeseries"
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum(istio_build{component=\"ztunnel\"}) by (tag)",
|
||||
"legendFormat": "Version ({{tag}})"
|
||||
}
|
||||
],
|
||||
"title": "Ztunnel Versions",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Bytes sent and received per instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "Bps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 8,
|
||||
"y": 10
|
||||
},
|
||||
"id": 7,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_tcp_sent_bytes_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Sent ({{pod}})"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_tcp_received_bytes_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Received ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Bytes Transmitted",
|
||||
"type": "timeseries"
|
||||
"description": "Memory usage of each running instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "bytes"
|
||||
}
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "DNS queries received per instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "qps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 16,
|
||||
"y": 10
|
||||
},
|
||||
"id": 8,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_dns_requests_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Request ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "DNS Request",
|
||||
"type": "timeseries"
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 8,
|
||||
"y": 1
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 18
|
||||
},
|
||||
"id": 9,
|
||||
"panels": [ ],
|
||||
"title": "Operations",
|
||||
"type": "row"
|
||||
"id": 3,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Count of XDS connection terminations.\nThis will typically spike every 30min for each instance.\n",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 19
|
||||
},
|
||||
"id": 10,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_xds_connection_terminations_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "XDS Connection Terminations ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "XDS",
|
||||
"type": "timeseries"
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n container_memory_working_set_bytes{container=\"istio-proxy\", pod=~\"ztunnel-.*\"}\n)",
|
||||
"legendFormat": "Container ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Memory Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "CPU usage of each running instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 16,
|
||||
"y": 1
|
||||
},
|
||||
"id": 4,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n irate(\n container_cpu_usage_seconds_total{container=\"istio-proxy\", pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Container ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "CPU Usage",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 9
|
||||
},
|
||||
"id": 5,
|
||||
"panels": [],
|
||||
"title": "Network",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Connections opened and closed per instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "cps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 0,
|
||||
"y": 10
|
||||
},
|
||||
"id": 6,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_tcp_connections_opened_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Opened ({{pod}})"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "-sum by (pod) (\n rate(\n istio_tcp_connections_closed_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Closed ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Connections",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Bytes sent and received per instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "Bps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 8,
|
||||
"y": 10
|
||||
},
|
||||
"id": 7,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_tcp_sent_bytes_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Sent ({{pod}})"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_tcp_received_bytes_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Received ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Bytes Transmitted",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "DNS queries received per instance",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
},
|
||||
"unit": "qps"
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 16,
|
||||
"y": 10
|
||||
},
|
||||
"id": 8,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_dns_requests_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "Request ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "DNS Request",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 18
|
||||
},
|
||||
"id": 9,
|
||||
"panels": [],
|
||||
"title": "Operations",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Count of XDS connection terminations.\nThis will typically spike every 30min for each instance.\n",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 19
|
||||
},
|
||||
"id": 10,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (\n rate(\n istio_xds_connection_terminations_total{pod=~\"ztunnel-.*\"}\n [$__rate_interval])\n)",
|
||||
"legendFormat": "XDS Connection Terminations ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "XDS",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Count of active and pending proxies managed by each instance.\nPending is expected to converge to zero.\n",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 19
|
||||
},
|
||||
"id": 11,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["last", "max"],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (workload_manager_active_proxy_count{pod=~\"ztunnel-.*\"})",
|
||||
"legendFormat": "Active Proxies ({{pod}})"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (workload_manager_pending_proxy_count{pod=~\"ztunnel-.*\"})",
|
||||
"legendFormat": "Pending Proxies ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Workload Manager",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"refresh": "15s",
|
||||
"schemaVersion": 39,
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"description": "Count of active and pending proxies managed by each instance.\nPending is expected to converge to zero.\n",
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "hue",
|
||||
"showPoints": "never"
|
||||
}
|
||||
}
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 19
|
||||
},
|
||||
"id": 11,
|
||||
"interval": "5s",
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": [
|
||||
"last",
|
||||
"max"
|
||||
],
|
||||
"displayMode": "table"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.0.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (workload_manager_active_proxy_count{pod=~\"ztunnel-.*\"})",
|
||||
"legendFormat": "Active Proxies ({{pod}})"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (pod) (workload_manager_pending_proxy_count{pod=~\"ztunnel-.*\"})",
|
||||
"legendFormat": "Pending Proxies ({{pod}})"
|
||||
}
|
||||
],
|
||||
"title": "Workload Manager",
|
||||
"type": "timeseries"
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"type": "datasource"
|
||||
}
|
||||
],
|
||||
"refresh": "15s",
|
||||
"schemaVersion": 39,
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"type": "datasource"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-30m",
|
||||
"to": "now"
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Istio Ztunnel Dashboard",
|
||||
"uid": "12c58766acc81a1c835dd5059eaf2741"
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-30m",
|
||||
"to": "now"
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Istio Ztunnel Dashboard",
|
||||
"uid": "istio-ztunnel"
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -4572,11 +4572,7 @@
|
||||
"refresh": "1m",
|
||||
"schemaVersion": 26,
|
||||
"style": "dark",
|
||||
"tags": [
|
||||
"kubevirt",
|
||||
"kubevirt-control-plane",
|
||||
"sig-scale"
|
||||
],
|
||||
"tags": ["kubevirt", "kubevirt-control-plane", "sig-scale"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
@@ -5165,32 +5161,11 @@
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {
|
||||
"refresh_intervals": [
|
||||
"5s",
|
||||
"10s",
|
||||
"30s",
|
||||
"1m",
|
||||
"5m",
|
||||
"15m",
|
||||
"30m",
|
||||
"1h",
|
||||
"2h",
|
||||
"1d"
|
||||
],
|
||||
"time_options": [
|
||||
"5m",
|
||||
"15m",
|
||||
"1h",
|
||||
"6h",
|
||||
"12h",
|
||||
"24h",
|
||||
"2d",
|
||||
"7d",
|
||||
"30d"
|
||||
]
|
||||
"refresh_intervals": ["5s", "10s", "30s", "1m", "5m", "15m", "30m", "1h", "2h", "1d"],
|
||||
"time_options": ["5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d"]
|
||||
},
|
||||
"timezone": "UTC",
|
||||
"title": "KubeVirt / Control Plane",
|
||||
"uid": "V1Qq_IBM_za0",
|
||||
"uid": "kubevirt-control-plane",
|
||||
"version": 3
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1157,6 +1157,6 @@
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Loki / Chunks",
|
||||
"uid": "chunks",
|
||||
"uid": "loki-chunks",
|
||||
"version": 0
|
||||
}
|
||||
|
||||
@@ -720,6 +720,6 @@
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Loki / Deletion",
|
||||
"uid": "deletion",
|
||||
"uid": "loki-deletion",
|
||||
"version": 0
|
||||
}
|
||||
|
||||
@@ -1032,6 +1032,6 @@
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Loki / Logs",
|
||||
"uid": "logs",
|
||||
"uid": "loki-logs",
|
||||
"version": 0
|
||||
}
|
||||
|
||||
@@ -6701,6 +6701,6 @@
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Loki / Operational",
|
||||
"uid": "operational",
|
||||
"uid": "loki-operational",
|
||||
"version": 0
|
||||
}
|
||||
|
||||
@@ -1464,6 +1464,6 @@
|
||||
},
|
||||
"timezone": "utc",
|
||||
"title": "Loki / Retention",
|
||||
"uid": "retention",
|
||||
"uid": "loki-retention",
|
||||
"version": 0
|
||||
}
|
||||
|
||||
+3
-3
@@ -6469,12 +6469,12 @@
|
||||
"type": "prometheus",
|
||||
"uid": "$ds"
|
||||
},
|
||||
"definition": "label_values(vm_app_version{version=~\"victoria-metrics-.*\"}, job)",
|
||||
"definition": "label_values(vm_app_version{}, job)",
|
||||
"includeAll": false,
|
||||
"name": "job",
|
||||
"options": [],
|
||||
"query": {
|
||||
"query": "label_values(vm_app_version{version=~\"victoria-metrics-.*\"}, job)",
|
||||
"query": "label_values(vm_app_version{}, job)",
|
||||
"refId": "VictoriaMetrics-job-Variable-Query"
|
||||
},
|
||||
"refresh": 1,
|
||||
@@ -6542,7 +6542,7 @@
|
||||
},
|
||||
"timezone": "",
|
||||
"title": "VictoriaMetrics - single-node",
|
||||
"uid": "wNf0q_kZk",
|
||||
"uid": "victoriametrics-single-node",
|
||||
"version": 1,
|
||||
"weekStart": "",
|
||||
"gnetId": 10229
|
||||
|
||||
@@ -1,6 +1,8 @@
|
||||
# Monitoring & Alerting
|
||||
|
||||
## Alert Rules
|
||||
## Alert Rules & Recoding Rules
|
||||
|
||||
- [awesome-prometheus-alerts](https://github.com/samber/awesome-prometheus-alerts): Collection of
|
||||
Prometheus alerting rules
|
||||
- [awesome-prometheus-alerts](https://github.com/samber/awesome-prometheus-alerts)
|
||||
- Collection of Prometheus alerting rules.
|
||||
- [victoria-metrics-k8s-stack/files/rules](https://github.com/VictoriaMetrics/helm-charts/tree/master/charts/victoria-metrics-k8s-stack/files/rules/generated)
|
||||
- Alert Rules & Recoding Rules used by kube-prometheus-stack.
|
||||
|
||||
@@ -1,12 +1,16 @@
|
||||
{ config, lib, ... }:
|
||||
{ config, ... }:
|
||||
{
|
||||
services.vmalert = {
|
||||
# https://docs.victoriametrics.com/victoriametrics/vmalert/
|
||||
services.vmalert.instances."homelab" = {
|
||||
enable = true;
|
||||
settings = {
|
||||
"httpListenAddr" = "127.0.0.1:8880";
|
||||
|
||||
"datasource.url" = "http://localhost:9090";
|
||||
"notifier.url" = [ "http://localhost:9093" ]; # alertmanager's api
|
||||
# Recording rules results are persisted via remote write.
|
||||
"remoteWrite.url" = "http://localhost:9090";
|
||||
"remoteRead.url" = "http://localhost:9090";
|
||||
|
||||
# Whether to disable long-lived connections to the datasource.
|
||||
"datasource.disableKeepAlive" = true;
|
||||
@@ -16,6 +20,7 @@
|
||||
# Path to the files with alerting and/or recording rules.
|
||||
rule = [
|
||||
"${./alert_rules}/*.yml"
|
||||
"${./recoding_rules}/*.yml"
|
||||
];
|
||||
# https://docs.victoriametrics.com/victoriametrics/vmalert/#link-to-alert-source
|
||||
# Set this two args to generate the correct `.GeneratorURL`
|
||||
|
||||
@@ -0,0 +1,8 @@
|
||||
# Alert Rules
|
||||
|
||||
Alert rules are configurations that define conditions, scope, and actions for generating alerts from
|
||||
monitored signals, such as metrics, logs, or activity. When an alert rule's defined conditions are
|
||||
met for a specific resource within its scope, the system generates a triggered alert, which is the
|
||||
actual instance of the condition being met. These rules specify the data to monitor, the trigger
|
||||
threshold, and the resulting actions, like sending notifications to specific receivers or performing
|
||||
automated tasks.
|
||||
@@ -0,0 +1,57 @@
|
||||
groups:
|
||||
- name: general.rules
|
||||
rules:
|
||||
- alert: TargetDown
|
||||
annotations:
|
||||
description:
|
||||
'{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in
|
||||
{{ $labels.namespace }} namespace are down.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown
|
||||
summary: One or more targets are unreachable.
|
||||
expr:
|
||||
100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up) BY (cluster, job,
|
||||
namespace, service)) > 10
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: Watchdog
|
||||
annotations:
|
||||
description: 'This is an alert meant to ensure that the entire alerting pipeline is
|
||||
functional.
|
||||
|
||||
This alert is always firing, therefore it should always be firing in Alertmanager
|
||||
|
||||
and always fire against a receiver. There are integrations with various notification
|
||||
|
||||
mechanisms that send a notification when this alert is not firing. For example the
|
||||
|
||||
"DeadMansSnitch" integration in PagerDuty.'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog
|
||||
summary:
|
||||
An alert that should always be firing to certify that Alertmanager is working properly.
|
||||
expr: vector(1)
|
||||
labels:
|
||||
severity: none
|
||||
- alert: InfoInhibitor
|
||||
annotations:
|
||||
description: 'This is an alert that is used to inhibit info alerts.
|
||||
|
||||
By themselves, the info-level alerts are sometimes very noisy, but they are relevant
|
||||
when combined with
|
||||
|
||||
other alerts.
|
||||
|
||||
This alert fires whenever there''s a severity="info" alert, and stops firing when
|
||||
another alert with a
|
||||
|
||||
severity of ''warning'' or ''critical'' starts firing on the same namespace.
|
||||
|
||||
This alert should be routed to a null receiver and configured to inhibit alerts with
|
||||
severity="info".'
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor
|
||||
summary: Info-level alert inhibition.
|
||||
expr:
|
||||
ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname != "InfoInhibitor",
|
||||
severity =~ "warning|critical", alertstate="firing"} == 1
|
||||
labels:
|
||||
severity: none
|
||||
@@ -0,0 +1,120 @@
|
||||
groups:
|
||||
- name: kubernetes-resources
|
||||
rules:
|
||||
- alert: KubeCPUOvercommit
|
||||
annotations:
|
||||
description:
|
||||
Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{
|
||||
$value }} CPU shares and cannot tolerate node failure.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
|
||||
summary: Cluster has overcommitted CPU resource requests.
|
||||
expr: |-
|
||||
sum(namespace_cpu:kube_pod_container_resource_requests:sum{job="kube-state-metrics",}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
|
||||
and
|
||||
(sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeMemoryOvercommit
|
||||
annotations:
|
||||
description:
|
||||
Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Pods by {{
|
||||
$value | humanize }} bytes and cannot tolerate node failure.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
|
||||
summary: Cluster has overcommitted memory resource requests.
|
||||
expr: |-
|
||||
sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
|
||||
and
|
||||
(sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
|
||||
for: 10m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeCPUQuotaOvercommit
|
||||
annotations:
|
||||
description:
|
||||
Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Namespaces.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
|
||||
summary: Cluster has overcommitted CPU resource requests.
|
||||
expr: |-
|
||||
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) by (cluster)
|
||||
/
|
||||
sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) by (cluster)
|
||||
> 1.5
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeMemoryQuotaOvercommit
|
||||
annotations:
|
||||
description:
|
||||
Cluster {{ $labels.cluster }} has overcommitted memory resource requests for
|
||||
Namespaces.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
|
||||
summary: Cluster has overcommitted memory resource requests.
|
||||
expr: |-
|
||||
sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster)
|
||||
/
|
||||
sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)
|
||||
> 1.5
|
||||
for: 5m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: KubeQuotaAlmostFull
|
||||
annotations:
|
||||
description:
|
||||
Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{
|
||||
$labels.resource }} quota.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
|
||||
summary: Namespace quota is going to be full.
|
||||
expr: |-
|
||||
kube_resourcequota{job="kube-state-metrics", type="used"}
|
||||
/ ignoring(instance, job, type)
|
||||
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
||||
> 0.9 < 1
|
||||
for: 15m
|
||||
labels:
|
||||
severity: info
|
||||
- alert: KubeQuotaFullyUsed
|
||||
annotations:
|
||||
description:
|
||||
Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{
|
||||
$labels.resource }} quota.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
|
||||
summary: Namespace quota is fully used.
|
||||
expr: |-
|
||||
kube_resourcequota{job="kube-state-metrics", type="used"}
|
||||
/ ignoring(instance, job, type)
|
||||
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
||||
== 1
|
||||
for: 15m
|
||||
labels:
|
||||
severity: info
|
||||
- alert: KubeQuotaExceeded
|
||||
annotations:
|
||||
description:
|
||||
Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{
|
||||
$labels.resource }} quota.
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
|
||||
summary: Namespace quota has exceeded the limits.
|
||||
expr: |-
|
||||
kube_resourcequota{job="kube-state-metrics", type="used"}
|
||||
/ ignoring(instance, job, type)
|
||||
(kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
|
||||
> 1
|
||||
for: 15m
|
||||
labels:
|
||||
severity: warning
|
||||
- alert: CPUThrottlingHigh
|
||||
annotations:
|
||||
description:
|
||||
"{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace
|
||||
}} for container {{ $labels.container }} in pod {{ $labels.pod }}."
|
||||
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
|
||||
summary: Processes experience elevated CPU throttling.
|
||||
expr: |-
|
||||
sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (cluster, container, pod, namespace)
|
||||
/
|
||||
sum(increase(container_cpu_cfs_periods_total{}[5m])) by (cluster, container, pod, namespace)
|
||||
> ( 25 / 100 )
|
||||
for: 15m
|
||||
labels:
|
||||
severity: info
|
||||
@@ -0,0 +1,7 @@
|
||||
# Recording Rules
|
||||
|
||||
Recording rules are pre-defined queries, often complex or computationally expensive, that are
|
||||
evaluated periodically to create new, pre-computed time series metrics.
|
||||
|
||||
These rules store the results in a metric backend, significantly speeding up queries for dashboards
|
||||
and other alerts, and reducing system load by avoiding the re-computation of data.
|
||||
@@ -0,0 +1,149 @@
|
||||
groups:
|
||||
- name: k8s.rules
|
||||
rules:
|
||||
- expr: |-
|
||||
sum by (cluster, namespace, pod, container) (
|
||||
irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m])
|
||||
) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
|
||||
1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
||||
)
|
||||
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
|
||||
- expr: |-
|
||||
container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
||||
* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
|
||||
max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
||||
)
|
||||
record: node_namespace_pod_container:container_memory_working_set_bytes
|
||||
- expr: |-
|
||||
container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
||||
* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
|
||||
max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
||||
)
|
||||
record: node_namespace_pod_container:container_memory_rss
|
||||
- expr: |-
|
||||
container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
||||
* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
|
||||
max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
||||
)
|
||||
record: node_namespace_pod_container:container_memory_cache
|
||||
- expr: |-
|
||||
container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}
|
||||
* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,
|
||||
max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
|
||||
)
|
||||
record: node_namespace_pod_container:container_memory_swap
|
||||
- expr: |-
|
||||
kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
||||
group_left() max by (namespace, pod, cluster) (
|
||||
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
||||
)
|
||||
record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
|
||||
- expr: |-
|
||||
sum by (namespace, cluster) (
|
||||
sum by (namespace, pod, cluster) (
|
||||
max by (namespace, pod, container, cluster) (
|
||||
kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"}
|
||||
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
||||
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
||||
)
|
||||
)
|
||||
)
|
||||
record: namespace_memory:kube_pod_container_resource_requests:sum
|
||||
- expr: |-
|
||||
kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
||||
group_left() max by (namespace, pod, cluster) (
|
||||
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
||||
)
|
||||
record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
|
||||
- expr: |-
|
||||
sum by (namespace, cluster) (
|
||||
sum by (namespace, pod, cluster) (
|
||||
max by (namespace, pod, container, cluster) (
|
||||
kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"}
|
||||
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
||||
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
||||
)
|
||||
)
|
||||
)
|
||||
record: namespace_cpu:kube_pod_container_resource_requests:sum
|
||||
- expr: |-
|
||||
kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
||||
group_left() max by (namespace, pod, cluster) (
|
||||
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
||||
)
|
||||
record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits
|
||||
- expr: |-
|
||||
sum by (namespace, cluster) (
|
||||
sum by (namespace, pod, cluster) (
|
||||
max by (namespace, pod, container, cluster) (
|
||||
kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"}
|
||||
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
||||
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
||||
)
|
||||
)
|
||||
)
|
||||
record: namespace_memory:kube_pod_container_resource_limits:sum
|
||||
- expr: |-
|
||||
kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster)
|
||||
group_left() max by (namespace, pod, cluster) (
|
||||
(kube_pod_status_phase{phase=~"Pending|Running"} == 1)
|
||||
)
|
||||
record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
|
||||
- expr: |-
|
||||
sum by (namespace, cluster) (
|
||||
sum by (namespace, pod, cluster) (
|
||||
max by (namespace, pod, container, cluster) (
|
||||
kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"}
|
||||
) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (
|
||||
kube_pod_status_phase{phase=~"Pending|Running"} == 1
|
||||
)
|
||||
)
|
||||
)
|
||||
record: namespace_cpu:kube_pod_container_resource_limits:sum
|
||||
- expr: |-
|
||||
max by (cluster, namespace, workload, pod) (
|
||||
label_replace(
|
||||
label_replace(
|
||||
kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"},
|
||||
"replicaset", "$1", "owner_name", "(.*)"
|
||||
) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (
|
||||
1, max by (replicaset, namespace, owner_name) (
|
||||
kube_replicaset_owner{job="kube-state-metrics"}
|
||||
)
|
||||
),
|
||||
"workload", "$1", "owner_name", "(.*)"
|
||||
)
|
||||
)
|
||||
labels:
|
||||
workload_type: deployment
|
||||
record: namespace_workload_pod:kube_pod_owner:relabel
|
||||
- expr: |-
|
||||
max by (cluster, namespace, workload, pod) (
|
||||
label_replace(
|
||||
kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"},
|
||||
"workload", "$1", "owner_name", "(.*)"
|
||||
)
|
||||
)
|
||||
labels:
|
||||
workload_type: daemonset
|
||||
record: namespace_workload_pod:kube_pod_owner:relabel
|
||||
- expr: |-
|
||||
max by (cluster, namespace, workload, pod) (
|
||||
label_replace(
|
||||
kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"},
|
||||
"workload", "$1", "owner_name", "(.*)"
|
||||
)
|
||||
)
|
||||
labels:
|
||||
workload_type: statefulset
|
||||
record: namespace_workload_pod:kube_pod_owner:relabel
|
||||
- expr: |-
|
||||
max by (cluster, namespace, workload, pod) (
|
||||
label_replace(
|
||||
kube_pod_owner{job="kube-state-metrics", owner_kind="Job"},
|
||||
"workload", "$1", "owner_name", "(.*)"
|
||||
)
|
||||
)
|
||||
labels:
|
||||
workload_type: job
|
||||
record: namespace_workload_pod:kube_pod_owner:relabel
|
||||
@@ -0,0 +1,128 @@
|
||||
groups:
|
||||
- name: kube-prometheus-node-recording.rules
|
||||
rules:
|
||||
- expr:
|
||||
sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY
|
||||
(instance)
|
||||
record: instance:node_cpu:rate:sum
|
||||
- expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance)
|
||||
record: instance:node_network_receive_bytes:rate:sum
|
||||
- expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance)
|
||||
record: instance:node_network_transmit_bytes:rate:sum
|
||||
- expr:
|
||||
sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT
|
||||
(cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance,
|
||||
cpu)) BY (instance)
|
||||
record: instance:node_cpu:ratio
|
||||
- expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m]))
|
||||
record: cluster:node_cpu:sum_rate5m
|
||||
- expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu))
|
||||
record: cluster:node_cpu:ratio
|
||||
|
||||
- name: node-exporter.rules
|
||||
rules:
|
||||
- expr: |-
|
||||
count without (cpu, mode) (
|
||||
node_cpu_seconds_total{job="node-exporter",mode="idle"}
|
||||
)
|
||||
record: instance:node_num_cpu:sum
|
||||
- expr: |-
|
||||
1 - avg without (cpu) (
|
||||
sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m]))
|
||||
)
|
||||
record: instance:node_cpu_utilisation:rate5m
|
||||
- expr: |-
|
||||
(
|
||||
node_load1{job="node-exporter"}
|
||||
/
|
||||
instance:node_num_cpu:sum{job="node-exporter"}
|
||||
)
|
||||
record: instance:node_load1_per_cpu:ratio
|
||||
- expr: |-
|
||||
1 - (
|
||||
(
|
||||
node_memory_MemAvailable_bytes{job="node-exporter"}
|
||||
or
|
||||
(
|
||||
node_memory_Buffers_bytes{job="node-exporter"}
|
||||
+
|
||||
node_memory_Cached_bytes{job="node-exporter"}
|
||||
+
|
||||
node_memory_MemFree_bytes{job="node-exporter"}
|
||||
+
|
||||
node_memory_Slab_bytes{job="node-exporter"}
|
||||
)
|
||||
)
|
||||
/
|
||||
node_memory_MemTotal_bytes{job="node-exporter"}
|
||||
)
|
||||
record: instance:node_memory_utilisation:ratio
|
||||
- expr: rate(node_vmstat_pgmajfault{job="node-exporter"}[5m])
|
||||
record: instance:node_vmstat_pgmajfault:rate5m
|
||||
- expr:
|
||||
rate(node_disk_io_time_seconds_total{job="node-exporter",
|
||||
device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
||||
record: instance_device:node_disk_io_time_seconds:rate5m
|
||||
- expr:
|
||||
rate(node_disk_io_time_weighted_seconds_total{job="node-exporter",
|
||||
device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m])
|
||||
record: instance_device:node_disk_io_time_weighted_seconds:rate5m
|
||||
- expr: |-
|
||||
sum without (device) (
|
||||
rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m])
|
||||
)
|
||||
record: instance:node_network_receive_bytes_excluding_lo:rate5m
|
||||
- expr: |-
|
||||
sum without (device) (
|
||||
rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m])
|
||||
)
|
||||
record: instance:node_network_transmit_bytes_excluding_lo:rate5m
|
||||
- expr: |-
|
||||
sum without (device) (
|
||||
rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m])
|
||||
)
|
||||
record: instance:node_network_receive_drop_excluding_lo:rate5m
|
||||
- expr: |-
|
||||
sum without (device) (
|
||||
rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m])
|
||||
)
|
||||
record: instance:node_network_transmit_drop_excluding_lo:rate5m
|
||||
|
||||
- name: node.rules
|
||||
rules:
|
||||
- expr: |-
|
||||
topk by(cluster, namespace, pod) (1,
|
||||
max by (cluster, node, namespace, pod) (
|
||||
label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
|
||||
))
|
||||
record: "node_namespace_pod:kube_pod_info:"
|
||||
- expr: |-
|
||||
count by (cluster, node) (
|
||||
node_cpu_seconds_total{mode="idle",job="node-exporter"}
|
||||
* on (namespace, pod) group_left(node)
|
||||
topk by(namespace, pod) (1, node_namespace_pod:kube_pod_info:)
|
||||
)
|
||||
record: node:node_num_cpu:sum
|
||||
- expr: |-
|
||||
sum(
|
||||
node_memory_MemAvailable_bytes{job="node-exporter"} or
|
||||
(
|
||||
node_memory_Buffers_bytes{job="node-exporter"} +
|
||||
node_memory_Cached_bytes{job="node-exporter"} +
|
||||
node_memory_MemFree_bytes{job="node-exporter"} +
|
||||
node_memory_Slab_bytes{job="node-exporter"}
|
||||
)
|
||||
) by (cluster)
|
||||
record: :node_memory_MemAvailable_bytes:sum
|
||||
- expr: |-
|
||||
avg by (cluster, node) (
|
||||
sum without (mode) (
|
||||
rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal",job="node-exporter"}[5m])
|
||||
)
|
||||
)
|
||||
record: node:node_cpu_utilization:ratio_rate5m
|
||||
- expr: |-
|
||||
avg by (cluster) (
|
||||
node:node_cpu_utilization:ratio_rate5m
|
||||
)
|
||||
record: cluster:node_cpu:ratio_rate5m
|
||||
@@ -50,6 +50,8 @@
|
||||
labels.type = "app";
|
||||
labels.app = "dnsmasq";
|
||||
labels.host = "suzi";
|
||||
labels.env = "homelab";
|
||||
labels.cluster = "homelab";
|
||||
}
|
||||
];
|
||||
}
|
||||
@@ -64,6 +66,8 @@
|
||||
labels.type = "app";
|
||||
labels.app = "v2ray";
|
||||
labels.host = "aquamarine";
|
||||
labels.env = "homelab";
|
||||
labels.cluster = "homelab";
|
||||
}
|
||||
];
|
||||
}
|
||||
@@ -77,6 +81,8 @@
|
||||
labels.type = "app";
|
||||
labels.app = "postgresql";
|
||||
labels.host = "aquamarine";
|
||||
labels.env = "homelab";
|
||||
labels.cluster = "homelab";
|
||||
}
|
||||
];
|
||||
}
|
||||
@@ -90,6 +96,39 @@
|
||||
labels.type = "app";
|
||||
labels.app = "sftpgo";
|
||||
labels.host = "aquamarine";
|
||||
labels.env = "homelab";
|
||||
labels.cluster = "homelab";
|
||||
}
|
||||
];
|
||||
}
|
||||
{
|
||||
job_name = "alertmanager-embedded-exporter";
|
||||
scrape_interval = "30s";
|
||||
metrics_path = "/metrics";
|
||||
static_configs = [
|
||||
{
|
||||
targets = [ "localhost:9093" ];
|
||||
labels.type = "app";
|
||||
labels.app = "alertmanager";
|
||||
labels.host = "aquamarine";
|
||||
labels.env = "homelab";
|
||||
labels.cluster = "homelab";
|
||||
}
|
||||
];
|
||||
}
|
||||
{
|
||||
job_name = "victoriametrics-embedded-exporter";
|
||||
scrape_interval = "30s";
|
||||
metrics_path = "/metrics";
|
||||
static_configs = [
|
||||
{
|
||||
# scrape vm itself
|
||||
targets = [ "localhost:9090" ];
|
||||
labels.type = "app";
|
||||
labels.app = "victoriametrics";
|
||||
labels.host = "aquamarine";
|
||||
labels.env = "homelab";
|
||||
labels.cluster = "homelab";
|
||||
}
|
||||
];
|
||||
}
|
||||
@@ -109,6 +148,8 @@
|
||||
targets = [ "${addr.ipv4}:9100" ];
|
||||
labels.type = "node";
|
||||
labels.host = hostname;
|
||||
labels.env = "homelab";
|
||||
labels.cluster = "homelab";
|
||||
}
|
||||
];
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user