mara/hyperhive
mara/hyperhive
Watch
0
0
Fork
You've already forked hyperhive
 0
Code Activity

host dashboard: pressure stall panels, docs for the new series

Browse source
This commit is contained in:
atlas 2026-11-12 16:07:09 +01:00
commit 5b319e0600
1 changed files with 191 additions and 21 deletions
Download patch file Download diff file Expand all files Collapse all files

168
nix/host-modules/swarm-grafana/dashboards/host.json
View file

@ -998,6 +998,174 @@
"sort": "desc"
}
}
},
{
"id": 17,
"type": "timeseries",
"title": "Pressure stall: some",
"description": "Share of time at least one task waited on CPU, memory or IO, averaged over hosts.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 48
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "avg by (resource) (rate({__name__=\"hyperhive.hive.pressure.stall\", kind=\"some\", hive=~\"$hive\", \"host.name\"=~\"$host\"}[5m])) / 1000000",
"legendFormat": "{{resource}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"color": {
"mode": "palette-classic"
},
"custom": {
"drawStyle": "line",
"lineWidth": 1,
"fillOpacity": 10,
"showPoints": "never",
"spanNulls": false,
"axisSoftMin": 0
}
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true,
"calcs": []
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 18,
"type": "timeseries",
"title": "Pressure stall: full",
"description": "Share of time all non-idle tasks waited on memory or IO at once, averaged over hosts.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 48
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "avg by (resource) (rate({__name__=\"hyperhive.hive.pressure.stall\", kind=\"full\", resource!=\"cpu\", hive=~\"$hive\", \"host.name\"=~\"$host\"}[5m])) / 1000000",
"legendFormat": "{{resource}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"color": {
"mode": "palette-classic"
},
"custom": {
"drawStyle": "line",
"lineWidth": 1,
"fillOpacity": 10,
"showPoints": "never",
"spanNulls": false,
"axisSoftMin": 0
}
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true,
"calcs": []
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 19,
"type": "timeseries",
"title": "Top 10 containers by memory stall",
"description": "Agent containers stalled longest on memory, as a share of time.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 56
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "topk(10, sum by (\"container.name\") (rate({__name__=\"hyperhive.container.memory.pressure.stall\", kind=\"some\", hive=~\"$hive\", \"host.name\"=~\"$host\"}[5m])) / 1000000)",
"legendFormat": "{{container.name}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"color": {
"mode": "palette-classic"
},
"custom": {
"drawStyle": "line",
"lineWidth": 1,
"fillOpacity": 10,
"showPoints": "never",
"spanNulls": false,
"axisSoftMin": 0
}
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true,
"calcs": []
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
}
]
}