8ed4b8c9c3
Two more per-service boards, cut from the withdrawn combined services board: the log store (4 panels) and the metrics store (5). The combined board was one page carrying panels for four different services; the seams were already there, so this is a re-cut rather than new authoring. Each board's subject is one service, and the services page that remains will carry only panels whose subject is the *set*. Both were imported by the operator before being committed here, so the queries are known to draw against the live stores rather than only parsing.
277 lines
7.1 KiB
JSON
277 lines
7.1 KiB
JSON
{
|
|
"title": "hyperhive · log store (victorialogs)",
|
|
"uid": "hyperhive-swarm-logstore",
|
|
"description": "VictoriaLogs health for the swarm log store. One of the per-service boards split out of the combined swarm-services page.",
|
|
"editable": true,
|
|
"refresh": "1m",
|
|
"schemaVersion": 39,
|
|
"tags": [
|
|
"hyperhive",
|
|
"swarm",
|
|
"victorialogs",
|
|
"logs"
|
|
],
|
|
"time": {
|
|
"from": "now-24h",
|
|
"to": "now"
|
|
},
|
|
"timezone": "utc",
|
|
"version": 1,
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "timeseries",
|
|
"title": "Log rows ingested (range)",
|
|
"description": "Rows accepted by the log store over the range. ⚠️ This counts what ARRIVED, never what became findable — the pipeline shipped for days with every record carrying a placeholder in place of its message, while this counter climbed normally. A healthy line here is necessary and not sufficient; the check that closes it is a query returning readable lines.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 4
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum(increase(vl_rows_ingested_total[$__range])) or vector(0)",
|
|
"legendFormat": "rows"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"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": 2,
|
|
"type": "timeseries",
|
|
"title": "Log store size on disk",
|
|
"description": "Compressed on-disk size, split by the store's own `type` label (storage vs indexdb). Retention is 30 days, so this is expected to climb to a plateau rather than forever; a straight line past that is the signal.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 12
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "vl_data_size_bytes",
|
|
"legendFormat": "{{type}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes",
|
|
"decimals": 1,
|
|
"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": 3,
|
|
"type": "stat",
|
|
"title": "Log store free disk",
|
|
"description": "Free space on the volume holding the log store. It shares a filesystem with the metrics store, so the two panels move together — a drop here that the metrics one does not show means something outside this swarm is filling the disk.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "vl_free_disk_space_bytes",
|
|
"instant": true,
|
|
"legendFormat": "free"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes",
|
|
"decimals": 1,
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 5000000000
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"graphMode": "none",
|
|
"colorMode": "value",
|
|
"textMode": "value",
|
|
"justifyMode": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "stat",
|
|
"title": "Log store errors",
|
|
"description": "Internal errors plus rejected HTTP requests. Healthy value is zero. ⚠️ A wrong OTLP path answers 400 and lands here, and so does a right path with a bad payload — the status code alone does not separate them, only the store's own log does.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum(vl_errors_total) or vector(0)",
|
|
"instant": true,
|
|
"legendFormat": "internal"
|
|
},
|
|
{
|
|
"refId": "B",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum(vl_http_errors_total) or vector(0)",
|
|
"instant": true,
|
|
"legendFormat": "http"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"mappings": [],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"graphMode": "none",
|
|
"colorMode": "value",
|
|
"textMode": "value",
|
|
"justifyMode": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
},
|
|
"x-zero-is-healthy": true
|
|
}
|
|
]
|
|
}
|