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

swarm-stt: metrics and a Grafana board for the speech-to-text service

Browse source
This commit is contained in:
damocles 2026-11-12 09:46:37 +01:00 • committed by mara
commit b180680427
2 changed files with 681 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

1
nix/host-modules/swarm-grafana.nix
View file

@ -289,6 +289,7 @@ let
"notify-router.json"
"queue.json"
"review-classifier.json"
"stt.json"
]
);

441
nix/host-modules/swarm-grafana/dashboards/stt.json Normal file
View file

@ -0,0 +1,441 @@
{
"title": "hyperhive · speech to text",
"uid": "hyperhive-swarm-stt",
"description": "The speech-to-text service: voice memos in, transcripts out, the cache hit rate and the engine's load.",
"tags": ["hyperhive", "swarm", "stt"],
"editable": true,
"refresh": "1m",
"schemaVersion": 39,
"time": {
"from": "now-24h",
"to": "now"
},
"timezone": "utc",
"version": 1,
"panels": [
{
"id": 1,
"type": "stat",
"title": "Requests in range",
"description": "Voice memos the service received in the selected range.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 4,
"w": 6,
"x": 0,
"y": 0
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "sum(increase({__name__=\"hyperhive.stt.requests\"}[$__range])) or vector(0)",
"instant": true,
"legendFormat": "requests in range"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"decimals": 0,
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"graphMode": "none",
"colorMode": "value",
"textMode": "value",
"justifyMode": "auto",
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}
}
},
{
"id": 2,
"type": "stat",
"title": "Served from cache",
"description": "Share of answered requests that needed no engine run.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 4,
"w": 6,
"x": 6,
"y": 0
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "sum(increase({__name__=\"hyperhive.stt.requests\", outcome=\"cached\"}[$__range])) / sum(increase({__name__=\"hyperhive.stt.requests\", outcome=~\"cached|transcribed\"}[$__range]))",
"instant": true,
"legendFormat": "served from cache"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"decimals": 2,
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"graphMode": "none",
"colorMode": "value",
"textMode": "value",
"justifyMode": "auto",
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}
}
},
{
"id": 3,
"type": "stat",
"title": "Failed or turned away",
"description": "Requests that failed in the engine or hit a limit, in the range.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 4,
"w": 6,
"x": 12,
"y": 0
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "sum(increase({__name__=\"hyperhive.stt.requests\", outcome=~\"failed|busy\"}[$__range])) or vector(0)",
"instant": true,
"legendFormat": "failed or turned away"
}
],
"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
}
}
},
{
"id": 4,
"type": "stat",
"title": "Mean time per run",
"description": "Mean time from taking a request to answering it, in the range.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 4,
"w": 6,
"x": 18,
"y": 0
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "sum(increase({__name__=\"hyperhive.stt.run.duration_sum\"}[$__range])) / sum(increase({__name__=\"hyperhive.stt.run.duration_count\"}[$__range]))",
"instant": true,
"legendFormat": "mean time per run"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"decimals": 2,
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
}
]
}
},
"overrides": []
},
"options": {
"graphMode": "none",
"colorMode": "value",
"textMode": "value",
"justifyMode": "auto",
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
}
}
},
{
"id": 5,
"type": "timeseries",
"title": "Requests by outcome",
"description": "Requests per hour, by what the service did with them.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 4
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "sum by (outcome) (increase({__name__=\"hyperhive.stt.requests\"}[1h]))",
"legendFormat": "{{outcome}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"decimals": 0,
"color": {
"mode": "palette-classic"
},
"custom": {
"drawStyle": "line",
"lineWidth": 1,
"fillOpacity": 10,
"showPoints": "never",
"spanNulls": false,
"axisSoftMin": 0,
"stacking": {
"mode": "normal",
"group": "A"
}
}
},
"overrides": []
},
"options": {
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true,
"calcs": []
},
"tooltip": {
"mode": "multi",
"sort": "desc"
}
}
},
{
"id": 6,
"type": "timeseries",
"title": "Time per request",
"description": "Median and 95th percentile seconds from taking a request to answering it.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 4
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "histogram_quantile(0.5, sum by (le) (increase({__name__=\"hyperhive.stt.run.duration_bucket\"}[5m])))",
"legendFormat": "median"
},
{
"refId": "B",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "histogram_quantile(0.95, sum by (le) (increase({__name__=\"hyperhive.stt.run.duration_bucket\"}[5m])))",
"legendFormat": "p95"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"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": 7,
"type": "timeseries",
"title": "Requests held",
"description": "Requests held at once, running or waiting for the engine's one slot. Pinned at the limit means senders are being turned away.",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 12
},
"targets": [
{
"refId": "A",
"datasource": {
"type": "prometheus",
"uid": "@datasourceUid@"
},
"expr": "max({__name__=\"hyperhive.stt.held\"})",
"legendFormat": "held"
}
],
"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"
}
}
}
]
}