mirror of
https://github.com/suitenumerique/docs.git
synced 2026-09-24 02:25:08 +02:00
Manuel Raynaud
d6793f2117
To see what is happening in the cluster we added grafana dashboards using all the metrics introduced previsouly
1102 lines
25 KiB
JSON
1102 lines
25 KiB
JSON
{
|
|
"uid": "docs-loadtest-backend",
|
|
"title": "Docs load test \u2014 backend",
|
|
"description": "The Django backend under load: what it spends on the other services, its database pool, its queue, and what k6 sees from the outside. The generic Django board (17658) has the per-view detail.",
|
|
"tags": [
|
|
"docs",
|
|
"loadtest"
|
|
],
|
|
"schemaVersion": 39,
|
|
"version": 1,
|
|
"editable": true,
|
|
"graphTooltip": 1,
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"refresh": "15s",
|
|
"timezone": "browser",
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "datasource",
|
|
"label": "Prometheus",
|
|
"type": "datasource",
|
|
"query": "prometheus",
|
|
"current": {},
|
|
"hide": 0,
|
|
"refresh": 1
|
|
},
|
|
{
|
|
"name": "hostname",
|
|
"label": "backend replica",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"query": {
|
|
"query": "label_values(django_http_requests_total_by_view_transport_method_total, hostname)",
|
|
"refId": "hostname"
|
|
},
|
|
"definition": "label_values(django_http_requests_total_by_view_transport_method_total, hostname)",
|
|
"refresh": 2,
|
|
"includeAll": true,
|
|
"multi": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"panels": [
|
|
{
|
|
"type": "row",
|
|
"title": "Requests",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"w": 24,
|
|
"h": 1,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"panels": [],
|
|
"id": 1
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Requests by view",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(django_http_requests_total_by_view_transport_method_total{hostname=~\"$hostname\"}[$__rate_interval])) by (view)",
|
|
"legendFormat": "{{view}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps",
|
|
"custom": {
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 2
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Latency p95 by view",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum(rate(django_http_requests_latency_seconds_by_view_method_bucket{hostname=~\"$hostname\"}[$__rate_interval])) by (le, view))",
|
|
"legendFormat": "{{view}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 3
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Responses by status",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(django_http_responses_total_by_status_view_method_total{hostname=~\"$hostname\"}[$__rate_interval])) by (status)",
|
|
"legendFormat": "{{status}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps",
|
|
"custom": {
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 9
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 4
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Errors (5xx) by view",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(django_http_responses_total_by_status_view_method_total{hostname=~\"$hostname\", status=~\"5..\"}[$__rate_interval])) by (view)",
|
|
"legendFormat": "{{view}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 9
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 5
|
|
},
|
|
{
|
|
"type": "row",
|
|
"title": "Calls to the other services",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"w": 24,
|
|
"h": 1,
|
|
"x": 0,
|
|
"y": 17
|
|
},
|
|
"panels": [],
|
|
"id": 6
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Outgoing calls p95",
|
|
"description": "yhub, and the converters. Made inside requests (duplicate, formatted-content, import) and from the Celery tasks.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum(rate(docs_outgoing_request_duration_seconds_bucket{hostname=~\"$hostname\"}[$__rate_interval])) by (le, service, operation))",
|
|
"legendFormat": "{{service}} {{operation}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 18
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 7
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Outgoing calls in flight",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(docs_outgoing_requests_inflight{hostname=~\"$hostname\"}) by (service, operation)",
|
|
"legendFormat": "{{service}} {{operation}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 18
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 8
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Outgoing calls failed",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(docs_outgoing_request_duration_seconds_count{hostname=~\"$hostname\", status=~\"timeout|error|5..\"}[$__rate_interval])) by (service, operation, status)",
|
|
"legendFormat": "{{service}} {{operation}} {{status}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 26
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 9
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Outgoing calls rate",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(docs_outgoing_request_duration_seconds_count{hostname=~\"$hostname\"}[$__rate_interval])) by (service, operation)",
|
|
"legendFormat": "{{service}} {{operation}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 26
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 10
|
|
},
|
|
{
|
|
"type": "row",
|
|
"title": "Database pool (DB_PSYCOPG_POOL_ENABLED)",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"w": 24,
|
|
"h": 1,
|
|
"x": 0,
|
|
"y": 34
|
|
},
|
|
"panels": [],
|
|
"id": 11
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Requests waiting for a connection",
|
|
"description": "The application waiting for connections, before Postgres shows anything. What was missing in the 2026-08-18 and 2026-09-07 outages.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(docs_db_pool_requests_waiting{hostname=~\"$hostname\"}) by (hostname)",
|
|
"legendFormat": "{{hostname}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 35
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 12
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Queued requests and time spent waiting",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(docs_db_pool_requests_queued_total{hostname=~\"$hostname\"}[$__rate_interval]))",
|
|
"legendFormat": "queued/s",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(docs_db_pool_requests_wait_seconds_total{hostname=~\"$hostname\"}[$__rate_interval]))",
|
|
"legendFormat": "wait s/s",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 35
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 13
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Pool size and idle",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(docs_db_pool_size{hostname=~\"$hostname\"})",
|
|
"legendFormat": "size",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(docs_db_pool_available{hostname=~\"$hostname\"})",
|
|
"legendFormat": "idle",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 43
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 14
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Connections opened to Postgres",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(docs_db_pool_connections_total{hostname=~\"$hostname\"}[$__rate_interval]))",
|
|
"legendFormat": "opened/s",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(docs_db_pool_connections_errors_total{hostname=~\"$hostname\"}[$__rate_interval]))",
|
|
"legendFormat": "errors/s",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 43
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 15
|
|
},
|
|
{
|
|
"type": "row",
|
|
"title": "Queries and Celery",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"w": 24,
|
|
"h": 1,
|
|
"x": 0,
|
|
"y": 51
|
|
},
|
|
"panels": [],
|
|
"id": 16
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Query duration p95",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum(rate(django_db_query_duration_seconds_bucket{hostname=~\"$hostname\"}[$__rate_interval])) by (le))",
|
|
"legendFormat": "p95",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 52
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 17
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Queries",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(django_db_execute_total{hostname=~\"$hostname\"}[$__rate_interval]))",
|
|
"legendFormat": "queries/s",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(django_db_errors_total{hostname=~\"$hostname\"}[$__rate_interval]))",
|
|
"legendFormat": "errors/s",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 52
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 18
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Celery queue length",
|
|
"description": "One queue for the whole deployment, reported by every replica: max, not sum. The delete, restore and access cascades land on it.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "max(docs_celery_queue_length) by (queue)",
|
|
"legendFormat": "{{queue}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 60
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 19
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "Uvicorn workers alive",
|
|
"description": "Replicas answering scrapes. The memory and CPU of the pods come from the cluster (cAdvisor), not from the application: prometheus_client exports no process metrics in multiprocess mode.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "count(count(django_http_requests_total_by_view_transport_method_total{hostname=~\"$hostname\"}) by (hostname))",
|
|
"legendFormat": "replicas",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 60
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 20
|
|
},
|
|
{
|
|
"type": "row",
|
|
"title": "k6 \u2014 what the clients see",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"w": 24,
|
|
"h": 1,
|
|
"x": 0,
|
|
"y": 68
|
|
},
|
|
"panels": [],
|
|
"id": 21
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "k6 requests by endpoint",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(k6_http_reqs_total[$__rate_interval])) by (name)",
|
|
"legendFormat": "{{name}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps",
|
|
"custom": {
|
|
"stacking": {
|
|
"mode": "normal"
|
|
}
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 69
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 22
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "k6 latency p99 by endpoint",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "max(k6_http_req_duration_p99{name!=\"\"}) by (name)",
|
|
"legendFormat": "{{name}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 69
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 23
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "k6 failures",
|
|
"description": "",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "max(k6_http_req_failed_rate)",
|
|
"legendFormat": "requests failed",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "1 - max(k6_checks_rate)",
|
|
"legendFormat": "checks failed",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"custom": {},
|
|
"min": 0,
|
|
"max": 1
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 0,
|
|
"y": 77
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 24
|
|
},
|
|
{
|
|
"type": "timeseries",
|
|
"title": "k6 virtual users and dropped iterations",
|
|
"description": "Dropped iterations: the arrival rate asked for could not be served with the VUs allocated, the API was too slow.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "max(k6_vus)",
|
|
"legendFormat": "VUs",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${datasource}"
|
|
},
|
|
"expr": "sum(rate(k6_dropped_iterations_total[$__rate_interval]))",
|
|
"legendFormat": "dropped/s",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"gridPos": {
|
|
"w": 12,
|
|
"h": 8,
|
|
"x": 12,
|
|
"y": 77
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"id": 25
|
|
}
|
|
]
|
|
}
|