Compare commits
15 Commits
2b2dfdfba6
...
master
| Author | SHA1 | Date | |
|---|---|---|---|
| 55517ae8c9 | |||
| 425c0918e4 | |||
| 7127227350 | |||
| 0db6ed576a | |||
| ada34fd601 | |||
| d6b9914c99 | |||
| 9868f5f54a | |||
| 370852bfe9 | |||
| 0472f89a44 | |||
| e1119608ea | |||
| 06df05bcdf | |||
| 3591602479 | |||
| b9a17ca31d | |||
| 88b85b3b2e | |||
| 7fb4145d23 |
@@ -1,3 +1,11 @@
|
||||
{
|
||||
admin :2019
|
||||
|
||||
metrics {
|
||||
per_host
|
||||
}
|
||||
}
|
||||
|
||||
(basic-auth) {
|
||||
basic_auth {
|
||||
admin $2a$14$2zQilpLka2h8Sn1mmOLAAezwDN8Zy8Ta36WECk4qt5MTn3CWksR0m
|
||||
@@ -6,29 +14,33 @@
|
||||
|
||||
adnova.itqdev.xyz {
|
||||
@healthPath path /health /health/*
|
||||
handle @healthPath {
|
||||
import basic-auth
|
||||
reverse_proxy http://backend:8080
|
||||
}
|
||||
handle @healthPath {
|
||||
import basic-auth
|
||||
reverse_proxy http://backend:8080
|
||||
}
|
||||
|
||||
handle_path /static/* {
|
||||
reverse_proxy http://backend-staticfiles:80
|
||||
}
|
||||
handle_path /static/* {
|
||||
reverse_proxy http://backend-staticfiles:80
|
||||
}
|
||||
|
||||
reverse_proxy http://backend:8080
|
||||
}
|
||||
|
||||
:8080 {
|
||||
reverse_proxy http://backend:8080
|
||||
}
|
||||
|
||||
admin.adnova.itqdev.xyz {
|
||||
import basic-auth
|
||||
import basic-auth
|
||||
|
||||
root * /var/www/admin
|
||||
file_server
|
||||
}
|
||||
|
||||
loadtest.adnova.itqdev.xyz {
|
||||
import basic-auth
|
||||
import basic-auth
|
||||
|
||||
reverse_proxy http://loadtest:5001
|
||||
reverse_proxy http://loadtest:5001
|
||||
}
|
||||
|
||||
grafana.adnova.itqdev.xyz {
|
||||
|
||||
@@ -52,7 +52,7 @@
|
||||
name: "Loadtest",
|
||||
link: "https://loadtest.adnova.itqdev.xyz",
|
||||
username: "admin",
|
||||
password: "proooooood",
|
||||
password: "kit2025_observability",
|
||||
description: "Stress test utility with multiple profiles and ability to load mocks."
|
||||
}
|
||||
]
|
||||
|
||||
@@ -48,7 +48,7 @@ domain = localhost
|
||||
enforce_domain = false
|
||||
|
||||
# The full public facing url
|
||||
root_url = %(protocol)s://%(domain)s:%(http_port)s/
|
||||
root_url = https://grafana.adnova.itqdev.xyz
|
||||
|
||||
# Serve Grafana from subpath specified in `root_url` setting. By default it is set to `false` for compatibility reasons.
|
||||
serve_from_sub_path = false
|
||||
|
||||
@@ -0,0 +1,17 @@
|
||||
apiVersion: 1
|
||||
|
||||
contactPoints:
|
||||
- orgId: 1
|
||||
name: Telegram
|
||||
receivers:
|
||||
- uid: aet1srtyc40lca
|
||||
type: telegram
|
||||
settings:
|
||||
bottoken: 7797967907:AAGZuUzzuS4LLb525rDNY52Awc2tvpsLjd4
|
||||
chatid: "-1002555823797"
|
||||
disable_notification: false
|
||||
disable_web_page_preview: false
|
||||
message: '{{ template "telegram.default.message" . }}'
|
||||
parse_mode: Markdown
|
||||
protect_content: false
|
||||
disableResolveMessage: false
|
||||
@@ -0,0 +1,141 @@
|
||||
apiVersion: 1
|
||||
|
||||
groups:
|
||||
- orgId: 1
|
||||
name: Default
|
||||
folder: Backend
|
||||
interval: 10s
|
||||
rules:
|
||||
- uid: aet1xbx1yaupsb
|
||||
title: Backend p99 > 500 ms
|
||||
condition: C
|
||||
data:
|
||||
- refId: A
|
||||
relativeTimeRange:
|
||||
from: 600
|
||||
to: 0
|
||||
datasourceUid: prometheus
|
||||
model:
|
||||
editorMode: code
|
||||
expr: |
|
||||
histogram_quantile(
|
||||
0.99,
|
||||
sum(
|
||||
rate(
|
||||
caddy_http_request_duration_seconds_bucket{instance="proxy:2019",handler="reverse_proxy",host="proxy:8080",job="caddy"}[$__rate_interval]
|
||||
)
|
||||
) by (le)
|
||||
)
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
- refId: C
|
||||
datasourceUid: __expr__
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 0.5
|
||||
type: gte
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
dashboardUid: e3a78c36-2f34-4ad6-81d5-284002896829
|
||||
panelId: 32
|
||||
noDataState: OK
|
||||
execErrState: Error
|
||||
for: 10s
|
||||
keepFiringFor: 10s
|
||||
annotations:
|
||||
__dashboardUid__: e3a78c36-2f34-4ad6-81d5-284002896829
|
||||
__panelId__: "32"
|
||||
runbook_url: https://admin.adnova.itqdev.xyz
|
||||
summary: p99 > 500 ms
|
||||
isPaused: false
|
||||
notification_settings:
|
||||
receiver: Telegram
|
||||
- orgId: 1
|
||||
name: Default
|
||||
folder: Postgres
|
||||
interval: 10s
|
||||
rules:
|
||||
- uid: fet1txr4slywwe
|
||||
title: "> 100 QPS on Postgresql"
|
||||
condition: C
|
||||
data:
|
||||
- refId: A
|
||||
relativeTimeRange:
|
||||
from: 600
|
||||
to: 0
|
||||
datasourceUid: prometheus
|
||||
model:
|
||||
editorMode: code
|
||||
expr: |
|
||||
sum(
|
||||
irate(pg_stat_database_xact_commit{datname="postgres",instance="postgres-exporter:9187",job="postgres"}[5m])
|
||||
)
|
||||
+ sum(
|
||||
irate(pg_stat_database_xact_rollback{datname="postgres",instance="postgres-exporter:9187",job="postgres"}[5m])
|
||||
)
|
||||
instant: true
|
||||
intervalMs: 1000
|
||||
legendFormat: __auto
|
||||
maxDataPoints: 43200
|
||||
range: false
|
||||
refId: A
|
||||
- refId: C
|
||||
datasourceUid: __expr__
|
||||
model:
|
||||
conditions:
|
||||
- evaluator:
|
||||
params:
|
||||
- 100
|
||||
type: gte
|
||||
operator:
|
||||
type: and
|
||||
query:
|
||||
params:
|
||||
- C
|
||||
reducer:
|
||||
params: []
|
||||
type: last
|
||||
type: query
|
||||
datasource:
|
||||
type: __expr__
|
||||
uid: __expr__
|
||||
expression: A
|
||||
intervalMs: 1000
|
||||
maxDataPoints: 43200
|
||||
refId: C
|
||||
type: threshold
|
||||
dashboardUid: postgres-overview
|
||||
panelId: 14
|
||||
noDataState: NoData
|
||||
execErrState: Error
|
||||
for: 10s
|
||||
keepFiringFor: 1m
|
||||
annotations:
|
||||
__dashboardUid__: postgres-overview
|
||||
__panelId__: "14"
|
||||
runbook_url: https://admin.adnova.itqdev.xyz
|
||||
summary: Postgresql QPS exceeded 100
|
||||
isPaused: false
|
||||
notification_settings:
|
||||
receiver: Telegram
|
||||
@@ -0,0 +1,54 @@
|
||||
apiVersion: 1
|
||||
|
||||
templates:
|
||||
- orgId: 1
|
||||
name: Telegram
|
||||
template: |
|
||||
{{ define "telegram.default.message" }} {{ if gt (len .Alerts.Firing) 0 }}
|
||||
🔥🚨 *FIRE IN THE HOLE!* 🚨🔥
|
||||
We've got *{{ len .Alerts.Firing }} firing alert(s)* that need your immediate attention!
|
||||
{{ range .Alerts.Firing }}
|
||||
---
|
||||
*Alert:* `{{ .Labels.alertname }}`
|
||||
{{ if .Labels.instance }}*Instance:* `{{ .Labels.instance }}`{{ end }}
|
||||
*Status:* 🔴 *FIRING* since {{ .StartsAt.Format "2006-01-02 15:04:05 MST" }}
|
||||
|
||||
{{ if .Annotations.summary }}*Summary:* {{ .Annotations.summary }}{{ end }}
|
||||
{{ if .Annotations.description }}*Description:* {{ .Annotations.description }}{{ end }}
|
||||
*Labels:*
|
||||
{{ range .Labels.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}`
|
||||
{{ end }}
|
||||
{{ if gt (len .Annotations) 0 }}*Annotations:*
|
||||
{{ range .Annotations.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}`
|
||||
{{ end }}{{ end }}
|
||||
|
||||
{{ if .DashboardURL }}📊 [View Dashboard]({{ .DashboardURL }})
|
||||
{{ end }}{{ if .PanelURL }}📈 [View Panel]({{ .PanelURL }})
|
||||
{{ end }}{{ if .GeneratorURL }}🔗 [Alert Source]({{ .GeneratorURL }})
|
||||
{{ end }}{{ if .SilenceURL }}🤫 [Silence Alert]({{ .SilenceURL }})
|
||||
{{ end }}--- {{ end }} {{ end }}
|
||||
{{ if gt (len .Alerts.Resolved) 0 }}
|
||||
✅🟢 *ALL CLEAR!* 🟢✅
|
||||
Great news! *{{ len .Alerts.Resolved }} alert(s)* have been resolved.
|
||||
{{ range .Alerts.Resolved }}
|
||||
---
|
||||
*Alert:* `{{ .Labels.alertname }}`
|
||||
{{ if .Labels.instance }}*Instance:* `{{ .Labels.instance }}`{{ end }}
|
||||
*Status:* ✅ *RESOLVED* at {{ .EndsAt.Format "2006-01-02 15:04:05 MST" }} (was active since {{ .StartsAt.Format "2006-01-02 15:04:05 MST" }})
|
||||
|
||||
{{ if .Annotations.summary }}*Summary:* {{ .Annotations.summary }}{{ end }}
|
||||
{{ if .Annotations.description }}*Description:* {{ .Annotations.description }}{{ end }}
|
||||
*Labels:*
|
||||
{{ range .Labels.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}`
|
||||
{{ end }}
|
||||
{{ if gt (len .Annotations) 0 }}*Annotations:*
|
||||
{{ range .Annotations.SortedPairs }} • `{{ .Name }}` = `{{ .Value }}`
|
||||
{{ end }}{{ end }}
|
||||
|
||||
{{ if .DashboardURL }}📊 [View Dashboard]({{ .DashboardURL }})
|
||||
{{ end }}{{ if .PanelURL }}📈 [View Panel]({{ .PanelURL }})
|
||||
{{ end }}{{ if .GeneratorURL }}🔗 [Alert Source]({{ .GeneratorURL }}) {{ end }} {{ end }} {{ end }}
|
||||
{{ if or (gt (len .Alerts.Firing) 0) (gt (len .Alerts.Resolved) 0) }}
|
||||
🔔 *Grafana Alertmanager:* [View All Alerts]({{ template "__alertmanagerURL" . }}) 🔔
|
||||
{{ end }}
|
||||
{{ end }}
|
||||
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,910 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": {
|
||||
"type": "grafana",
|
||||
"uid": "-- Grafana --"
|
||||
},
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "A dashboard that monitors Django which focuses on breaking down requests by view.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 0,
|
||||
"id": 12,
|
||||
"links": [
|
||||
{
|
||||
"tags": ["backend"],
|
||||
"targetBlank": true,
|
||||
"title": "Backend Dashboards",
|
||||
"type": "dashboards"
|
||||
}
|
||||
],
|
||||
"liveNow": true,
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"panels": [],
|
||||
"title": "Summary",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "red"
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 0.95
|
||||
},
|
||||
{
|
||||
"color": "green",
|
||||
"value": 0.99
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "percentunit"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 4,
|
||||
"w": 6,
|
||||
"x": 0,
|
||||
"y": 1
|
||||
},
|
||||
"id": 2,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"percentChangeColorMode": "standard",
|
||||
"reduceOptions": {
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
"showPercentChange": false,
|
||||
"textMode": "auto",
|
||||
"wideLayout": true
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum(\n rate(\n django_http_responses_total_by_status_view_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\",\n status!~\"[4-5].*\"\n }[1w]\n )\n) /\nsum(\n rate(\n django_http_responses_total_by_status_view_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\"\n }[1w]\n )\n)\n",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Success Rate (non 4xx-5xx responses) [1w]",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 10
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 100
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 4,
|
||||
"w": 6,
|
||||
"x": 6,
|
||||
"y": 1
|
||||
},
|
||||
"id": 3,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"percentChangeColorMode": "standard",
|
||||
"reduceOptions": {
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
"showPercentChange": false,
|
||||
"textMode": "auto",
|
||||
"wideLayout": true
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum by (view) (\n increase(\n django_http_exceptions_total_by_view_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n }[1w]\n ) > 0\n)\n",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "HTTP Exceptions [1w]",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 1000
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 2000
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 4,
|
||||
"w": 6,
|
||||
"x": 12,
|
||||
"y": 1
|
||||
},
|
||||
"id": 4,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"percentChangeColorMode": "standard",
|
||||
"reduceOptions": {
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
"showPercentChange": false,
|
||||
"textMode": "auto",
|
||||
"wideLayout": true
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.50,\n sum (\n rate (\n django_http_requests_latency_seconds_by_view_method_bucket {\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\"\n }[$__range]\n )\n ) by (job, le)\n)\n",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Average Request Latency (P50) [1w]",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "yellow",
|
||||
"value": 2500
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 5000
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 4,
|
||||
"w": 6,
|
||||
"x": 18,
|
||||
"y": 1
|
||||
},
|
||||
"id": 5,
|
||||
"options": {
|
||||
"colorMode": "value",
|
||||
"graphMode": "area",
|
||||
"justifyMode": "auto",
|
||||
"orientation": "auto",
|
||||
"percentChangeColorMode": "standard",
|
||||
"reduceOptions": {
|
||||
"calcs": ["lastNotNull"],
|
||||
"fields": "",
|
||||
"values": false
|
||||
},
|
||||
"showPercentChange": false,
|
||||
"textMode": "auto",
|
||||
"wideLayout": true
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95,\n sum (\n rate (\n django_http_requests_latency_seconds_by_view_method_bucket {\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\"\n }[$__range]\n )\n ) by (job, le)\n)\n",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Average Request Latency (P95) [1w]",
|
||||
"type": "stat"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 5
|
||||
},
|
||||
"id": 6,
|
||||
"panels": [],
|
||||
"title": "Request & Responses",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 100,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 6
|
||||
},
|
||||
"id": 7,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["lastNotNull", "mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"sortBy": "Mean",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": false,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "round(\n sum(\n rate(\n django_http_requests_total_by_view_transport_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\"\n }[$__rate_interval]\n ) > 0\n ) by (job), 0.001\n)\n",
|
||||
"legendFormat": "reqps",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Requests",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 100,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "percent"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "2xx"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "green",
|
||||
"mode": "fixed"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "3xx"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "blue",
|
||||
"mode": "fixed"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "4xx"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "yellow",
|
||||
"mode": "fixed"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "5xx"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "red",
|
||||
"mode": "fixed"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 6
|
||||
},
|
||||
"id": 8,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["lastNotNull", "mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"sortBy": "Mean",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": false,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "round(\n sum(\n rate(\n django_http_responses_total_by_status_view_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n status=~\"2.*\",\n }[$__rate_interval]\n ) > 0\n ) by (job), 0.001\n)\n",
|
||||
"legendFormat": "2xx",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "round(\n sum(\n rate(\n django_http_responses_total_by_status_view_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n status=~\"3.*\",\n }[$__rate_interval]\n ) > 0\n ) by (job), 0.001\n)\n",
|
||||
"legendFormat": "3xx",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "round(\n sum(\n rate(\n django_http_responses_total_by_status_view_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n status=~\"4.*\",\n }[$__rate_interval]\n ) > 0\n ) by (job), 0.001\n)\n",
|
||||
"legendFormat": "4xx",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "round(\n sum(\n rate(\n django_http_responses_total_by_status_view_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n status=~\"5.*\",\n }[$__rate_interval]\n ) > 0\n ) by (job), 0.001\n)\n",
|
||||
"legendFormat": "5xx",
|
||||
"refId": "D"
|
||||
}
|
||||
],
|
||||
"title": "Responses",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 14
|
||||
},
|
||||
"id": 9,
|
||||
"panels": [],
|
||||
"title": "Latency & Status Codes",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 100,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "value"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "reqps"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 0,
|
||||
"y": 15
|
||||
},
|
||||
"id": 10,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["lastNotNull", "mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"sortBy": "Mean",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": false,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "round(\n sum(\n rate(\n django_http_responses_total_by_status_view_method_total{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\",\n }[$__rate_interval]\n ) > 0\n ) by (namespace, job, view, status, method), 0.001\n)\n",
|
||||
"legendFormat": "{{ view }} / {{ status }} / {{ method }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Responses Status Codes",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 10,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 12,
|
||||
"x": 12,
|
||||
"y": 15
|
||||
},
|
||||
"id": 11,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["lastNotNull", "mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"sortBy": "Mean",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": false,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.50,\n sum(\n irate(\n django_http_requests_latency_seconds_by_view_method_bucket{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\"\n }[$__rate_interval]\n ) > 0\n ) by (view, le)\n)\n",
|
||||
"legendFormat": "50 - {{ view }}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95,\n sum(\n irate(\n django_http_requests_latency_seconds_by_view_method_bucket{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\"\n }[$__rate_interval]\n ) > 0\n ) by (view, le)\n)\n",
|
||||
"legendFormat": "95 - {{ view }}",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99,\n sum(\n irate(\n django_http_requests_latency_seconds_by_view_method_bucket{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\"\n }[$__rate_interval]\n ) > 0\n ) by (view, le)\n)\n",
|
||||
"legendFormat": "99 - {{ view }}",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.999,\n sum(\n irate(\n django_http_requests_latency_seconds_by_view_method_bucket{\n namespace=~\"$namespace\",\n job=~\"$job\",\n view=\"$view\",\n method=~\"$method\"\n }[$__rate_interval]\n ) > 0\n ) by (view, le)\n)\n",
|
||||
"legendFormat": "99.9 - {{ view }}",
|
||||
"refId": "D"
|
||||
}
|
||||
],
|
||||
"title": "Request Latency",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"preload": false,
|
||||
"refresh": "5s",
|
||||
"schemaVersion": 41,
|
||||
"tags": ["backend"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"refresh": 1,
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": false,
|
||||
"label": "Namespace",
|
||||
"name": "namespace",
|
||||
"query": "label_values(django_http_responses_total_by_status_view_method_total{}, namespace)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": false,
|
||||
"label": "Job",
|
||||
"name": "job",
|
||||
"query": "label_values(django_http_responses_total_by_status_view_method_total{namespace=~\"$namespace\"}, job)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": false,
|
||||
"label": "View",
|
||||
"name": "view",
|
||||
"query": "label_values(django_http_responses_total_by_status_view_method_total{namespace=~\"$namespace\", job=~\"$job\", view!~\"<unnamed view>|health_check:health_check_home|prometheus-django-metrics\"}, view)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": true,
|
||||
"label": "Method",
|
||||
"multi": true,
|
||||
"name": "method",
|
||||
"query": "label_values(django_http_responses_total_by_status_view_method_total{namespace=~\"$namespace\", job=~\"$job\", view=~\"$view\"}, method)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-30m",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "browser",
|
||||
"title": "Requests / By View",
|
||||
"uid": "backend-requests-by-view",
|
||||
"version": 2,
|
||||
"weekStart": "monday"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -0,0 +1,768 @@
|
||||
{
|
||||
"annotations": {
|
||||
"list": [
|
||||
{
|
||||
"builtIn": 1,
|
||||
"datasource": {
|
||||
"type": "grafana",
|
||||
"uid": "-- Grafana --"
|
||||
},
|
||||
"enable": true,
|
||||
"hide": true,
|
||||
"iconColor": "rgba(0, 211, 255, 1)",
|
||||
"name": "Annotations & Alerts",
|
||||
"type": "dashboard"
|
||||
}
|
||||
]
|
||||
},
|
||||
"description": "A dashboard that monitors Celery.",
|
||||
"editable": true,
|
||||
"fiscalYearStartMonth": 0,
|
||||
"graphTooltip": 0,
|
||||
"id": 2,
|
||||
"links": [
|
||||
{
|
||||
"tags": ["celery"],
|
||||
"targetBlank": true,
|
||||
"title": "Celery Dashboards",
|
||||
"type": "dashboards"
|
||||
}
|
||||
],
|
||||
"liveNow": true,
|
||||
"panels": [
|
||||
{
|
||||
"collapsed": false,
|
||||
"gridPos": {
|
||||
"h": 1,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 0
|
||||
},
|
||||
"id": 1,
|
||||
"panels": [],
|
||||
"title": "Tasks",
|
||||
"type": "row"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"noValue": 0,
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "Success Rate"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "unit",
|
||||
"value": "percentunit"
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 16,
|
||||
"x": 0,
|
||||
"y": 1
|
||||
},
|
||||
"id": 2,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"footer": {
|
||||
"countRows": false,
|
||||
"enablePagination": true,
|
||||
"fields": "",
|
||||
"reducer": ["sum"],
|
||||
"show": false
|
||||
},
|
||||
"showHeader": true,
|
||||
"sortBy": [
|
||||
{
|
||||
"desc": true,
|
||||
"displayName": "Succeeded"
|
||||
}
|
||||
]
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name)\n/(sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name)\n+sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name)\n) > -1\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_sent_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "D"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_received_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "E"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_rejected_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "F"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_retried_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "G"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_revoked_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n )\n) by (name) > 0\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "H"
|
||||
}
|
||||
],
|
||||
"title": "Task Stats",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "merge"
|
||||
},
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Value #A": 1,
|
||||
"Value #B": 2,
|
||||
"Value #C": 3,
|
||||
"Value #D": 4,
|
||||
"Value #E": 5,
|
||||
"Value #F": 6,
|
||||
"Value #G": 7,
|
||||
"Value #H": 8,
|
||||
"name": 0
|
||||
},
|
||||
"renameByName": {
|
||||
"Value #A": "Success Rate",
|
||||
"Value #B": "Succeeded",
|
||||
"Value #C": "Failed",
|
||||
"Value #D": "Sent",
|
||||
"Value #E": "Received",
|
||||
"Value #F": "Rejected",
|
||||
"Value #G": "Retried",
|
||||
"Value #H": "Revoked",
|
||||
"name": "Name"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"align": "auto",
|
||||
"cellOptions": {
|
||||
"type": "auto"
|
||||
},
|
||||
"inspect": false
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 8,
|
||||
"x": 16,
|
||||
"y": 1
|
||||
},
|
||||
"id": 3,
|
||||
"options": {
|
||||
"cellHeight": "sm",
|
||||
"footer": {
|
||||
"countRows": false,
|
||||
"enablePagination": true,
|
||||
"fields": "",
|
||||
"reducer": ["sum"],
|
||||
"show": false
|
||||
},
|
||||
"showHeader": true,
|
||||
"sortBy": [
|
||||
{
|
||||
"desc": true,
|
||||
"displayName": "Value"
|
||||
}
|
||||
]
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "round(\n sum (\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__range]\n )\n ) by (name, exception) > 0\n)\n",
|
||||
"format": "table",
|
||||
"instant": true,
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Task Exceptions",
|
||||
"transformations": [
|
||||
{
|
||||
"id": "organize",
|
||||
"options": {
|
||||
"excludeByName": {
|
||||
"Time": true,
|
||||
"job": true
|
||||
},
|
||||
"indexByName": {
|
||||
"Value": 2,
|
||||
"exception": 1,
|
||||
"name": 0
|
||||
},
|
||||
"renameByName": {
|
||||
"exception": "Exception",
|
||||
"name": "Task"
|
||||
}
|
||||
}
|
||||
}
|
||||
],
|
||||
"type": "table"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 9
|
||||
},
|
||||
"id": 4,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"sortBy": "Mean",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": false,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_succeeded_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n",
|
||||
"legendFormat": "Succeeded - {{ name }}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n",
|
||||
"legendFormat": "Failed - {{ name }}",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_sent_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n",
|
||||
"legendFormat": "Sent - {{ name }}",
|
||||
"refId": "C"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_received_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n",
|
||||
"legendFormat": "Received - {{ name }}",
|
||||
"refId": "D"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_retried_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n",
|
||||
"legendFormat": "Retried - {{ name }}",
|
||||
"refId": "E"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_revoked_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n",
|
||||
"legendFormat": "Revoked - {{ name }}",
|
||||
"refId": "F"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_rejected_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name) > 0\n",
|
||||
"legendFormat": "Rejected - {{ name }}",
|
||||
"refId": "G"
|
||||
}
|
||||
],
|
||||
"title": "Tasks Completed",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"color": {
|
||||
"mode": "palette-classic"
|
||||
},
|
||||
"custom": {
|
||||
"axisBorderShow": false,
|
||||
"axisCenteredZero": false,
|
||||
"axisColorMode": "text",
|
||||
"axisLabel": "",
|
||||
"axisPlacement": "auto",
|
||||
"barAlignment": 0,
|
||||
"barWidthFactor": 0.6,
|
||||
"drawStyle": "line",
|
||||
"fillOpacity": 0,
|
||||
"gradientMode": "none",
|
||||
"hideFrom": {
|
||||
"legend": false,
|
||||
"tooltip": false,
|
||||
"viz": false
|
||||
},
|
||||
"insertNulls": false,
|
||||
"lineInterpolation": "linear",
|
||||
"lineWidth": 1,
|
||||
"pointSize": 5,
|
||||
"scaleDistribution": {
|
||||
"type": "linear"
|
||||
},
|
||||
"showPoints": "auto",
|
||||
"spanNulls": false,
|
||||
"stacking": {
|
||||
"group": "A",
|
||||
"mode": "none"
|
||||
},
|
||||
"thresholdsStyle": {
|
||||
"mode": "off"
|
||||
}
|
||||
},
|
||||
"mappings": [],
|
||||
"thresholds": {
|
||||
"mode": "absolute",
|
||||
"steps": [
|
||||
{
|
||||
"color": "green"
|
||||
},
|
||||
{
|
||||
"color": "red",
|
||||
"value": 80
|
||||
}
|
||||
]
|
||||
},
|
||||
"unit": "short"
|
||||
},
|
||||
"overrides": []
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 17
|
||||
},
|
||||
"id": 5,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"sortBy": "Mean",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"hideZeros": false,
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "12.0.2",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "sum (\n round(\n increase(\n celery_task_failed_total{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n )\n )\n) by (name, exception) > 0\n",
|
||||
"legendFormat": "{{ name }}/{{ exception }}",
|
||||
"refId": "A"
|
||||
}
|
||||
],
|
||||
"title": "Task Exceptions",
|
||||
"type": "timeseries"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "datasource",
|
||||
"uid": "-- Mixed --"
|
||||
},
|
||||
"fieldConfig": {
|
||||
"defaults": {
|
||||
"custom": {
|
||||
"spanNulls": false
|
||||
},
|
||||
"unit": "s"
|
||||
},
|
||||
"overrides": [
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "P50"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "green",
|
||||
"mode": "fixed"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "P95"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "yellow",
|
||||
"mode": "fixed"
|
||||
}
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"matcher": {
|
||||
"id": "byName",
|
||||
"options": "P99"
|
||||
},
|
||||
"properties": [
|
||||
{
|
||||
"id": "color",
|
||||
"value": {
|
||||
"fixedColor": "red",
|
||||
"mode": "fixed"
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
]
|
||||
},
|
||||
"gridPos": {
|
||||
"h": 8,
|
||||
"w": 24,
|
||||
"x": 0,
|
||||
"y": 25
|
||||
},
|
||||
"id": 6,
|
||||
"options": {
|
||||
"legend": {
|
||||
"calcs": ["mean", "max"],
|
||||
"displayMode": "table",
|
||||
"placement": "right",
|
||||
"showLegend": true,
|
||||
"sortBy": "Mean",
|
||||
"sortDesc": true
|
||||
},
|
||||
"tooltip": {
|
||||
"mode": "multi",
|
||||
"sort": "desc"
|
||||
}
|
||||
},
|
||||
"pluginVersion": "v11.1.0",
|
||||
"targets": [
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.50,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (name, job, le)\n)\n",
|
||||
"legendFormat": "P50 - {{ name }}",
|
||||
"refId": "A"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.95,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (name, job, le)\n)\n",
|
||||
"legendFormat": "P95 - {{ name }}",
|
||||
"refId": "B"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "$datasource"
|
||||
},
|
||||
"expr": "histogram_quantile(0.99,\n sum(\n irate(\n celery_task_runtime_bucket{\n job=\"$job\",\n name=~\"$task\",\n queue_name=~\"$queue_name\"\n }[$__rate_interval]\n ) > 0\n ) by (name, job, le)\n)\n",
|
||||
"legendFormat": "P99 - {{ name }}",
|
||||
"refId": "C"
|
||||
}
|
||||
],
|
||||
"title": "Tasks Runtime",
|
||||
"type": "timeseries"
|
||||
}
|
||||
],
|
||||
"preload": false,
|
||||
"refresh": "10s",
|
||||
"schemaVersion": 41,
|
||||
"tags": ["celery"],
|
||||
"templating": {
|
||||
"list": [
|
||||
{
|
||||
"label": "Data source",
|
||||
"name": "datasource",
|
||||
"query": "prometheus",
|
||||
"refresh": 1,
|
||||
"type": "datasource"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": false,
|
||||
"label": "Namespace",
|
||||
"name": "namespace",
|
||||
"query": "label_values(celery_worker_up{}, namespace)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": false,
|
||||
"label": "Job",
|
||||
"name": "job",
|
||||
"query": "label_values(celery_worker_up{namespace=\"$namespace\"}, job)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": false,
|
||||
"label": "Queue Name",
|
||||
"name": "queue_name",
|
||||
"query": "label_values(celery_task_received_total{namespace=\"$namespace\", job=\"$job\", name!~\"None\"}, queue_name)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
},
|
||||
{
|
||||
"datasource": {
|
||||
"type": "prometheus",
|
||||
"uid": "${datasource}"
|
||||
},
|
||||
"includeAll": false,
|
||||
"label": "Task",
|
||||
"multi": true,
|
||||
"name": "task",
|
||||
"query": "label_values(celery_task_received_total{namespace=\"$namespace\", job=\"$job\", queue_name=~\"$queue_name\", name!~\"None\"}, name)",
|
||||
"refresh": 2,
|
||||
"sort": 1,
|
||||
"type": "query"
|
||||
}
|
||||
]
|
||||
},
|
||||
"time": {
|
||||
"from": "now-24h",
|
||||
"to": "now"
|
||||
},
|
||||
"timepicker": {},
|
||||
"timezone": "browser",
|
||||
"title": "By Task",
|
||||
"uid": "celery-tasks-by-task",
|
||||
"version": 1,
|
||||
"weekStart": "monday"
|
||||
}
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,7 +1,7 @@
|
||||
# Global config
|
||||
global:
|
||||
scrape_interval: 10s
|
||||
scrape_timeout: 10s
|
||||
scrape_interval: 5s
|
||||
scrape_timeout: 5s
|
||||
evaluation_interval: 10m
|
||||
external_labels:
|
||||
environment: local
|
||||
@@ -10,24 +10,31 @@ global:
|
||||
scrape_configs:
|
||||
# Prometheus
|
||||
- job_name: prometheus
|
||||
scrape_interval: 5s
|
||||
static_configs:
|
||||
- targets: ["localhost:9090"]
|
||||
|
||||
# Postgres
|
||||
- job_name: postgres
|
||||
scrape_interval: 10s
|
||||
static_configs:
|
||||
- targets: ["postgres-exporter:9187"]
|
||||
|
||||
# Redis
|
||||
- job_name: redis
|
||||
scrape_interval: 10s
|
||||
static_configs:
|
||||
- targets: ["redis-exporter:9121"]
|
||||
|
||||
# Celery
|
||||
- job_name: celery
|
||||
scrape_interval: 30s
|
||||
scrape_interval: 15s
|
||||
static_configs:
|
||||
- targets: ["celery-exporter:9808"]
|
||||
|
||||
# Backend
|
||||
- job_name: backend
|
||||
static_configs:
|
||||
- targets: ["backend:8080"]
|
||||
|
||||
# Caddy
|
||||
- job_name: caddy
|
||||
static_configs:
|
||||
- targets: ["proxy:2019"]
|
||||
|
||||
Reference in New Issue
Block a user