Skip to content

test: add self-metrics to observability setup #1923

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
PedroBinotto wants to merge 1 commit into
base: dev
Choose a base branch
from
Draft

test: add self-metrics to observability setup #1923

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .changeset/prom-alertmgr-debug-logs.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
---
---
8 changes: 7 additions & 1 deletion infra/monitoring/entrypoint.alertmanager.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,9 @@
#!/bin/sh
sed "s|\${SLACK_WEBHOOK_URL}|${SLACK_WEBHOOK_URL}|g;s|\${SLACK_CHANNEL}|${SLACK_CHANNEL}|g" /etc/alertmanager/config.yml.tmpl > /etc/alertmanager/config.yml
exec /bin/alertmanager --config.file=/etc/alertmanager/config.yml --storage.path=/alertmanager ${ALERTMANAGER_EXTERNAL_URL:+--web.external-url="$ALERTMANAGER_EXTERNAL_URL"} "$@"
exec /bin/alertmanager \
--config.file=/etc/alertmanager/config.yml \
--storage.path=/alertmanager \
--log.level="${ALERTMANAGER_LOG_LEVEL:-debug}" \
--log.format="${ALERTMANAGER_LOG_FORMAT:-json}" \
${ALERTMANAGER_EXTERNAL_URL:+--web.external-url="$ALERTMANAGER_EXTERNAL_URL"} \
"$@"
9 changes: 8 additions & 1 deletion infra/monitoring/entrypoint.prometheus.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,10 @@
#!/bin/sh
envsubst < /etc/prometheus/prometheus.yml.tmpl > /etc/prometheus/prometheus.yml
exec /bin/prometheus --config.file=/etc/prometheus/prometheus.yml --storage.tsdb.path=/prometheus --web.enable-lifecycle --web.enable-remote-write-receiver "$@"
exec /bin/prometheus \
--config.file=/etc/prometheus/prometheus.yml \
--storage.tsdb.path=/prometheus \
--web.enable-lifecycle \
--web.enable-remote-write-receiver \
--log.level="${PROMETHEUS_LOG_LEVEL:-debug}" \
--log.format="${PROMETHEUS_LOG_FORMAT:-json}" \
"$@"
141 changes: 141 additions & 0 deletions infra/monitoring/grafana/dashboards/anticapture-v2.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -943,6 +943,147 @@
]
}
]
},
{
"id": 140,
"type": "row",
"title": "Scrape Diagnostics",
"collapsed": true,
"gridPos": { "x": 0, "y": 113, "w": 24, "h": 1 },
"panels": [
{
"id": 1401,
"title": "up (per job) — 1 = scrape succeeded, 0 = scrape failed",
"type": "timeseries",
"gridPos": { "x": 0, "y": 114, "w": 12, "h": 8 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"unit": "short",
"min": 0,
"max": 1,
"color": { "mode": "palette-classic" },
"custom": { "fillOpacity": 10, "lineInterpolation": "stepAfter" }
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
}
},
"targets": [
{
"expr": "up{job=~\"anticapture-.*\"}",
"legendFormat": "{{job}}",
"refId": "A"
}
]
},
{
"id": 1402,
"title": "Scrape flap count (changes in up over 1h)",
"type": "timeseries",
"gridPos": { "x": 12, "y": 114, "w": 12, "h": 8 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"unit": "short",
"color": { "mode": "palette-classic" },
"custom": { "fillOpacity": 10 }
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
}
},
"targets": [
{
"expr": "changes(up{job=~\"anticapture-.*\"}[1h])",
"legendFormat": "{{job}}",
"refId": "A"
}
]
},
{
"id": 1403,
"title": "scrape_duration_seconds (threshold = scrape_timeout 12s)",
"type": "timeseries",
"gridPos": { "x": 0, "y": 122, "w": 12, "h": 8 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"unit": "s",
"color": { "mode": "palette-classic" },
"thresholds": {
"mode": "absolute",
"steps": [
{ "color": "green", "value": null },
{ "color": "red", "value": 12 }
]
},
"custom": {
"fillOpacity": 5,
"thresholdsStyle": { "mode": "line" }
}
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
}
},
"targets": [
{
"expr": "scrape_duration_seconds{job=~\"anticapture-.*\"}",
"legendFormat": "{{job}}",
"refId": "A"
}
]
},
{
"id": 1404,
"title": "scrape_samples_scraped (0 = empty / failed response)",
"type": "timeseries",
"gridPos": { "x": 12, "y": 122, "w": 12, "h": 8 },
"datasource": { "type": "prometheus", "uid": "prometheus" },
"fieldConfig": {
"defaults": {
"unit": "short",
"color": { "mode": "palette-classic" },
"custom": { "fillOpacity": 5 }
},
"overrides": []
},
"options": {
"tooltip": { "mode": "multi", "sort": "desc" },
"legend": {
"displayMode": "list",
"placement": "bottom",
"showLegend": true
}
},
"targets": [
{
"expr": "scrape_samples_scraped{job=~\"anticapture-.*\"}",
"legendFormat": "{{job}}",
"refId": "A"
}
]
}
]
}
]
}
4 changes: 4 additions & 0 deletions infra/monitoring/prometheus.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,7 @@
global:
scrape_interval: 15s
scrape_timeout: 12s

alerting:
alertmanagers:
- static_configs:
Expand Down
Loading