eho/register-referentie
1
0
Fork 0
Code Issues 10 Pull Requests 1 Actions Packages Projects Releases 1 Wiki Activity

feat(infra): Tempo + Prometheus + Grafana observability backplane in compose (refs #122)

Browse Source 
Three built images on the cg network with config baked in: Tempo (OTLP ingest,
ports 4317/4318), Prometheus, and Grafana with both datasources auto-provisioned.
Config lives in infra/observability/. The verify-observability step runs early in
CI verify-stack; the three containers are added to the failure log-dump list.
Tempo's Grafana plugin has no datasource /health method, so the check proves
Tempo reachability through Grafana's datasource proxy instead.

refs #122
This commit is contained in:
not
2026-07-23 12:46:54 +02:00
parent f12e9ce746
commit f29a8598fd
9 changed files with 120 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
infra/run-observability-check.sh
+14 -8
View File
@@ -12,16 +12,19 @@ GRAFANA="${GRAFANA_URL:-http://localhost:3000}"
AUTH="${GRAFANA_AUTH:-admin:admin}"
TIMEOUT="${OBS_TIMEOUT:-60}"
# poll <description> <url> <json-path-expr> <expected>
# poll <description> <url> <python-bool-expr over `d` (parsed JSON)>
# Passes when the expression prints True within TIMEOUT. Tempo's Grafana plugin
# doesn't implement the datasource /health method, so instead of the Prometheus-
# style health probe we prove reachability through Grafana's datasource proxy.
poll() {
local desc="$1" url="$2" path="$3" want="$4" got deadline
local desc="$1" url="$2" expr="$3" got deadline
deadline=$(( $(date +%s) + TIMEOUT ))
while :; do
got="$(curl -fsS -u "$AUTH" "$url" 2>/dev/null \
| python3 -c "import sys,json;print(json.load(sys.stdin)$path)" 2>/dev/null || true)"
[ "$got" = "$want" ] && { echo " ✓ $desc"; return 0; }
| python3 -c "import sys,json; d=json.load(sys.stdin); print($expr)" 2>/dev/null || true)"
[ "$got" = "True" ] && { echo " ✓ $desc"; return 0; }
if [ "$(date +%s)" -ge "$deadline" ]; then
echo " ✗ $desc — got '$got', want '$want' ($url)" >&2
echo " ✗ $desc — check failed ($url)" >&2
return 1
fi
sleep 2
@@ -29,7 +32,10 @@ poll() {
}
echo "Checking observability backplane at $GRAFANA ..."
poll "Grafana is healthy" "$GRAFANA/api/health" "['database']" "ok"
poll "Prometheus datasource reachable" "$GRAFANA/api/datasources/uid/prometheus/health" "['status']" "OK"
poll "Tempo datasource reachable" "$GRAFANA/api/datasources/uid/tempo/health" "['status']" "OK"
poll "Grafana is healthy" \
"$GRAFANA/api/health" "d['database'] == 'ok'"
poll "Prometheus datasource reachable" \
"$GRAFANA/api/datasources/uid/prometheus/health" "d['status'] == 'OK'"
poll "Tempo datasource reachable (via Grafana proxy)" \
"$GRAFANA/api/datasources/proxy/uid/tempo/api/status/buildinfo" "bool(d.get('version'))"
echo "Observability backplane OK."