fix(alerting): align Alertmanager metric schema
All checks were successful
CD Pipeline / workflow-shape (push) Successful in 2s
CD Pipeline / cancel-stale-cd (push) Has been skipped
CD Pipeline / tests (push) Successful in 2m31s
CD Pipeline / build-and-deploy (push) Successful in 15m18s
AWOOOI Harbor 110 Local Repair / workflow-shape (push) Successful in 1s
AWOOOI Harbor 110 Local Repair / harbor-110-local-repair (push) Successful in 22s
CD Pipeline / post-deploy-checks (push) Successful in 5m35s

This commit is contained in:
ogt
2026-07-16 17:38:45 +08:00
parent 7cd4b30363
commit 4af6487ba6
16 changed files with 324 additions and 43 deletions

View File

@@ -119,8 +119,8 @@ test -f "${REMOTE_CONFIG}"
test "$(docker inspect --format '{{.State.Running}}' "${PROMETHEUS_CONTAINER}")" = true
curl -fsS "${PROMETHEUS_URL}/-/ready" >/dev/null
METRICS_SNAPSHOT="$(curl -fsS "${ALERTMANAGER_METRICS_URL}")"
grep -Eq '^alertmanager_notification_requests_total\{[^}]*receiver="awoooi-webhook"' <<<"${METRICS_SNAPSHOT}"
grep -Eq '^alertmanager_notification_requests_failed_total\{[^}]*receiver="awoooi-webhook"' <<<"${METRICS_SNAPSHOT}"
grep -Eq '^alertmanager_notification_requests_total\{[^}]*integration="webhook"' <<<"${METRICS_SNAPSHOT}"
grep -Eq '^alertmanager_notification_requests_failed_total\{[^}]*integration="webhook"' <<<"${METRICS_SNAPSHOT}"
SOURCE_SHA="$(sha256sum "${REMOTE_CONFIG}" | awk '{print $1}')"
python3 - "${REMOTE_CONFIG}" "${REMOTE_CANDIDATE}" <<'PY'
@@ -144,6 +144,12 @@ block = """ # BEGIN AWOOOI ALERTMANAGER RUNTIME DELIVERY TRUTH
host: '110'
service: 'alertmanager'
env: 'prod'
metric_relabel_configs:
- source_labels: [__name__, integration]
separator: ';'
regex: 'alertmanager_notification_requests(_failed)?_total;webhook'
target_label: receiver_contract
replacement: 'awoooi-webhook'
# END AWOOOI ALERTMANAGER RUNTIME DELIVERY TRUTH
"""
@@ -376,7 +382,7 @@ test "${SECOND_GCP_A_SCRAPE}" != "${FIRST_GCP_A_SCRAPE}"
test "${SECOND_GCP_B_SCRAPE}" != "${FIRST_GCP_B_SCRAPE}"
SERIES_COUNT="$(curl -fsS --get \
--data-urlencode 'query=alertmanager_notification_requests_total{job="alertmanager-runtime",integration="webhook",receiver="awoooi-webhook"}' \
--data-urlencode 'query=alertmanager_notification_requests_total{job="alertmanager-runtime",integration="webhook",receiver_contract="awoooi-webhook"}' \
"${PROMETHEUS_URL}/api/v1/query" | python3 -c '
import json
import sys
@@ -385,7 +391,7 @@ print(len(json.load(sys.stdin)["data"]["result"]))
test "${SERIES_COUNT}" = 1
FAILED_SERIES_COUNT="$(curl -fsS --get \
--data-urlencode 'query=alertmanager_notification_requests_failed_total{job="alertmanager-runtime",integration="webhook",receiver="awoooi-webhook"}' \
--data-urlencode 'query=alertmanager_notification_requests_failed_total{job="alertmanager-runtime",integration="webhook",receiver_contract="awoooi-webhook"}' \
"${PROMETHEUS_URL}/api/v1/query" | python3 -c '
import json
import sys