Reviewed the last 24h of Slack alerts after the midday node-pressure blip: the volume came far less from the outage than from (a) alerts re-pinging every few hours while nothing changed and (b) a pod cascade that fired uninhibited. This hardens the alerting *system* so recurrences are quiet, rather than just clearing today's broken services. Changes (all in the monitoring module): * Alert-on-change routing. warning/info repeat_interval -> 8760h (notify once, then only on a membership change or resolve); critical 1h -> 6h (a slow nag, not an hourly drip). send_resolved stays on. The bulk of the 24h volume was these re-pings (RpiSofiaUndervoltage alone fired continuously for ~24h, re-notifying every 4h). * Daily digest CronJob (alert_digest.tf + alert_digest.py) -> #alerts at 08:00 Europe/London: the full current board grouped by severity + what resolved in the last 24h. This is the standing-state safety net for the alert-on-change model. Stock python:3.12-alpine, pure-stdlib script (no pip/apk at runtime -> none of the per-run disk-write footprint that disabled status-page-pusher). Reuses the existing Alertmanager Slack webhook via a namespaced Secret; reads Alertmanager v2 + Prometheus. * Cascade inhibition. NodeConditionBad/NodeDiskPressure now suppress the downstream pod-churn alerts (PodCrashLooping, PodImagePullBackOff, PodsStuckContainerCreating, ScrapeTargetDown, *ReplicasMismatch, ...). The midday DiskPressure event on 4 nodes fired 25 PodCrashLooping + 14 PodImagePullBackOff uninhibited because only NodeDown was a source. * T3 probe de-duplication. T3ProbeLegDown now inhibits T3ProbeDropBurst for the same leg — two alerts described one condition and were the #1 noise source (~3,400 alert-minutes over 24h). * ScrapeTargetDown false positives. Scrape only Ready endpoints, so completed CronJob pods that linger in EndpointSlices as NotReady addresses stop firing phantom "down" alerts (tts/tripit/beads). A Ready pod with a genuinely broken metrics endpoint still fires. * for: 0m -> 5m on the flappy backup-status flags (LVM/Weekly/Offsite/ NfsMirror/Vzdump *Failing) and DNS spike detectors, so a single transient Pushgateway/scrape blip no longer fires-and-resolves. * Added an Alertmanager scrape target: it carried no prometheus.io/scrape annotation, so notification volume was unmeasurable — now we can verify this change worked (alertmanager_notifications_total et al.). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
127 lines
4.3 KiB
HCL
127 lines
4.3 KiB
HCL
# =============================================================================
|
|
# Daily alert digest -> #alerts Slack
|
|
# =============================================================================
|
|
# Companion to the "alert on change" routing model (alert-noise-reduction
|
|
# 2026-06-12). Warning/info alerts no longer re-notify while they stay firing
|
|
# (repeat_interval is effectively off) and criticals only re-ping every 6h, so
|
|
# Slack reflects *changes*, not steady state. This CronJob is the safety net:
|
|
# once a day it posts the full current board of firing alerts grouped by
|
|
# severity (+ what cleared in the last 24h) so the standing state is reviewed
|
|
# on a schedule, the way the #security lane is skimmed daily.
|
|
#
|
|
# Implementation: stock python:3.12-alpine running a pure-stdlib script
|
|
# (alert_digest.py, mounted from a ConfigMap). NO pip/apk at runtime — once a
|
|
# day, zero per-run package-install disk writes (the footprint that got
|
|
# status-page-pusher disabled, memory id=559). Queries the in-cluster
|
|
# Alertmanager v2 API for the current board (respects silences + inhibitions)
|
|
# and Prometheus for the resolved-in-24h line.
|
|
# =============================================================================
|
|
|
|
resource "kubernetes_config_map" "alert_digest_script" {
|
|
metadata {
|
|
name = "alert-digest-script"
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
|
}
|
|
data = {
|
|
"alert_digest.py" = file("${path.module}/alert_digest.py")
|
|
}
|
|
}
|
|
|
|
# Reuses the same Slack incoming-webhook the Alertmanager receivers post with
|
|
# (var.alertmanager_slack_api_url) — no new webhook, just a namespaced Secret so
|
|
# the URL isn't a literal in the pod spec.
|
|
resource "kubernetes_secret" "alert_digest" {
|
|
metadata {
|
|
name = "alert-digest"
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
|
}
|
|
type = "Opaque"
|
|
data = {
|
|
SLACK_WEBHOOK_URL = var.alertmanager_slack_api_url
|
|
}
|
|
}
|
|
|
|
resource "kubernetes_cron_job_v1" "alert_digest" {
|
|
metadata {
|
|
name = "alert-digest"
|
|
namespace = kubernetes_namespace.monitoring.metadata[0].name
|
|
labels = {
|
|
app = "alert-digest"
|
|
tier = var.tier
|
|
}
|
|
}
|
|
spec {
|
|
concurrency_policy = "Forbid"
|
|
failed_jobs_history_limit = 3
|
|
successful_jobs_history_limit = 3
|
|
schedule = "0 8 * * *"
|
|
timezone = "Europe/London"
|
|
starting_deadline_seconds = 600
|
|
job_template {
|
|
metadata {}
|
|
spec {
|
|
backoff_limit = 2
|
|
ttl_seconds_after_finished = 86400
|
|
template {
|
|
metadata {
|
|
labels = {
|
|
app = "alert-digest"
|
|
}
|
|
}
|
|
spec {
|
|
restart_policy = "OnFailure"
|
|
container {
|
|
name = "alert-digest"
|
|
image = "docker.io/library/python:3.12-alpine"
|
|
image_pull_policy = "IfNotPresent"
|
|
command = ["python3", "/scripts/alert_digest.py"]
|
|
env {
|
|
name = "SLACK_WEBHOOK_URL"
|
|
value_from {
|
|
secret_key_ref {
|
|
name = kubernetes_secret.alert_digest.metadata[0].name
|
|
key = "SLACK_WEBHOOK_URL"
|
|
}
|
|
}
|
|
}
|
|
env {
|
|
name = "SLACK_CHANNEL"
|
|
value = "#alerts"
|
|
}
|
|
volume_mount {
|
|
name = "script"
|
|
mount_path = "/scripts"
|
|
read_only = true
|
|
}
|
|
resources {
|
|
requests = {
|
|
cpu = "10m"
|
|
memory = "48Mi"
|
|
}
|
|
limits = {
|
|
memory = "96Mi"
|
|
}
|
|
}
|
|
}
|
|
volume {
|
|
name = "script"
|
|
config_map {
|
|
name = kubernetes_config_map.alert_digest_script.metadata[0].name
|
|
}
|
|
}
|
|
dns_config {
|
|
option {
|
|
name = "ndots"
|
|
value = "2"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
lifecycle {
|
|
# KYVERNO_LIFECYCLE_V1: Kyverno admission webhook mutates dns_config with ndots=2
|
|
ignore_changes = [spec[0].job_template[0].spec[0].template[0].spec[0].dns_config]
|
|
}
|
|
}
|