viktor/infra
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

cluster-health: helm check #18 catches pending/failed releases (helm list -a)
All checks were successful
ci/woodpecker/push/default Pipeline was successful
Details

Browse source 
check_helm_releases used `helm list` without -a, which HIDES pending-upgrade and
failed releases — so on 2026-06-16 check #18 reported "All deployed" while the
prometheus release sat in pending-upgrade for ~4 days, silently blocking every
monitoring terragrunt apply (frozen alert/rule config). Add -a to surface them
and flag pending-* (FAIL, blocks applies) + failed (WARN); deployed/uninstalled/
superseded stay green.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
Viktor Barzin 2026-06-16 15:39:06 +00:00
parent e74f4208f5
commit 044444d328
1 changed files with 9 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

13
scripts/cluster_healthcheck.sh
View file

@ -1093,7 +1093,7 @@ check_helm_releases() {
section 18 "Helm Release Health" section 18 "Helm Release Health"
local releases detail="" had_issue=false status="PASS" local releases detail="" had_issue=false status="PASS"
releases=$(helm list -A --kubeconfig "$KUBECONFIG_PATH" -o json 2>/dev/null) || { releases=$(helm list -A -a --kubeconfig "$KUBECONFIG_PATH" -o json 2>/dev/null) || {
[[ "$QUIET" == true ]] && section_always 18 "Helm Release Health" [[ "$QUIET" == true ]] && section_always 18 "Helm Release Health"
warn "Cannot list Helm releases" warn "Cannot list Helm releases"
json_add "helm_releases" "WARN" "Cannot list" json_add "helm_releases" "WARN" "Cannot list"
@ -1108,9 +1108,14 @@ for r in data:
name = r.get("name", "?") name = r.get("name", "?")
ns = r.get("namespace", "?") ns = r.get("namespace", "?")
st = r.get("status", "unknown") st = r.get("status", "unknown")
if st != "deployed": # helm list -a (above) surfaces pending-*/failed releases that plain
level = "FAIL" if st.startswith("pending") else "WARN" # `helm list` HIDES; a stuck pending-upgrade silently blocks every
print(f"{level}:{ns}/{name}:{st}") # terragrunt apply of the stack (2026-06-16 prometheus incident, ~4 days
# of frozen monitoring config). Ignore deployed/uninstalled/superseded.
if st.startswith("pending"):
print(f"FAIL:{ns}/{name}:{st}")
elif st == "failed":
print(f"WARN:{ns}/{name}:{st}")
' 2>/dev/null) || true ' 2>/dev/null) || true
if [[ -z "$bad_releases" ]]; then if [[ -z "$bad_releases" ]]; then