GRM-159: feat(healthcheck): add two-tier disk prune with critical threshold
Post-merge / detect-and-configure (push) Successful in 1m38s
Post-merge / release-and-maintain (push) Successful in 2m26s

Co-authored-by: emil User <emil.simeonov@tutanota.com>
This commit was merged in pull request #248.
This commit is contained in:
2026-08-09 11:12:37 +00:00
committed by emo
parent e7b2d4e6af
commit 2ffedaa793
7 changed files with 77 additions and 19 deletions
+7 -1
View File
@@ -41,7 +41,13 @@ gitea_runner_service_restart_sec: "5"
# jobs in the window between healthcheck runs.
gitea_runner_healthcheck_interval: "2min"
gitea_runner_healthcheck_boot_delay: "2min"
gitea_runner_healthcheck_disk_threshold: 75
gitea_runner_healthcheck_disk_threshold: 70
# When disk reaches this level, prune EVERYTHING (no until-filter) — the
# runner is dangerously full and the gentle until=1h prune isn't enough.
# This removes all stopped containers and unused images regardless of age.
# At 75%+, molecule containers fail with "container is not running" because
# overlay2 runs out of space under parallel DinD load.
gitea_runner_healthcheck_disk_critical: 75
gitea_runner_healthcheck_script_path: "{{ gitea_runner_config_dir }}/healthcheck.sh"
# Auto-recovery: when the healthcheck detects an unregistered runner, it
@@ -112,4 +112,5 @@
- "'status=removing' in healthcheck_script.content | b64decode"
- "'status=stopping' in healthcheck_script.content | b64decode"
- "gitea_runner_healthcheck_disk_threshold | string in healthcheck_script.content | b64decode"
- "gitea_runner_healthcheck_disk_critical | string in healthcheck_script.content | b64decode"
fail_msg: "Healthcheck script template is missing expected content"
@@ -223,8 +223,23 @@ fi
# 3. Check disk space — prune aggressively if below threshold
disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
echo "WARN: Disk usage at ${disk_pct}%, pruning all runner resources"
if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_critical }} ]]; then
echo "CRITICAL: Disk usage at ${disk_pct}% (>= {{ gitea_runner_healthcheck_disk_critical }}%), full prune"
# Critical level: remove ALL stopped containers (no age filter) and ALL
# unused images/volumes. The until=1h gentle prune is insufficient here.
# Stop+rm stale non-CI containers regardless of age (failed molecule tests
# from the last 59 minutes also consume disk).
docker ps -a --format '{% raw %}{{.ID}} {{.Names}}{% endraw %}' 2>/dev/null \
| grep -v 'GITEA-ACTIONS-TASK' \
| awk '{print $1}' \
| xargs -r docker rm -f 2>/dev/null || true
docker system prune -af --volumes || true
docker network prune -f || true
docker builder prune -af || true
disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
echo "INFO: Disk usage after full prune: ${disk_pct}%"
elif [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
echo "WARN: Disk usage at ${disk_pct}%, pruning runner resources (until=1h)"
# Force-remove stale containers (including running ones from failed molecule tests)
# that are older than 1 hour. "docker container prune -f" only removes stopped
# containers, so running containers from crashed CI jobs accumulate and consume
@@ -236,7 +251,11 @@ if [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
| grep -E '(hour|day|week|month|year)s? ago' \
| awk '{print $1}' \
| xargs -r docker rm -f 2>/dev/null || true
docker system prune -af --filter "until=1h" --volumes || true
# Prune images and containers older than 1h (until filter is NOT
# supported with --volumes, so prune volumes separately without a filter).
docker image prune -af --filter "until=1h" 2>/dev/null || true
docker container prune -f --filter "until=1h" 2>/dev/null || true
docker volume prune -f 2>/dev/null || true
# Prune networks older than 1 hour to avoid removing networks that
# molecule tests are actively creating (e.g. 'traefik' network created
# during molecule create phase before containers are attached).