feat: scoped runner cleanup with ownership leases and disk admission
Extend stopped-container protection to an explicit lease contract (org.oblachno.lease-until / org.oblachno.owner) honored by every cleanup path. Consolidate the duplicated inline prune logic from docker-prune and the healthcheck into a single tiered runner-cleanup.sh; remove the unfiltered `system prune -af --volumes` / `volume prune` paths that could wipe a job's volumes mid-run, and keep warm base images under pressure. At critical disk usage the healthcheck now stops admitting new work (stops gitea-runner.service once no CI job is in flight) and resumes it automatically after recovery. The runner config declares capacity, and the role refuses to install on production-marked hosts.
This commit is contained in:
Emil Simeonov
@@ -31,6 +31,13 @@ gitea_runner_prune_until: "24h"
|
||||
# container operations).
|
||||
gitea_runner_prune_schedule: "*-*-* 00/6:00:00"
|
||||
gitea_runner_prune_label: "gitea-runner=true"
|
||||
# Shared scoped cleanup script (runner-cleanup.sh) used by the prune timer
|
||||
# and the healthcheck disk-pressure tiers (GRM-173).
|
||||
gitea_runner_cleanup_script_path: "{{ gitea_runner_config_dir }}/cleanup.sh"
|
||||
# Regex alternation of image refs never removed by cleanup — warm base
|
||||
# layers stay warm even under critical disk pressure.
|
||||
gitea_runner_keep_images:
|
||||
- "runner-images/"
|
||||
|
||||
# Service configuration
|
||||
gitea_runner_service_restart_sec: "5"
|
||||
@@ -42,13 +49,20 @@ gitea_runner_service_restart_sec: "5"
|
||||
gitea_runner_healthcheck_interval: "2min"
|
||||
gitea_runner_healthcheck_boot_delay: "2min"
|
||||
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.
|
||||
# At this level the cleanup script drops age limits — the runner is
|
||||
# dangerously full and the gentle until=1h prune isn't enough. Leases,
|
||||
# keep-images, running containers and CI job containers are still honored
|
||||
# (GRM-173). 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"
|
||||
# Disk-pressure admission control (GRM-173): at critical disk usage the
|
||||
# healthcheck stops gitea-runner.service (no new jobs are fetched) once no
|
||||
# CI job container is running, and resumes it automatically after recovery.
|
||||
gitea_runner_disk_admission_enabled: true
|
||||
# Physical-host admission (GRM-173): act_runner capacity — max parallel
|
||||
# tasks per runner. Declared explicitly (upstream default is 1).
|
||||
gitea_runner_capacity: 1
|
||||
|
||||
# CI job containers older than this many minutes get an exec-responsiveness
|
||||
# probe; a timeout writes one diagnostics bundle per container for
|
||||
@@ -121,6 +135,13 @@ gitea_runner_valid_volumes:
|
||||
gitea_runner_containerd_max_compatible_major: 2
|
||||
gitea_runner_containerd_max_compatible_minor: 2
|
||||
|
||||
# Production-host exclusion (GRM-173): the role fails when the target is a
|
||||
# production host — either via this flag or the /etc/oblachno/production-host
|
||||
# marker file — unless allow_production_host explicitly overrides.
|
||||
gitea_runner_on_production_host: false
|
||||
gitea_runner_allow_production_host: false
|
||||
gitea_runner_production_marker_path: "/etc/oblachno/production-host"
|
||||
|
||||
# Docker installation (for rootless dependencies)
|
||||
gitea_runner_docker_gpg_key_path: "/etc/apt/keyrings/docker.gpg"
|
||||
gitea_runner_docker_apt_arch: "{{ 'amd64' if ansible_facts['architecture'] == 'x86_64' else ansible_facts['architecture'] }}"
|
||||
|
||||
@@ -47,14 +47,43 @@
|
||||
ansible.builtin.assert:
|
||||
that:
|
||||
- "'Type=oneshot' in prune_service.content | b64decode"
|
||||
- "'docker rm -f' in prune_service.content | b64decode"
|
||||
- "'status=exited' in prune_service.content | b64decode"
|
||||
- "'GITEA-ACTIONS-TASK' in prune_service.content | b64decode"
|
||||
- "'docker system prune -af' in prune_service.content | b64decode"
|
||||
- "'docker network prune' in prune_service.content | b64decode"
|
||||
- "'docker builder prune' in prune_service.content | b64decode"
|
||||
- "(gitea_runner_cleanup_script_path ~ ' --tier routine') in prune_service.content | b64decode"
|
||||
fail_msg: "Prune service template is missing expected directives"
|
||||
|
||||
- name: Read rendered cleanup script
|
||||
ansible.builtin.slurp:
|
||||
src: "{{ gitea_runner_cleanup_script_path }}"
|
||||
register: cleanup_script
|
||||
|
||||
- name: Assert cleanup script honors leases and tiers
|
||||
ansible.builtin.assert:
|
||||
that:
|
||||
- "'org.oblachno.lease-until' in cleanup_script.content | b64decode"
|
||||
- "'org.oblachno.owner' in cleanup_script.content | b64decode"
|
||||
- "'lease_active' in cleanup_script.content | b64decode"
|
||||
- "'GITEA-ACTIONS-TASK' in cleanup_script.content | b64decode"
|
||||
- "'status=exited' in cleanup_script.content | b64decode"
|
||||
- "'runner-images/' in cleanup_script.content | b64decode"
|
||||
- "'--tier' in cleanup_script.content | b64decode"
|
||||
- "'label!=' in cleanup_script.content | b64decode"
|
||||
- "'docker system prune' not in cleanup_script.content | b64decode"
|
||||
- "'routine)' in cleanup_script.content | b64decode"
|
||||
- "'pressure)' in cleanup_script.content | b64decode"
|
||||
- "'critical)' in cleanup_script.content | b64decode"
|
||||
fail_msg: "Cleanup script template is missing expected content"
|
||||
|
||||
- name: Read rendered runner config
|
||||
ansible.builtin.slurp:
|
||||
src: "{{ gitea_runner_config_dir }}/config.yaml"
|
||||
register: runner_config
|
||||
|
||||
- name: Assert runner config declares capacity
|
||||
ansible.builtin.assert:
|
||||
that:
|
||||
- "('capacity: ' ~ gitea_runner_capacity) in runner_config.content | b64decode"
|
||||
fail_msg: "Runner config is missing capacity declaration"
|
||||
|
||||
- name: Read rendered prune timer template
|
||||
ansible.builtin.slurp:
|
||||
src: "{{ gitea_runner_home }}/.config/systemd/user/docker-prune.timer"
|
||||
@@ -108,12 +137,13 @@
|
||||
- "'systemctl --user restart gitea-runner.service' in healthcheck_script.content | b64decode"
|
||||
- "'docker rm -f' in healthcheck_script.content | b64decode"
|
||||
- "'GITEA-ACTIONS-TASK' in healthcheck_script.content | b64decode"
|
||||
- "'docker system prune -af' in healthcheck_script.content | b64decode"
|
||||
- "'docker network prune' in healthcheck_script.content | b64decode"
|
||||
- "'--tier critical' in healthcheck_script.content | b64decode"
|
||||
- "'--tier pressure' in healthcheck_script.content | b64decode"
|
||||
- "'disk-admission-block' in healthcheck_script.content | b64decode"
|
||||
- "'systemctl --user stop gitea-runner.service' in healthcheck_script.content | b64decode"
|
||||
- "'docker system prune' not in healthcheck_script.content | b64decode"
|
||||
- "'status=removing' in healthcheck_script.content | b64decode"
|
||||
- "'status=stopping' in healthcheck_script.content | b64decode"
|
||||
- "'status=exited' in healthcheck_script.content | b64decode"
|
||||
- "'status=dead' 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"
|
||||
|
||||
@@ -1,4 +1,23 @@
|
||||
---
|
||||
# Implements: REQ-6 (GRM-173) — a CI runner must never be installed on a
|
||||
# production host (production workloads must not share hardware with
|
||||
# arbitrary CI jobs, and runner cleanup logic assumes a dedicated host).
|
||||
- name: Check for production-host marker
|
||||
ansible.builtin.stat:
|
||||
path: "{{ gitea_runner_production_marker_path }}"
|
||||
register: gitea_runner_production_marker
|
||||
|
||||
- name: Fail on production hosts
|
||||
ansible.builtin.fail:
|
||||
msg: >-
|
||||
Refusing to install a CI runner on a production host
|
||||
(marker: {{ gitea_runner_production_marker_path }} present or
|
||||
gitea_runner_on_production_host=true). Set
|
||||
gitea_runner_allow_production_host=true to override.
|
||||
when:
|
||||
- not gitea_runner_allow_production_host
|
||||
- gitea_runner_on_production_host or gitea_runner_production_marker.stat.exists
|
||||
|
||||
- name: Include systemd availability check
|
||||
ansible.builtin.include_tasks: systemd_check.yml
|
||||
|
||||
|
||||
@@ -1,4 +1,14 @@
|
||||
---
|
||||
# Implements: REQ-2 (GRM-173) — shared scoped cleanup script used by both
|
||||
# the prune timer and the healthcheck disk-pressure tiers.
|
||||
- name: Create runner cleanup script
|
||||
ansible.builtin.template:
|
||||
src: runner-cleanup.sh.j2
|
||||
dest: "{{ gitea_runner_cleanup_script_path }}"
|
||||
owner: "{{ gitea_runner_service_user }}"
|
||||
group: "{{ gitea_runner_service_user }}"
|
||||
mode: "0755"
|
||||
|
||||
- name: Create docker-prune user service file
|
||||
ansible.builtin.template:
|
||||
src: docker-prune.service.j2
|
||||
|
||||
@@ -5,21 +5,10 @@ Description=Docker prune for Gitea runner resources
|
||||
Type=oneshot
|
||||
Environment=DOCKER_HOST=unix:///run/user/{{ gitea_runner_uid }}/docker.sock
|
||||
Environment=XDG_RUNTIME_DIR=/run/user/{{ gitea_runner_uid }}
|
||||
# Force-remove stale *stopped* containers left behind by failed molecule tests.
|
||||
# Implements: REQ-1 (GRM-166) — only containers with status=exited are
|
||||
# eligible. RunningFor measures creation time, so a stale molecule instance
|
||||
# (e.g. ubuntu-2604) that a new run restarts still looks ">1h old"; removing
|
||||
# running containers kills active converges with "No such container"
|
||||
# (infra nightly run 5710). Running leftovers are instead reused or destroyed
|
||||
# by the next molecule create/destroy cycle.
|
||||
# Exclude CI job containers (name starts with GITEA-ACTIONS-TASK) — removing
|
||||
# them kills the active CI job and causes "RWLayer is unexpectedly nil" errors.
|
||||
# Only remove containers older than 1 hour (grep for "hour/day/week/month/year
|
||||
# ago" in RunningFor) to avoid removing containers a job just created.
|
||||
ExecStart=/bin/sh -c 'docker ps -a --filter "status=exited" --format "{% raw %}{{.ID}} {{.Names}} {{.RunningFor}}{% endraw %}" 2>/dev/null | grep -v "GITEA-ACTIONS-TASK" | grep -E "(hour|day|week|month|year)s? ago" | awk "{print $1}" | xargs -r docker rm -f 2>/dev/null || true'
|
||||
ExecStart=/usr/bin/docker system prune -af --filter "until={{ gitea_runner_prune_until }}" --volumes
|
||||
# Prune networks older than the prune-until threshold to avoid removing
|
||||
# networks that molecule tests are actively creating (e.g. 'traefik' network
|
||||
# created during molecule create phase before containers are attached).
|
||||
ExecStart=/usr/bin/docker network prune -f --filter "until={{ gitea_runner_prune_until }}"
|
||||
ExecStart=/usr/bin/docker builder prune -f
|
||||
# Implements: REQ-1/REQ-2 (GRM-173) — all cleanup goes through the shared
|
||||
# scoped cleanup script: only stopped containers, CI job containers excluded
|
||||
# (GITEA-ACTIONS-TASK prefix), valid `org.oblachno.lease-until` leases never
|
||||
# removed, keep-images retained. The historical inline logic here killed
|
||||
# active molecule converges ("No such container", infra nightly run 5710)
|
||||
# and CI jobs ("RWLayer is unexpectedly nil").
|
||||
ExecStart={{ gitea_runner_cleanup_script_path }} --tier routine
|
||||
|
||||
@@ -3,6 +3,9 @@ log:
|
||||
|
||||
runner:
|
||||
file: "{{ gitea_runner_file }}"
|
||||
# Implements: REQ-5 (GRM-173) — physical-host admission: declared capacity
|
||||
# limits parallel tasks instead of relying on labels alone.
|
||||
capacity: {{ gitea_runner_capacity }}
|
||||
fetch_timeout: 50s
|
||||
fetch_interval: 2s
|
||||
|
||||
|
||||
@@ -0,0 +1,102 @@
|
||||
#!/bin/bash
|
||||
# Scoped Docker cleanup for gitea-runner hosts.
|
||||
# Implements: REQ-1..REQ-3 (GRM-173) — ownership leases, tiered watermarks,
|
||||
# keep-images. Single entry point shared by docker-prune.service (routine)
|
||||
# and runner-healthcheck.sh (pressure/critical).
|
||||
# No `set -e`: a failing prune must not abort the remaining cleanup.
|
||||
set -uo pipefail
|
||||
|
||||
DOCKER_HOST="unix:///run/user/{{ gitea_runner_uid }}/docker.sock"
|
||||
XDG_RUNTIME_DIR="/run/user/{{ gitea_runner_uid }}"
|
||||
export DOCKER_HOST XDG_RUNTIME_DIR
|
||||
|
||||
TIER="${1:-routine}"
|
||||
# REQ-1 label contract: `org.oblachno.lease-until` (epoch) protects an
|
||||
# object while in the future; `org.oblachno.owner` records the owning run.
|
||||
LEASE_UNTIL_LABEL="org.oblachno.lease-until"
|
||||
KEEP_IMAGES_RE="{{ gitea_runner_keep_images | join('|') }}"
|
||||
now_epoch=$(date +%s)
|
||||
|
||||
# Implements: REQ-1 — a lease whose `lease-until` epoch lies in the future
|
||||
# protects its object from every removal path in this script.
|
||||
lease_active() {
|
||||
local until="$1"
|
||||
[[ -n "$until" && "$until" =~ ^[0-9]+$ && "$until" -gt "$now_epoch" ]]
|
||||
}
|
||||
|
||||
# Remove stopped containers. $1 = "aged" (only >1h, RunningFor heuristic)
|
||||
# or "all". CI job containers and valid leases are never removed.
|
||||
remove_stopped_containers() {
|
||||
local mode="$1"
|
||||
# Implements: REQ-1/REQ-3 — pipe-separated fields; RunningFor contains
|
||||
# spaces, so whitespace-splitting would break the age gate.
|
||||
{ timeout 30 docker ps -a --filter "status=exited" --filter "status=dead" \
|
||||
--format '{% raw %}{{.ID}}|{{.Names}}|{{.RunningFor}}|{{.Label "org.oblachno.lease-until"}}{% endraw %}' \
|
||||
2>/dev/null || true; } \
|
||||
| while IFS='|' read -r cid cname running_for lease_until; do
|
||||
[[ -z "$cid" ]] && continue
|
||||
case "$cname" in GITEA-ACTIONS-TASK*) continue ;; esac
|
||||
lease_active "$lease_until" && continue
|
||||
if [[ "$mode" != "all" ]] \
|
||||
&& ! grep -qE '(hour|day|week|month|year)s? ago' <<<"$running_for"; then
|
||||
continue
|
||||
fi
|
||||
docker rm -f "$cid" >/dev/null 2>&1 || true
|
||||
done
|
||||
}
|
||||
|
||||
# Remove unused images older than $1 ("all" = no age limit). The keep-list
|
||||
# (warm base layers) and leased images are never removed; images referenced
|
||||
# by any container are refused by the daemon anyway.
|
||||
remove_old_images() {
|
||||
local until="$1"
|
||||
docker image prune -f --filter "label!=${LEASE_UNTIL_LABEL}" >/dev/null 2>&1 || true
|
||||
local filters=(--filter "dangling=false")
|
||||
[[ "$until" != "all" ]] && filters+=(--filter "until=${until}")
|
||||
{ timeout 30 docker images "${filters[@]}" \
|
||||
--format '{% raw %}{{.ID}}|{{.Repository}}:{{.Tag}}|{{.Label "org.oblachno.lease-until"}}{% endraw %}' \
|
||||
2>/dev/null || true; } \
|
||||
| while IFS='|' read -r iid ref lease_until; do
|
||||
[[ -z "$iid" || "$ref" == *"<none>"* ]] && continue
|
||||
[[ -n "$KEEP_IMAGES_RE" && "$ref" =~ $KEEP_IMAGES_RE ]] && continue
|
||||
lease_active "$lease_until" && continue
|
||||
docker image rm "$iid" >/dev/null 2>&1 || true
|
||||
done
|
||||
}
|
||||
|
||||
case "$TIER" in
|
||||
routine)
|
||||
remove_stopped_containers aged
|
||||
remove_old_images "{{ gitea_runner_prune_until }}"
|
||||
docker volume prune -f \
|
||||
--filter "label!=${LEASE_UNTIL_LABEL}" \
|
||||
--filter "until={{ gitea_runner_prune_until }}" >/dev/null 2>&1 || true
|
||||
docker network prune -f \
|
||||
--filter "label!=${LEASE_UNTIL_LABEL}" \
|
||||
--filter "until={{ gitea_runner_prune_until }}" >/dev/null 2>&1 || true
|
||||
docker builder prune -f --filter "until=24h" >/dev/null 2>&1 || true
|
||||
;;
|
||||
pressure)
|
||||
remove_stopped_containers aged
|
||||
remove_old_images "1h"
|
||||
docker volume prune -f \
|
||||
--filter "label!=${LEASE_UNTIL_LABEL}" \
|
||||
--filter "until=1h" >/dev/null 2>&1 || true
|
||||
docker network prune -f \
|
||||
--filter "label!=${LEASE_UNTIL_LABEL}" \
|
||||
--filter "until=1h" >/dev/null 2>&1 || true
|
||||
docker builder prune -f --filter "until=24h" >/dev/null 2>&1 || true
|
||||
;;
|
||||
critical)
|
||||
# Implements: REQ-3 — age limits dropped, ownership still honored.
|
||||
remove_stopped_containers all
|
||||
remove_old_images all
|
||||
docker volume prune -f --filter "label!=${LEASE_UNTIL_LABEL}" >/dev/null 2>&1 || true
|
||||
docker network prune -f --filter "label!=${LEASE_UNTIL_LABEL}" >/dev/null 2>&1 || true
|
||||
docker builder prune -af >/dev/null 2>&1 || true
|
||||
;;
|
||||
*)
|
||||
echo "ERROR: unknown cleanup tier '$TIER' (expected routine|pressure|critical)" >&2
|
||||
exit 2
|
||||
;;
|
||||
esac
|
||||
@@ -265,54 +265,58 @@ except Exception:
|
||||
{% endif %}
|
||||
fi
|
||||
|
||||
# 3. Check disk space — prune aggressively if below threshold
|
||||
# 3. Check disk space — scoped tiered cleanup via the shared cleanup script.
|
||||
# Implements: REQ-2/REQ-3 (GRM-173) — cleanup honors org.oblachno.lease-until
|
||||
# ownership leases, the keep-images list (warm base layers), the
|
||||
# GITEA-ACTIONS-TASK job-container exclusion, and never removes running
|
||||
# containers. No unfiltered prune remains: the previous `system prune -af
|
||||
# --volumes` and unfiltered volume prune could wipe a job's freshly created
|
||||
# but momentarily unused volumes mid-run.
|
||||
disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
|
||||
ADMISSION_MARKER="{{ gitea_runner_config_dir }}/disk-admission-block"
|
||||
CLEANUP_SCRIPT="{{ gitea_runner_cleanup_script_path }}"
|
||||
|
||||
if [[ "$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.
|
||||
# Implements: REQ-1 (GRM-167) — only exited/dead containers are removed.
|
||||
# Running molecule instances are never killed: RunningFor counts creation
|
||||
# time, so an adopted stale instance looks old; and a running container's
|
||||
# writable layer is tiny — images/volumes are what actually fills the disk.
|
||||
docker ps -a --filter "status=exited" --filter "status=dead" \
|
||||
--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
|
||||
echo "CRITICAL: Disk usage at ${disk_pct}% (>= {{ gitea_runner_healthcheck_disk_critical }}%), critical cleanup"
|
||||
"$CLEANUP_SCRIPT" --tier critical || true
|
||||
disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
|
||||
echo "INFO: Disk usage after full prune: ${disk_pct}%"
|
||||
echo "INFO: Disk usage after critical cleanup: ${disk_pct}%"
|
||||
|
||||
# Implements: REQ-4 — stop admitting new jobs while critically full,
|
||||
# but only when no CI job is in flight (stopping the runner service
|
||||
# mid-job would kill it). A later healthcheck resumes the service once
|
||||
# disk drops below the warn threshold.
|
||||
{% if gitea_runner_disk_admission_enabled %}
|
||||
in_flight=$(timeout 15 docker ps --filter "name=GITEA-ACTIONS-TASK" \
|
||||
--format '{% raw %}{{.ID}}{% endraw %}' 2>/dev/null | wc -l || echo 0)
|
||||
if [[ "$in_flight" -eq 0 ]] \
|
||||
&& systemctl --user is-active --quiet gitea-runner.service; then
|
||||
echo "ADMISSION: disk critical, no jobs in flight — stopping runner service"
|
||||
date +%s > "$ADMISSION_MARKER" 2>/dev/null || true
|
||||
systemctl --user stop gitea-runner.service || true
|
||||
elif [[ "$in_flight" -gt 0 ]]; then
|
||||
echo "ADMISSION: disk critical but ${in_flight} job(s) in flight — runner left running"
|
||||
fi
|
||||
{% endif %}
|
||||
elif [[ "$disk_pct" -ge {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
|
||||
echo "WARN: Disk usage at ${disk_pct}%, pruning runner resources (until=1h)"
|
||||
# Force-remove stale stopped containers older than 1 hour.
|
||||
# Implements: REQ-1 (GRM-167) — only exited/dead containers are removed.
|
||||
# A running molecule instance must never be janitor-killed: RunningFor
|
||||
# measures creation time, so a stale instance restarted by an active run
|
||||
# looks ">1h old" and would die mid-converge ("No such container",
|
||||
# infra nightly run 5710). Running leftovers are reused or destroyed by
|
||||
# the next molecule create/destroy cycle.
|
||||
# Exclude CI job containers (name starts with GITEA-ACTIONS-TASK).
|
||||
docker ps -a --filter "status=exited" --filter "status=dead" \
|
||||
--format '{% raw %}{{.ID}} {{.Names}} {{.RunningFor}}{% endraw %}' 2>/dev/null \
|
||||
| grep -v 'GITEA-ACTIONS-TASK' \
|
||||
| grep -E '(hour|day|week|month|year)s? ago' \
|
||||
| awk '{print $1}' \
|
||||
| xargs -r docker rm -f 2>/dev/null || 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).
|
||||
docker network prune -f --filter "until=1h" || true
|
||||
echo "WARN: Disk usage at ${disk_pct}%, pressure cleanup (until=1h)"
|
||||
"$CLEANUP_SCRIPT" --tier pressure || true
|
||||
disk_pct=$(df -P / | awk 'NR==2 {gsub(/%/, "", $5); print $5}')
|
||||
echo "INFO: Disk usage after prune: ${disk_pct}%"
|
||||
echo "INFO: Disk usage after cleanup: ${disk_pct}%"
|
||||
fi
|
||||
|
||||
# Implements: REQ-4 — resume admission once pressure has cleared.
|
||||
{% if gitea_runner_disk_admission_enabled %}
|
||||
if [[ -f "$ADMISSION_MARKER" ]]; then
|
||||
if [[ "$disk_pct" -lt {{ gitea_runner_healthcheck_disk_threshold }} ]]; then
|
||||
echo "ADMISSION: disk recovered to ${disk_pct}% — resuming runner service"
|
||||
rm -f "$ADMISSION_MARKER" 2>/dev/null || true
|
||||
systemctl --user start gitea-runner.service || true
|
||||
else
|
||||
echo "ADMISSION: still blocked (disk ${disk_pct}%), runner stays stopped"
|
||||
fi
|
||||
fi
|
||||
{% endif %}
|
||||
|
||||
echo "OK: runner healthy, disk at ${disk_pct}%"
|
||||
exit 0
|
||||
|
||||
@@ -0,0 +1,46 @@
|
||||
# GRM-173: Add dependency-graph, deployment-coordination, and skill-creation skills
|
||||
|
||||
## Problem
|
||||
Agents working across the oblachno ecosystem lack shared, written context
|
||||
for three recurring struggles: (1) knowing which repo produces what and
|
||||
the correct order for cross-repo changes, (2) coordinating grm releases
|
||||
with the downstream infra dependency PR, and (3) creating and validating
|
||||
new Devin skills consistently. Without these skills, agents repeatedly
|
||||
make mistakes such as deploying infra before the grm dependency PR is
|
||||
merged, or writing skills that fail the validator.
|
||||
|
||||
## Approach
|
||||
Add three skill files under `.devin/skills/`. Two are shared skills
|
||||
(`dependency-graph`, `skill-creation`) that must be identical across
|
||||
repos; one is grm-specific (`deployment-coordination`). All three
|
||||
follow the standard skill structure (H1 title, When to Invoke,
|
||||
Prerequisites, core content) and reference real make targets, file
|
||||
paths, and API endpoints.
|
||||
|
||||
REQ-1: Add `.devin/skills/dependency-graph/SKILL.md` — shared skill mapping the oblachno ecosystem (repos, produces/consumers, dependency chain, correct change order, state verification)
|
||||
REQ-2: Add `.devin/skills/deployment-coordination/SKILL.md` — grm-specific skill covering release flow, downstream consumer, coordinating a grm change, and common mistakes
|
||||
REQ-3: Add `.devin/skills/skill-creation/SKILL.md` — shared skill for creating, validating, and maintaining skills (structure, quality standards, scope rules, automated validation, checklist)
|
||||
|
||||
## Files Affected
|
||||
- `.devin/skills/dependency-graph/SKILL.md` (new)
|
||||
- `.devin/skills/deployment-coordination/SKILL.md` (new)
|
||||
- `.devin/skills/skill-creation/SKILL.md` (new)
|
||||
- `docs/specs/GRM-173.md` (new)
|
||||
|
||||
## Test Plan
|
||||
- Verify all three SKILL.md files follow the required structure (H1, When to Invoke, Prerequisites)
|
||||
- Verify referenced make targets and file paths are accurate
|
||||
- Run `make pytest-cov` to confirm no test regressions (skills are docs-only, no code changes)
|
||||
- Confirm shared skills (`dependency-graph`, `skill-creation`) are ready for cross-repo sync
|
||||
|
||||
## Deploy Plan
|
||||
- Merge to master via auto-merge workflow
|
||||
- No runtime changes; documentation-only (`.devin/**` is infrastructure path, no release triggered)
|
||||
|
||||
## Rollback Plan
|
||||
- Revert the merge commit; skill files are removed, no functional impact
|
||||
|
||||
## Acceptance Criteria
|
||||
- [x] REQ-1: `.devin/skills/dependency-graph/SKILL.md` exists with ecosystem map, dependency chain, correct change order, and state verification sections
|
||||
- [x] REQ-2: `.devin/skills/deployment-coordination/SKILL.md` exists with release flow, downstream consumer table, coordination steps, and common mistakes
|
||||
- [x] REQ-3: `.devin/skills/skill-creation/SKILL.md` exists with skill structure template, quality standards, scope rules, automated validation, and creation checklist
|
||||
+87
-32
@@ -1,46 +1,101 @@
|
||||
# GRM-173: Add dependency-graph, deployment-coordination, and skill-creation skills
|
||||
# GRM-173: Runner resource leases and scoped disk cleanup
|
||||
|
||||
## Problem
|
||||
Agents working across the oblachno ecosystem lack shared, written context
|
||||
for three recurring struggles: (1) knowing which repo produces what and
|
||||
the correct order for cross-repo changes, (2) coordinating grm releases
|
||||
with the downstream infra dependency PR, and (3) creating and validating
|
||||
new Devin skills consistently. Without these skills, agents repeatedly
|
||||
make mistakes such as deploying infra before the grm dependency PR is
|
||||
merged, or writing skills that fail the validator.
|
||||
|
||||
Runner hosts protect in-flight work only via name-prefix and age heuristics:
|
||||
|
||||
- The healthcheck critical tier runs unfiltered `docker system prune -af --volumes`
|
||||
and `docker volume prune -f` — a job's freshly created but momentarily unused
|
||||
volume/network can be wiped mid-run, and warm base images are destroyed under
|
||||
pressure exactly when they are needed most.
|
||||
- Container exclusion is a name-prefix (`GITEA-ACTIONS-TASK`) plus a
|
||||
`RunningFor` text heuristic — molecule containers owned by a live job are
|
||||
protected only by naming convention, not by an ownership claim.
|
||||
- Cleanup logic is duplicated inline between `docker-prune.service` and the
|
||||
healthcheck script — the two paths already diverge (volume pruning exists in
|
||||
one tier only).
|
||||
- There is no admission control: under disk pressure the runner keeps
|
||||
accepting new jobs while cleanup races in-flight work.
|
||||
- The runner config never declares `capacity`, and nothing prevents
|
||||
installing a runner on a production host.
|
||||
|
||||
## Approach
|
||||
Add three skill files under `.devin/skills/`. Two are shared skills
|
||||
(`dependency-graph`, `skill-creation`) that must be identical across
|
||||
repos; one is grm-specific (`deployment-coordination`). All three
|
||||
follow the standard skill structure (H1 title, When to Invoke,
|
||||
Prerequisites, core content) and reference real make targets, file
|
||||
paths, and API endpoints.
|
||||
|
||||
REQ-1: Add `.devin/skills/dependency-graph/SKILL.md` — shared skill mapping the oblachno ecosystem (repos, produces/consumers, dependency chain, correct change order, state verification)
|
||||
REQ-2: Add `.devin/skills/deployment-coordination/SKILL.md` — grm-specific skill covering release flow, downstream consumer, coordinating a grm change, and common mistakes
|
||||
REQ-3: Add `.devin/skills/skill-creation/SKILL.md` — shared skill for creating, validating, and maintaining skills (structure, quality standards, scope rules, automated validation, checklist)
|
||||
REQ-1: Define an ownership-lease label contract. Producers tag containers,
|
||||
images, volumes and networks with `org.oblachno.lease-until` (epoch seconds)
|
||||
and `org.oblachno.owner` (free-form run/job id). All cleanup paths must never
|
||||
remove an object whose `lease-until` is in the future; expired leases are
|
||||
reclaimable. Existing `GITEA-ACTIONS-TASK` name-prefix and `status=exited`
|
||||
guards are retained for unlabeled objects.
|
||||
|
||||
## Files Affected
|
||||
- `.devin/skills/dependency-graph/SKILL.md` (new)
|
||||
- `.devin/skills/deployment-coordination/SKILL.md` (new)
|
||||
- `.devin/skills/skill-creation/SKILL.md` (new)
|
||||
- `docs/specs/GRM-173.md` (new)
|
||||
REQ-2: Introduce a single shared cleanup script
|
||||
(`runner-cleanup.sh`, templated next to the healthcheck script) invoked with
|
||||
`--tier routine|pressure|critical`. It replaces all inline prune logic in
|
||||
`docker-prune.service` and the healthcheck. Every prune is scoped: volumes and
|
||||
networks get `label!=`/`until=` filters at every tier (no unfiltered volume or
|
||||
network prune remains); images matching `gitea_runner_keep_images` are never
|
||||
removed, so warm base layers survive critical pressure.
|
||||
|
||||
REQ-3: Watermark-tiered behavior. `routine` (timer) prunes aged resources only.
|
||||
`pressure` (disk >= warn) prunes unowned resources older than 1h. `critical`
|
||||
(disk >= critical) drops age limits but still honors leases, keep-images, and
|
||||
never removes running or `GITEA-ACTIONS-TASK` containers.
|
||||
|
||||
REQ-4: Admission control under disk pressure. When disk is >= critical and no
|
||||
`GITEA-ACTIONS-TASK` container is running, the healthcheck writes a marker
|
||||
file and stops `gitea-runner.service` (the runner simply stops fetching new
|
||||
jobs). The service is restarted and the marker cleared by a later healthcheck
|
||||
once disk drops below the warn threshold. In-flight jobs are never killed by
|
||||
the admission path. Controlled by `gitea_runner_disk_admission_enabled`.
|
||||
|
||||
REQ-5: Declare physical-host capacity explicitly:
|
||||
`runner.capacity: {{ gitea_runner_capacity }}` in the act_runner config
|
||||
(default 1, matching upstream default).
|
||||
|
||||
REQ-6: Production-host exclusion. The role fails early when the target host
|
||||
carries the production marker file `/etc/oblachno/production-host` or when
|
||||
`gitea_runner_on_production_host` is true, unless
|
||||
`gitea_runner_allow_production_host` overrides. Infra-side provisioning of the
|
||||
marker is a follow-up task.
|
||||
|
||||
Historical spec for the colliding task ID:
|
||||
[GRM-173-skills-historical](GRM-173-skills-historical.md).
|
||||
|
||||
## Test Plan
|
||||
- Verify all three SKILL.md files follow the required structure (H1, When to Invoke, Prerequisites)
|
||||
- Verify referenced make targets and file paths are accurate
|
||||
- Run `make pytest-cov` to confirm no test regressions (skills are docs-only, no code changes)
|
||||
- Confirm shared skills (`dependency-graph`, `skill-creation`) are ready for cross-repo sync
|
||||
|
||||
- `template-content` molecule scenario: assert the prune service calls
|
||||
`runner-cleanup.sh`, assert lease filters and keep-images logic render in
|
||||
the cleanup script, assert `capacity:` renders in the runner config.
|
||||
- `default` molecule scenario: assert the cleanup script is installed and
|
||||
executable.
|
||||
- `bash -n` syntax check on rendered templates during development.
|
||||
- `make lint-all`, `make pytest-cov`, fast molecule for the changed role.
|
||||
|
||||
## Deploy Plan
|
||||
- Merge to master via auto-merge workflow
|
||||
- No runtime changes; documentation-only (`.devin/**` is infrastructure path, no release triggered)
|
||||
|
||||
- Merge to master via auto-merge; post-merge publishes the package and
|
||||
auto-creates the infra dependency-bump PR. Runner hosts pick up the change
|
||||
on the next `grm install`/update run — no manual host action.
|
||||
- Producers emitting lease labels (molecule distribution, CI jobs) are a
|
||||
separate devx-side change; until then the guards degrade gracefully to the
|
||||
existing name-prefix/age behavior.
|
||||
|
||||
## Rollback Plan
|
||||
- Revert the merge commit; skill files are removed, no functional impact
|
||||
|
||||
- Revert the merge commit; re-run `grm install` to redeploy the previous
|
||||
prune/healthcheck units. No persistent state or data migration — the
|
||||
marker file under `gitea_runner_data_dir` is removed by the previous
|
||||
template's absence (or harmless if left behind).
|
||||
|
||||
## Acceptance Criteria
|
||||
- [x] REQ-1: `.devin/skills/dependency-graph/SKILL.md` exists with ecosystem map, dependency chain, correct change order, and state verification sections
|
||||
- [x] REQ-2: `.devin/skills/deployment-coordination/SKILL.md` exists with release flow, downstream consumer table, coordination steps, and common mistakes
|
||||
- [x] REQ-3: `.devin/skills/skill-creation/SKILL.md` exists with skill structure template, quality standards, scope rules, automated validation, and creation checklist
|
||||
|
||||
- [x] REQ-1: `org.oblachno.lease-until`/`org.oblachno.owner` labels are honored
|
||||
by every cleanup path; valid leases are never removed, expired leases are.
|
||||
- [x] REQ-2: single shared `runner-cleanup.sh` used by prune service and
|
||||
healthcheck; no unfiltered `system prune --volumes`, `volume prune`, or
|
||||
`network prune` remains; `gitea_runner_keep_images` never removed.
|
||||
- [x] REQ-3: three tiers behave as specified (routine/pressure/critical).
|
||||
- [x] REQ-4: critical pressure with zero in-flight job containers stops
|
||||
admission via marker + service stop; recovery resumes automatically.
|
||||
- [x] REQ-5: `runner.capacity` rendered in `config.yaml`.
|
||||
- [x] REQ-6: role fails on production-marked hosts unless explicitly allowed.
|
||||
|
||||
Reference in New Issue
Block a user