Files
grm/ansible/roles/gitea_runner/templates/runner-cleanup.sh.j2
T

126 lines
5.4 KiB
Django/Jinja

#!/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
# REQ-1 label contract: `org.oblachno.lease-until` (epoch) protects an object
# while in the future; `org.oblachno.owner` records the owning run.
TIER="${1:-routine}"
LEASE_UNTIL_LABEL="org.oblachno.lease-until"
KEEP_IMAGES_RE="{{ gitea_runner_keep_images | join('|') }}"
now_epoch=$(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. `docker images` has no
# label formatter, so the lease is checked via inspect per candidate.
remove_old_images() {
local until="$1"
docker image prune -f >/dev/null 2>&1 || true
local filters=(--filter "dangling=false")
[[ "$until" != "all" ]] && filters+=(--filter "until=${until}")
{ timeout 30 docker images "${filters[@]}" \
--format '{% raw %}{{.ID}}|{{.Repository}}:{{.Tag}}{% endraw %}' \
2>/dev/null || true; } \
| while IFS='|' read -r iid ref; do
[[ -z "$iid" || "$ref" == *"<none>"* ]] && continue
[[ -n "$KEEP_IMAGES_RE" && "$ref" =~ $KEEP_IMAGES_RE ]] && continue
local lease_until
lease_until=$(docker image inspect "$iid" \
--format '{% raw %}{{index .Config.Labels "org.oblachno.lease-until"}}{% endraw %}' \
2>/dev/null || true)
lease_active "$lease_until" && continue
docker image rm "$iid" >/dev/null 2>&1 || true
done
}
# Reclaim volumes/networks whose lease expired. The prune filters below
# skip every leased object (label!=); this pass removes the expired ones.
reclaim_expired_leases() {
timeout 20 docker volume ls -q --filter "label=${LEASE_UNTIL_LABEL}" 2>/dev/null \
| while read -r vol; do
lease_until=$(docker volume inspect "$vol" \
--format '{% raw %}{{index .Labels "org.oblachno.lease-until"}}{% endraw %}' \
2>/dev/null || true)
lease_active "$lease_until" || docker volume rm "$vol" >/dev/null 2>&1 || true
done
timeout 20 docker network ls -q --filter "label=${LEASE_UNTIL_LABEL}" 2>/dev/null \
| while read -r net; do
lease_until=$(docker network inspect "$net" \
--format '{% raw %}{{index .Labels "org.oblachno.lease-until"}}{% endraw %}' \
2>/dev/null || true)
lease_active "$lease_until" || docker network rm "$net" >/dev/null 2>&1 || true
done
}
# Anonymous volumes only at routine/pressure tiers — a named volume may
# belong to a job between create/attach steps. Critical removes all unused.
prune_volumes_networks() {
local vol_all="$1" net_until="$2"
docker volume prune ${vol_all:+$vol_all} -f --filter "label!=${LEASE_UNTIL_LABEL}" >/dev/null 2>&1 || true
docker network prune -f --filter "label!=${LEASE_UNTIL_LABEL}" ${net_until:+--filter until=${net_until}} >/dev/null 2>&1 || true
}
case "$TIER" in
routine)
remove_stopped_containers aged
remove_old_images "{{ gitea_runner_prune_until }}"
prune_volumes_networks "" "{{ gitea_runner_prune_until }}"
docker builder prune -f --filter "until=24h" >/dev/null 2>&1 || true
;;
pressure)
remove_stopped_containers aged
remove_old_images "1h"
prune_volumes_networks "" "1h"
docker builder prune -f --filter "until=24h" >/dev/null 2>&1 || true
;;
critical)
# Implements: REQ-3 — age limits dropped, ownership still honored.
remove_stopped_containers all
remove_old_images all
prune_volumes_networks "-a" ""
docker builder prune -af >/dev/null 2>&1 || true
;;
*)
echo "ERROR: unknown cleanup tier '$TIER' (expected routine|pressure|critical)" >&2
exit 2
;;
esac
reclaim_expired_leases