Files
gitea/rootfs/usr/local/bin/start-runners
T
jason 6a3a9bde14
gitea / release-gitea (push) Failing after 48s
🚀 Enable shared act_runner cache-server 🚀
Turned on the act_runner Actions cache instead of leaving it disabled.
The standalone `cache-server` process was already being launched
unconditionally by zz-act_runner.sh but had no `external_secret`, so it
was refusing to start (the binary requires a non-empty secret even
though its own `cache.enabled` field is unused). Wired a shared,
randomly generated secret through the existing REPLACE_* templating
pattern so the "gitea" runner, the cache-server, and the extra
runner-N daemons spawned by start-runners all share one cache backend.

- rootfs/tmp/etc/act_runner/default_config.yaml: cache.enabled: true;
  added external_server (pointed at the local cache-server) and
  external_secret placeholders
- rootfs/tmp/etc/act_runner/cache_server.yaml: cache.enabled: true;
  added external_secret placeholder (required for the binary to start)
- rootfs/usr/local/etc/docker/init.d/zz-act_runner.sh: added
  __gen_cache_secret() (mirrors __gen_auth_token's persisted-token
  pattern, stored at $CONF_DIR/tokens/cache_secret); substitutes
  REPLACE_RUNNER_CACHE_SECRET into both the runner config and the
  cache-server config; exports RUNNER_CACHE_HOST/PORT/SECRET for
  start-runners; bumped version stamp
- rootfs/usr/local/bin/start-runners: generates a shared
  runners-cache.yaml from the exported cache env vars and passes
  --config to both `act_runner register` and `act_runner daemon` for
  every runner-N instance, so they use the same external cache server
  instead of an unshared per-process local cache
- TODO.AI.md: logged pre-existing script-lint findings (missing `--`
  before grep queries throughout zz-act_runner.sh, a UUOC in
  start-runners, an unpinned/stale docker.yaml CI workflow, and
  forbidden OCI labels in the Dockerfile) surfaced incidentally by the
  lint pass for this change but out of scope for it
2026-08-03 11:57:10 -04:00

122 lines
5.9 KiB
Bash
Executable File

#!/usr/bin/env bash
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
set -e
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
trap 'retVal=$?; echo "❌ Fatal error occurred: Exit code $retVal at line $LINENO in command: $BASH_COMMAND"; kill -TERM 1' ERR
trap 'retVal=$?;if [ "$SERVICE_IS_RUNNING" != "yes" ] && [ -f "$SERVICE_PID_FILE" ]; then rm -Rf "$SERVICE_PID_FILE"; fi;exit $retVal' SIGINT SIGTERM SIGPWR
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Function to __log messages with timestamp
__log() { echo "[$(date '+%Y-%m-%d %H:%M:%S')] $1" >>"$RUNNERS_LOG_DIR/runners" 2>&1; }
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Function to cleanup child processes on exit
__cleanup() {
__log "Shutting down runners..."
kill $(jobs -p) 2>/dev/null || true
wait
__log "All runners stopped"
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Set up signal handling
trap __cleanup SIGTERM SIGINT
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Validate required environment variables
if [ -n "$SERVER_ADDRESS" ]; then
if ! echo "$SERVER_ADDRESS" | grep -q '://'; then
SERVER_ADDRESS="http://$SERVER_ADDRESS"
fi
else
SERVER_ADDRESS=http://$HOSTNAME
fi
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
if [ -z "$SERVER_TOKEN" ]; then
__log "ERROR: SERVER_TOKEN environment variable is required"
exit 1
fi
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
RUNNER_LABELS="${RUNNER_LABELS:-linux:host,node14:docker://node:14,node16:docker://node:16,node18:docker://node:18,node20:docker://node:20,node22:docker://node:22,node:docker://node:latest,perl:docker://perl:latest,ruby:docker://ruby:latest,python:docker://python:latest,python3:docker://python:latest,php7:docker://casjaysdevdocker/php:7,php8:docker://casjaysdevdocker/php:8,php:docker://casjaysdevdocker/php:latest,alpine:docker://casjaysdev/alpine:latest,debian:docker://casjaysdev/debian:latest,ubuntu:docker://casjaysdev/ubuntu:latest,rhel:docker://casjaysdev/almalinux:latest,redhat:docker://casjaysdev/almalinux:latest,almalinux:docker://casjaysdev/almalinux:latest,act_runner:docker://catthehacker/ubuntu:full-latest,ubuntu-latest:docker://catthehacker/ubuntu:full-latest}"
# Determine number of runners to start
RUNNERS_START=${RUNNERS_START:-1}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Validate RUNNERS_START is a positive integer
if ! [[ "$RUNNERS_START" =~ ^[0-9]+$ ]] || [ "$RUNNERS_START" -lt 1 ]; then
__log "WARNING: Invalid RUNNERS_START value '$RUNNERS_START', defaulting to 1"
RUNNERS_START=1
fi
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
__log "Starting $RUNNERS_START act_runner instance(s)"
__log "Server Address: $SERVER_ADDRESS"
__log "Runner Name Prefix: ${RUNNER_NAME_PREFIX:-runner}"
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Shared cache config so runner-N instances use the same cache-server
# started by zz-act_runner.sh instead of an unshared per-process cache.
RUNNERS_CACHE_CONFIG=""
if [ -n "$RUNNER_CACHE_HOST" ] && [ -n "$RUNNER_CACHE_PORT" ] && [ -n "$RUNNER_CACHE_SECRET" ]; then
RUNNERS_CACHE_CONFIG="/config/act_runner/runners-cache.yaml"
cat <<EOF >"$RUNNERS_CACHE_CONFIG"
cache:
enabled: true
external_server: 'http://${RUNNER_CACHE_HOST}:${RUNNER_CACHE_PORT}/'
external_secret: '${RUNNER_CACHE_SECRET}'
EOF
fi
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Register a single runner synchronously (no daemon start)
__register_runner() {
local runner_id=$1
local runner_name="${RUNNER_NAME_PREFIX:-runner}-${runner_id}"
local runner_dir="/config/act_runner/reg/${runner_name}"
local config_args=()
mkdir -p "$runner_dir"
[ -d "$runner_dir" ] && cd "$runner_dir" || return 1
[ -n "$RUNNERS_CACHE_CONFIG" ] && config_args=(--config "$RUNNERS_CACHE_CONFIG")
if [ ! -f "$runner_dir/.runner" ]; then
__log "Registering runner: $runner_name (ID: $runner_id)"
act_runner register "${config_args[@]}" --instance "$SERVER_ADDRESS" --token "$SERVER_TOKEN" --name "$runner_name" --labels "$RUNNER_LABELS" --no-interactive
if [ $? -ne 0 ]; then
__log "ERROR: Failed to register runner $runner_name"
return 1
fi
fi
__log "Runner $runner_name registered"
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Start daemon for a single runner (called in background after all are registered)
__start_runner_daemon() {
local runner_id=$1
local runner_name="${RUNNER_NAME_PREFIX:-runner}-${runner_id}"
local runner_dir="/config/act_runner/reg/${runner_name}"
local config_args=()
[ -d "$runner_dir" ] && cd "$runner_dir" || return 1
[ -n "$RUNNERS_CACHE_CONFIG" ] && config_args=(--config "$RUNNERS_CACHE_CONFIG")
__log "Starting daemon for runner: $runner_name"
exec act_runner daemon "${config_args[@]}"
}
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Phase 1: register all runners sequentially so IDs are assigned in order
for i in $(seq 1 $RUNNERS_START); do
__register_runner "$i" || { __log "Aborting: registration failed for runner-$i"; exit 1; }
done
unset i
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Phase 2: start all daemons in parallel
for i in $(seq 1 $RUNNERS_START); do
(__start_runner_daemon "$i") &
done
unset i
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
RUNNERS_ID="$(jobs -p | tr '\n' ' ')"
if [ -n "$RUNNERS_ID" ]; then
__log "All $RUNNERS_START runners started successfully"
__log "Process IDs: $RUNNERS_ID"
printf 'All %s runners started successfully: %s\n' "$RUNNERS_START" "$RUNNERS_ID"
else
__log "The runners have failed to start"
printf '%s\n' "The runners have failed to start"
fi
# - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
# Wait for all background processes
wait