#!/usr/bin/env bash # Shared contract: one JSON object per run in /var/lib/vps-health/latest.json. # Status values: ok, warning, critical, unknown. Exit codes: 0 healthy/warning, # 2 critical, 3 unknown. Check detail must never include secret values. set -uo pipefail RESULT_DIR='{{ healthcheck_state_dir }}' LOG_DIR='{{ healthcheck_log_dir }}' HOST_NAME="$(hostname -f 2>/dev/null || hostname)" CHECK_NAME='{{ healthcheck_profile }}' STATUS=ok EXIT_CODE=0 DETAILS=() record() { local severity="$1" message="$2" DETAILS+=("${severity}:${message}") case "$severity" in critical) STATUS=critical; EXIT_CODE=2 ;; unknown) [[ "$STATUS" != critical ]] && STATUS=unknown; [[ "$EXIT_CODE" -eq 0 ]] && EXIT_CODE=3 ;; warning) [[ "$STATUS" == ok ]] && STATUS=warning ;; esac } require_command() { command -v "$1" >/dev/null 2>&1 || record unknown "missing_command:$1" } compose_ps() { docker compose --project-directory '{{ compose_project_dir }}' ps --all 2>&1 } check_compose() { local output output="$(compose_ps)" || { record critical 'compose_ps_failed'; return; } if grep -qiE 'Exited|Restarting|[[:space:]]Dead[[:space:]]' <<<"$output"; then record critical 'compose_unhealthy_container' else record ok 'compose_ok' fi } check_backup_freshness() { local pattern="$1" newest now age newest="$(find {{ compose_project_dir | quote }} -type f -path "$pattern" -printf '%T@\n' 2>/dev/null | sort -nr | head -n1)" if [[ -z "$newest" ]]; then record warning 'backup_not_found' return fi now="$(date +%s)" age="$(( now - ${newest%.*} ))" if (( age > {{ healthcheck_backup_max_age_hours }} * 3600 )); then record critical 'backup_stale' else record ok 'backup_fresh' fi } check_https() { local url="$1" expected="$2" code code="$(curl --silent --show-error --output /dev/null --write-out '%{http_code}' --max-time 20 "$url" 2>/dev/null)" || { record critical 'https_request_failed'; return; } [[ "$code" =~ $expected ]] && record ok "https_${code}" || record critical "https_${code}" } check_tls_days() { local host="$1" port="$2" expires epoch remaining expires="$(timeout 20 openssl s_client -connect "${host}:${port}" -servername "$host" /dev/null | openssl x509 -noout -enddate 2>/dev/null | cut -d= -f2-)" || { record unknown 'tls_read_failed'; return; } epoch="$(date -d "$expires" +%s 2>/dev/null)" || { record unknown 'tls_date_parse_failed'; return; } remaining="$(( (epoch - $(date +%s)) / 86400 ))" if (( remaining < 0 )); then record critical 'tls_expired' elif (( remaining < {{ healthcheck_tls_warn_days }} )); then record warning 'tls_near_expiry' else record ok 'tls_valid'; fi } emit_result() { local tmp detail_json tmp="$(mktemp "${RESULT_DIR}/latest.json.XXXXXX")" detail_json="$(printf '%s\n' "${DETAILS[@]:-unknown:no_details}" | python3 -c 'import json,sys; print(json.dumps([line.rstrip() for line in sys.stdin if line.strip()]))')" python3 - "$tmp" "$HOST_NAME" "$CHECK_NAME" "$STATUS" "$EXIT_CODE" "$detail_json" <<'PY' import json, sys path, host, check, status, code, details = sys.argv[1:] with open(path, 'w', encoding='utf-8') as f: json.dump({'schema': 1, 'host': host, 'check': check, 'status': status, 'exit_code': int(code), 'details': json.loads(details)}, f, sort_keys=True, separators=(',', ':')) f.write('\n') PY chmod 0640 "$tmp" mv "$tmp" "${RESULT_DIR}/latest.json" cat "${RESULT_DIR}/latest.json" }