Files
Varaverk/Monitors/cert_monitor.sh
T
Gmer4Lfe 369a9e6c19 Platform adapter: rename System_Essentials, add Plugin/unraid/adapter.sh, wire call sites
- Rename unRAID_Essentials/ → System_Essentials/ (git detects as rename)
- Add Plugin/unraid/adapter.sh: 13 platform_*() functions providing OS-agnostic API
  for storage health, service management, mover, user scripts, notifications,
  disk temps, and platform command validation
- Update load_config.sh: detect PLATFORM (unraid/truenas/unknown), export SCRIPTS_DIR,
  auto-source Plugin/$PLATFORM/adapter.sh after common.sh
- Wire all call sites: replace direct rc.d, pgrep/pkill, var.ini, dynamix.cfg,
  disks.ini, and validate_unraid_cmd calls with platform_*() functions across
  watchdogs, orchestrators, and System_Essentials scripts
- Update all documentation: rename refs, update webgui escalation logic,
  add platform adapter section to Plugin README, update main README with
  portability vision and corrected self-healing stack description
2026-06-04 18:14:34 -04:00

282 lines
12 KiB
Bash
Executable File

#!/bin/bash
# ==============================================================================================
# ============================= Certificate Monitor ============================================
# ==============================================================================================
#
# PURPOSE
# ─────────────────────────────────────────────────────────────────────────────
# SSL certificate expiry monitoring for all configured domains. Scheduled weekly
# (Sunday 9am). Connects via openssl directly to each domain — not to NPM's API,
# not to any internal check, but to the actual TLS handshake the outside world sees.
#
# Per domain: HEALTHY (> CERT_WARN_DAYS remaining, silent) | WARNING (≤ CERT_WARN_DAYS)
# | CRITICAL (≤ CERT_CRIT_DAYS) | FAILED (could not connect or parse cert).
# Notifications batched by severity — one message lists all WARNING domains, a
# separate message lists all CRITICAL domains. Not one notification per domain.
#
# ==============================================================================================
# DESIGN PRINCIPLES
# ==============================================================================================
#
# Direct openssl, Not an API
# API-based cert checks ask the certificate manager whether the cert is valid.
# openssl checks ask the server what cert it is actually serving. These are not
# the same question and the answers can differ. Catches: cert renewed in NPM but
# server not reloaded (old cert still serving), wrong cert being served to external
# clients, chain issues visible externally but not internally, NPM reporting healthy
# while the outside world sees an expired cert.
#
# ==============================================================================================
# OPERATIONAL SAFEGUARDS
# ==============================================================================================
#
# Single Instance Lock
# acquire_lock prevents concurrent runs producing duplicate notifications.
#
# Per-Host Domain List
# detect_hosts() aliases HOST*_CERT_MONITOR_DOMAINS → CERT_MONITOR_DOMAINS.
# Each server monitors its own domains only.
#
# Empty Array Guard
# Warns and exits cleanly if CERT_MONITOR_DOMAINS is empty — no silent no-op.
#
# Connection Timeout
# CERT_TIMEOUT caps each openssl connection attempt. One unreachable domain
# does not block the remaining domains.
#
# Notification Validated
# platform_require_cmd confirms openssl and notify script are present before use.
#
# ==============================================================================================
# CONFIGURATION
# ==============================================================================================
#
# host*.conf
#
# HOST*_CERT_MONITOR_DOMAINS
# Domains this host monitors. Each domain and subdomain is a separate entry —
# they have independent certs. Aliased by detect_hosts() → CERT_MONITOR_DOMAINS.
#
# master.conf
#
# CERT_WARN_DAYS
# Days before expiry at which to send a warning notification. (default: 30)
#
# CERT_CRIT_DAYS
# Days before expiry at which to send a critical notification. (default: 7)
#
# CERT_TIMEOUT
# Seconds to wait per domain before declaring FAILED. (default: 10)
#
# ==============================================================================================
# RUNTIME MODES
# ==============================================================================================
#
# cert_monitor.sh
# Check all configured domains and notify on WARNING, CRITICAL, or FAILED.
# Silent when all domains are healthy.
#
# cert_monitor.sh --dry-run
# Check all domains and show results. No notifications sent regardless of result.
#
# cert_monitor.sh --status
# Show domain list, warning thresholds, and timeout. Then exit.
#
# cert_monitor.sh --log
# Verbose per-domain output during the run.
#
# ==============================================================================================
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
source "$SCRIPT_DIR/../load_config.sh"
parse_args "$@"
# ==============================================================================================
# ━━━ Setup ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_GEAR Setup ━━━"
if [[ "$EUID" -ne 0 ]]; then
error "Must be run as root"
exit 1
fi
# Validate openssl — required for all cert checks
platform_require_cmd \
"$(command -v openssl 2>/dev/null || echo /usr/bin/openssl)" \
"version" "OpenSSL" \
"openssl" || { error "openssl not found — required for certificate checks"; exit 1; }
platform_require_cmd \
"/usr/local/emhttp/plugins/dynamix/scripts/notify" \
"" "" \
"unRAID notify script" || warn "unRAID notify script not found — native notifications disabled"
acquire_lock
# detect_hosts() sets MY_ID and aliases HOST*_CERT_MONITOR_DOMAINS
detect_hosts
# Empty array guard
if [[ ${#CERT_MONITOR_DOMAINS[@]} -eq 0 ]]; then
warn "CERT_MONITOR_DOMAINS is empty for $MY_ID"
warn "Check HOST*_CERT_MONITOR_DOMAINS in host*.conf"
exit 0
fi
info "Domains to check: ${#CERT_MONITOR_DOMAINS[@]}"
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — results shown but no notifications sent"
# ==============================================================================================
# ━━━ Status ━━━
# ==============================================================================================
if [[ "$SHOW_STATUS" == true ]]; then
echo ""
echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_CERT Domains: ${CERT_MONITOR_DOMAINS[*]}"
echo "$ICON_WARN Warn at: ${CERT_WARN_DAYS} days remaining"
echo "$ICON_ERROR Crit at: ${CERT_CRIT_DAYS} days remaining"
echo "$ICON_TIME Timeout: ${CERT_TIMEOUT}s per domain"
echo "$ICON_GEAR Dry Run: $DRY_RUN"
echo "━━━━━━━━━━━━━━━━━━━━━━━"
exit 0
fi
# ==============================================================================================
# ── CERT CHECK FUNCTION ───────────────────────────────────────────────────────────────────────
# ==============================================================================================
# Connects to domain:443 via openssl, extracts expiry date, calculates days remaining.
# Returns:
# 0 = healthy (> CERT_WARN_DAYS)
# 1 = warning (<= CERT_WARN_DAYS)
# 2 = critical (<= CERT_CRIT_DAYS)
# 3 = failed (could not connect or parse)
check_cert() {
local domain="$1"
local port="${2:-443}"
local expiry_str
expiry_str=$(echo | timeout "$CERT_TIMEOUT" openssl s_client \
-connect "${domain}:${port}" \
-servername "$domain" \
2>/dev/null | openssl x509 -noout -enddate 2>/dev/null | cut -d= -f2)
if [[ -z "$expiry_str" ]]; then
error "$ICON_CERT $domain — could not retrieve certificate (unreachable or no TLS)"
return 3
fi
local expiry_epoch
expiry_epoch=$(date -d "$expiry_str" +%s 2>/dev/null)
if [[ -z "$expiry_epoch" ]]; then
error "$ICON_CERT $domain — could not parse expiry date: $expiry_str"
return 3
fi
local now days_remaining expiry_display
now=$(date +%s)
days_remaining=$(( (expiry_epoch - now) / 86400 ))
expiry_display=$(date -d "$expiry_str" '+%Y-%m-%d' 2>/dev/null)
if [[ "$days_remaining" -le "$CERT_CRIT_DAYS" ]]; then
error "$ICON_CERT $domain — CRITICAL: ${days_remaining} days remaining (expires $expiry_display)"
return 2
elif [[ "$days_remaining" -le "$CERT_WARN_DAYS" ]]; then
warn "$ICON_CERT $domain — WARNING: ${days_remaining} days remaining (expires $expiry_display)"
return 1
else
log "$ICON_CERT $domain — OK: ${days_remaining} days remaining (expires $expiry_display)"
return 0
fi
}
# ==============================================================================================
# ━━━ Certificate Monitor ━━━
# ==============================================================================================
echo ""
echo "━━━ $ICON_CERT Certificate Monitor — $(date '+%Y-%m-%d %H:%M:%S') ━━━"
echo "$ICON_HOST $MY_ID ($LOCAL_SERVER_NAME)"
info "Warn threshold: ${CERT_WARN_DAYS} days"
info "Crit threshold: ${CERT_CRIT_DAYS} days"
echo ""
START=$(date +%s)
HEALTHY=()
WARNING=()
CRITICAL=()
FAILED=()
declare -A DOMAIN_STATUS
for domain in "${CERT_MONITOR_DOMAINS[@]}"; do
[[ -z "$domain" ]] && continue
check_cert "$domain"
result=$?
case $result in
0) HEALTHY+=("$domain"); DOMAIN_STATUS["$domain"]="OK" ;;
1) WARNING+=("$domain"); DOMAIN_STATUS["$domain"]="WARN" ;;
2) CRITICAL+=("$domain"); DOMAIN_STATUS["$domain"]="CRIT" ;;
3) FAILED+=("$domain"); DOMAIN_STATUS["$domain"]="FAIL" ;;
esac
done
END=$(date +%s)
# ── Send notifications — batched per severity ─────────────────────────────────────────────────
if [[ "$DRY_RUN" == false ]]; then
[[ ${#CRITICAL[@]} -gt 0 ]] && \
notify "Certificate CRITICAL on $(hostname) — expiring within ${CERT_CRIT_DAYS} days: ${CRITICAL[*]}" \
"Certificate Monitor" "warning"
[[ ${#WARNING[@]} -gt 0 ]] && \
notify "Certificate WARNING on $(hostname) — expiring within ${CERT_WARN_DAYS} days: ${WARNING[*]}" \
"Certificate Monitor" "warning"
[[ ${#FAILED[@]} -gt 0 ]] && \
notify "Certificate check FAILED on $(hostname) — could not reach: ${FAILED[*]}" \
"Certificate Monitor" "warning"
fi
# ==============================================================================================
# ━━━ Summary ━━━
# ==============================================================================================
echo ""
echo "━━━━━ $ICON_SUMMARY CERTIFICATE MONITOR SUMMARY ━━━━━"
echo "$ICON_HOST Identity: $MY_ID ($LOCAL_SERVER_NAME)"
echo "$ICON_TIME Duration: $(format_duration $(( END - START )))"
echo ""
echo " $ICON_SUCCESS Healthy: ${#HEALTHY[@]}"
[[ ${#WARNING[@]} -gt 0 ]] && warn "Warning: ${#WARNING[@]} — renewal recommended"
[[ ${#CRITICAL[@]} -gt 0 ]] && echo "$ICON_ERROR Critical: ${#CRITICAL[@]} — ACTION REQUIRED"
[[ ${#FAILED[@]} -gt 0 ]] && echo "$ICON_ERROR Failed: ${#FAILED[@]} — unreachable"
echo ""
# Per-domain results — only show problems, healthy ones stay in log()
for domain in "${CERT_MONITOR_DOMAINS[@]}"; do
[[ -z "$domain" ]] && continue
case "${DOMAIN_STATUS[$domain]:-UNKN}" in
OK) log " $ICON_SUCCESS $domain — healthy" ;;
WARN) warn " $ICON_WARN $domain — warning" ;;
CRIT) echo " $ICON_ERROR $domain — CRITICAL" ;;
FAIL) echo " $ICON_ERROR $domain — unreachable" ;;
esac
done
echo ""
if [[ "$DRY_RUN" == true ]]; then
warn "DRY RUN — no notifications sent"
elif [[ ${#CRITICAL[@]} -gt 0 || ${#FAILED[@]} -gt 0 ]]; then
echo "$ICON_ERROR Status: ACTION REQUIRED"
elif [[ ${#WARNING[@]} -gt 0 ]]; then
warn "Status: WARNINGS — renewal recommended"
else
echo "$ICON_DONE Status: all ${#HEALTHY[@]} certs healthy ✅"
fi
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
[[ ${#CRITICAL[@]} -gt 0 || ${#FAILED[@]} -gt 0 ]] && exit 1
exit 0