added failover script and other sytem scripts
This commit is contained in:
@@ -0,0 +1,198 @@
|
||||
#!/bin/bash
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
# --------------------------------- WebGUI Watchdog --------------------------------------------
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
# Monitors unRAID's WebGUI and restarts it if unresponsive.
|
||||
# Uses an escalating restart strategy — tries nginx first, then emhttp if needed.
|
||||
# emhttp is the unRAID management daemon — restarting it is more disruptive than nginx
|
||||
# but recovers cleanly. Notification sent on any restart so you know what happened.
|
||||
#
|
||||
# Escalation path:
|
||||
# Check WebGUI → unresponsive → restart nginx → recheck
|
||||
# Still unresponsive → restart emhttp → recheck
|
||||
# Still unresponsive → notify warning, manual intervention needed
|
||||
#
|
||||
# Run every 5-10 minutes via cron/User Scripts plugin.
|
||||
# All configuration in Master.conf under WebGUI Watchdog section.
|
||||
# Supports --dry-run to show what would be restarted without acting.
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
|
||||
source "$SCRIPT_DIR/../Master.conf"
|
||||
source "$SCRIPT_DIR/../common.sh"
|
||||
|
||||
parse_args "$@"
|
||||
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
# ━━━ $ICON_GEAR Setup ━━━
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
echo ""
|
||||
echo "━━━ $ICON_GEAR Setup ━━━"
|
||||
|
||||
if [[ "$EUID" -ne 0 ]]; then
|
||||
error "Must be run as root"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
success "Running as root"
|
||||
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
# ━━━ $ICON_SUMMARY Status ━━━
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
if [[ "$SHOW_STATUS" == true ]]; then
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY STATUS ━━━━━"
|
||||
echo "$ICON_WEBGUI URL: $WEBGUI_URL"
|
||||
echo "$ICON_WEBGUI Curl timeout: ${WEBGUI_TIMEOUT}s"
|
||||
echo "$ICON_WEBGUI Nginx wait: ${WEBGUI_NGINX_WAIT}s"
|
||||
echo "$ICON_WEBGUI emhttp wait: ${WEBGUI_EMHTTP_WAIT}s"
|
||||
echo "$ICON_GEAR Dry Run: $DRY_RUN"
|
||||
|
||||
# Show current state
|
||||
if curl -sf --max-time "$WEBGUI_TIMEOUT" "$WEBGUI_URL" >/dev/null 2>&1; then
|
||||
echo "$ICON_WEBGUI WebGUI: $ICON_RUNNING responding"
|
||||
else
|
||||
echo "$ICON_WEBGUI WebGUI: $ICON_NOT_RUNNING not responding"
|
||||
fi
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
[[ "$DRY_RUN" == true ]] && warn "DRY RUN — no services will be restarted"
|
||||
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
# FUNCTIONS
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
|
||||
# Check if WebGUI is responding
|
||||
check_webgui() {
|
||||
curl -sf --max-time "$WEBGUI_TIMEOUT" "$WEBGUI_URL" >/dev/null 2>&1
|
||||
}
|
||||
|
||||
# Restart nginx — lightweight fix, try first
|
||||
restart_nginx() {
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — would restart nginx"
|
||||
return 0
|
||||
fi
|
||||
|
||||
info "$ICON_WEBGUI Restarting nginx..."
|
||||
if /etc/rc.d/rc.nginx restart >/dev/null 2>&1; then
|
||||
success "nginx restarted"
|
||||
return 0
|
||||
else
|
||||
error "nginx restart failed"
|
||||
return 1
|
||||
fi
|
||||
}
|
||||
|
||||
# Restart emhttp — heavier fix, escalate if nginx didn't help
|
||||
# emhttp drives the array, Docker management, shares — recovers cleanly but takes longer
|
||||
restart_emhttp() {
|
||||
if [[ "$DRY_RUN" == true ]]; then
|
||||
warn "DRY RUN — would restart emhttp"
|
||||
return 0
|
||||
fi
|
||||
|
||||
info "$ICON_WEBGUI Restarting emhttp..."
|
||||
if /etc/rc.d/rc.emhttp restart >/dev/null 2>&1; then
|
||||
success "emhttp restarted"
|
||||
return 0
|
||||
else
|
||||
error "emhttp restart failed"
|
||||
return 1
|
||||
fi
|
||||
}
|
||||
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
# ━━━ $ICON_WEBGUI WebGUI Watchdog ━━━
|
||||
# -----------------------------------------------------------------------------------------------
|
||||
echo ""
|
||||
echo "━━━ $ICON_WEBGUI WebGUI Watchdog — $(date '+%Y-%m-%d %H:%M:%S') ━━━"
|
||||
echo "$ICON_WEBGUI URL: $WEBGUI_URL"
|
||||
echo ""
|
||||
|
||||
START=$(date +%s)
|
||||
|
||||
# Initial check
|
||||
info "Checking WebGUI..."
|
||||
|
||||
if check_webgui; then
|
||||
success "$ICON_WEBGUI WebGUI is responding — nothing to do"
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY WEBGUI WATCHDOG SUMMARY ━━━━━"
|
||||
echo "$ICON_WEBGUI Status: $ICON_RUNNING HEALTHY"
|
||||
echo "$ICON_TIME Duration: $(format_duration $(($(date +%s) - START)))"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# WebGUI not responding — begin escalation
|
||||
warn "$ICON_WEBGUI WebGUI is not responding at $WEBGUI_URL"
|
||||
|
||||
# ── Step 1: Restart nginx ──
|
||||
echo ""
|
||||
echo "━━━ $ICON_WEBGUI Step 1 — Nginx Restart ━━━"
|
||||
|
||||
restart_nginx
|
||||
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
info "Waiting ${WEBGUI_NGINX_WAIT}s for nginx to recover..."
|
||||
sleep "$WEBGUI_NGINX_WAIT"
|
||||
|
||||
if check_webgui; then
|
||||
success "$ICON_WEBGUI WebGUI recovered after nginx restart"
|
||||
notify "WebGUI recovered on $(hostname) after nginx restart" "WebGUI Watchdog" "warning"
|
||||
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY WEBGUI WATCHDOG SUMMARY ━━━━━"
|
||||
echo "$ICON_WEBGUI Status: $ICON_SUCCESS RECOVERED via nginx restart"
|
||||
echo "$ICON_TIME Duration: $(format_duration $(($(date +%s) - START)))"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
warn "WebGUI still not responding after nginx restart — escalating to emhttp"
|
||||
fi
|
||||
|
||||
# ── Step 2: Restart emhttp ──
|
||||
echo ""
|
||||
echo "━━━ $ICON_WEBGUI Step 2 — emhttp Restart ━━━"
|
||||
warn "Restarting emhttp — this is the unRAID management daemon"
|
||||
warn "Array, Docker management and shares remain running but WebGUI will be briefly unavailable"
|
||||
|
||||
restart_emhttp
|
||||
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
info "Waiting ${WEBGUI_EMHTTP_WAIT}s for emhttp to recover..."
|
||||
sleep "$WEBGUI_EMHTTP_WAIT"
|
||||
|
||||
if check_webgui; then
|
||||
success "$ICON_WEBGUI WebGUI recovered after emhttp restart"
|
||||
notify "WebGUI recovered on $(hostname) after emhttp restart — check system health" "WebGUI Watchdog" "warning"
|
||||
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY WEBGUI WATCHDOG SUMMARY ━━━━━"
|
||||
echo "$ICON_WEBGUI Status: $ICON_SUCCESS RECOVERED via emhttp restart"
|
||||
echo "$ICON_TIME Duration: $(format_duration $(($(date +%s) - START)))"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
exit 0
|
||||
fi
|
||||
fi
|
||||
|
||||
# ── Both restarts failed ──
|
||||
END=$(date +%s)
|
||||
|
||||
echo ""
|
||||
echo "━━━━━ $ICON_SUMMARY WEBGUI WATCHDOG SUMMARY ━━━━━"
|
||||
echo "$ICON_WEBGUI Status: $ICON_ERROR UNRECOVERED — manual intervention needed"
|
||||
echo "$ICON_TIME Duration: $(format_duration $((END - START)))"
|
||||
echo "━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━"
|
||||
|
||||
if [[ "$DRY_RUN" == false ]]; then
|
||||
notify "WebGUI unrecovered on $(hostname) after nginx and emhttp restart — manual intervention needed" "WebGUI Watchdog" "warning"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
exit 0
|
||||
Reference in New Issue
Block a user